OpenCloudOS-Kernel/mm/vmalloc.c

3690 lines
93 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/vmalloc.c
*
* Copyright (C) 1993 Linus Torvalds
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
* SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
* Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
* Numa awareness, Christoph Lameter, SGI, June 2005
*/
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/highmem.h>
sched/headers: Move task_struct::signal and task_struct::sighand types and accessors into <linux/sched/signal.h> task_struct::signal and task_struct::sighand are pointers, which would normally make it straightforward to not define those types in sched.h. That is not so, because the types are accompanied by a myriad of APIs (macros and inline functions) that dereference them. Split the types and the APIs out of sched.h and move them into a new header, <linux/sched/signal.h>. With this change sched.h does not know about 'struct signal' and 'struct sighand' anymore, trying to put accessors into sched.h as a test fails the following way: ./include/linux/sched.h: In function ‘test_signal_types’: ./include/linux/sched.h:2461:18: error: dereferencing pointer to incomplete type ‘struct signal_struct’ ^ This reduces the size and complexity of sched.h significantly. Update all headers and .c code that relied on getting the signal handling functionality from <linux/sched.h> to include <linux/sched/signal.h>. The list of affected files in the preparatory patch was partly generated by grepping for the APIs, and partly by doing coverage build testing, both all[yes|mod|def|no]config builds on 64-bit and 32-bit x86, and an array of cross-architecture builds. Nevertheless some (trivial) build breakage is still expected related to rare Kconfig combinations and in-flight patches to various kernel code, but most of it should be handled by this patch. Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-02-02 15:35:14 +08:00
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
2008-04-28 17:12:40 +08:00
#include <linux/seq_file.h>
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
#include <linux/set_memory.h>
infrastructure to debug (dynamic) objects We can see an ever repeating problem pattern with objects of any kind in the kernel: 1) freeing of active objects 2) reinitialization of active objects Both problems can be hard to debug because the crash happens at a point where we have no chance to decode the root cause anymore. One problem spot are kernel timers, where the detection of the problem often happens in interrupt context and usually causes the machine to panic. While working on a timer related bug report I had to hack specialized code into the timer subsystem to get a reasonable hint for the root cause. This debug hack was fine for temporary use, but far from a mergeable solution due to the intrusiveness into the timer code. The code further lacked the ability to detect and report the root cause instantly and keep the system operational. Keeping the system operational is important to get hold of the debug information without special debugging aids like serial consoles and special knowledge of the bug reporter. The problems described above are not restricted to timers, but timers tend to expose it usually in a full system crash. Other objects are less explosive, but the symptoms caused by such mistakes can be even harder to debug. Instead of creating specialized debugging code for the timer subsystem a generic infrastructure is created which allows developers to verify their code and provides an easy to enable debug facility for users in case of trouble. The debugobjects core code keeps track of operations on static and dynamic objects by inserting them into a hashed list and sanity checking them on object operations and provides additional checks whenever kernel memory is freed. The tracked object operations are: - initializing an object - adding an object to a subsystem list - deleting an object from a subsystem list Each operation is sanity checked before the operation is executed and the subsystem specific code can provide a fixup function which allows to prevent the damage of the operation. When the sanity check triggers a warning message and a stack trace is printed. The list of operations can be extended if the need arises. For now it's limited to the requirements of the first user (timers). The core code enqueues the objects into hash buckets. The hash index is generated from the address of the object to simplify the lookup for the check on kfree/vfree. Each bucket has it's own spinlock to avoid contention on a global lock. The debug code can be compiled in without being active. The runtime overhead is minimal and could be optimized by asm alternatives. A kernel command line option enables the debugging code. Thanks to Ingo Molnar for review, suggestions and cleanup patches. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu> Cc: Greg KH <greg@kroah.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-30 15:55:01 +08:00
#include <linux/debugobjects.h>
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
#include <linux/kallsyms.h>
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
#include <linux/list.h>
#include <linux/notifier.h>
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
#include <linux/rbtree.h>
#include <linux/radix-tree.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
#include <linux/compiler.h>
#include <linux/llist.h>
mm: change __get_vm_area_node() to use fls_long() ioremap() and its related interfaces are used to create I/O mappings to memory-mapped I/O devices. The mapping sizes of the traditional I/O devices are relatively small. Non-volatile memory (NVM), however, has many GB and is going to have TB soon. It is not very efficient to create large I/O mappings with 4KB. This patchset extends the ioremap() interfaces to transparently create I/O mappings with huge pages whenever possible. ioremap() continues to use 4KB mappings when a huge page does not fit into a requested range. There is no change necessary to the drivers using ioremap(). A requested physical address must be aligned by a huge page size (1GB or 2MB on x86) for using huge page mapping, though. The kernel huge I/O mapping will improve performance of NVM and other devices with large memory, and reduce the time to create their mappings as well. On x86, MTRRs can override PAT memory types with a 4KB granularity. When using a huge page, MTRRs can override the memory type of the huge page, which may lead a performance penalty. The processor can also behave in an undefined manner if a huge page is mapped to a memory range that MTRRs have mapped with multiple different memory types. Therefore, the mapping code falls back to use a smaller page size toward 4KB when a mapping range is covered by non-WB type of MTRRs. The WB type of MTRRs has no affect on the PAT memory types. The patchset introduces HAVE_ARCH_HUGE_VMAP, which indicates that the arch supports huge KVA mappings for ioremap(). User may specify a new kernel option "nohugeiomap" to disable the huge I/O mapping capability of ioremap() when necessary. Patch 1-4 change common files to support huge I/O mappings. There is no change in the functinalities unless HAVE_ARCH_HUGE_VMAP is defined on the architecture of the system. Patch 5-6 implement the HAVE_ARCH_HUGE_VMAP funcs on x86, and set HAVE_ARCH_HUGE_VMAP on x86. This patch (of 6): __get_vm_area_node() takes unsigned long size, which is a 64-bit value on a 64-bit kernel. However, fls(size) simply ignores the upper 32-bit. Change to use fls_long() to handle the size properly. Signed-off-by: Toshi Kani <toshi.kani@hp.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Robert Elliott <Elliott@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 06:47:17 +08:00
#include <linux/bitops.h>
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
#include <linux/rbtree_augmented.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
#include "internal.h"
bool is_vmalloc_addr(const void *x)
{
unsigned long addr = (unsigned long)x;
return addr >= VMALLOC_START && addr < VMALLOC_END;
}
EXPORT_SYMBOL(is_vmalloc_addr);
struct vfree_deferred {
struct llist_head list;
struct work_struct wq;
};
static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);
static void __vunmap(const void *, int);
static void free_work(struct work_struct *w)
{
struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
struct llist_node *t, *llnode;
llist_for_each_safe(llnode, t, llist_del_all(&p->list))
__vunmap((void *)llnode, 1);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*** Page table manipulation functions ***/
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
{
pte_t *pte;
pte = pte_offset_kernel(pmd, addr);
do {
pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte);
WARN_ON(!pte_none(ptent) && !pte_present(ptent));
} while (pte++, addr += PAGE_SIZE, addr != end);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_clear_huge(pmd))
continue;
if (pmd_none_or_clear_bad(pmd))
continue;
vunmap_pte_range(pmd, addr, next);
} while (pmd++, addr = next, addr != end);
}
static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(p4d, addr);
do {
next = pud_addr_end(addr, end);
if (pud_clear_huge(pud))
continue;
if (pud_none_or_clear_bad(pud))
continue;
vunmap_pmd_range(pud, addr, next);
} while (pud++, addr = next, addr != end);
}
static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_offset(pgd, addr);
do {
next = p4d_addr_end(addr, end);
if (p4d_clear_huge(p4d))
continue;
if (p4d_none_or_clear_bad(p4d))
continue;
vunmap_pud_range(p4d, addr, next);
} while (p4d++, addr = next, addr != end);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static void vunmap_page_range(unsigned long addr, unsigned long end)
{
pgd_t *pgd;
unsigned long next;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
vunmap_p4d_range(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pte_t *pte;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* nr is a running index into the array which helps higher level
* callers keep track of where we're up to.
*/
[PATCH] mm: init_mm without ptlock First step in pushing down the page_table_lock. init_mm.page_table_lock has been used throughout the architectures (usually for ioremap): not to serialize kernel address space allocation (that's usually vmlist_lock), but because pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it. Reverse that: don't lock or unlock init_mm.page_table_lock in any of the architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take and drop it when allocating a new one, to check lest a racing task already did. Similarly no page_table_lock in vmalloc's map_vm_area. Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle user mms, which are converted only by a later patch, for now they have to lock differently according to whether or not it's init_mm. If sources get muddled, there's a danger that an arch source taking init_mm.page_table_lock will be mixed with common source also taking it (or neither take it). So break the rules and make another change, which should break the build for such a mismatch: remove the redundant mm arg from pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13). Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64 used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64 map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free took page_table_lock for no good reason. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 09:16:21 +08:00
pte = pte_alloc_kernel(pmd, addr);
if (!pte)
return -ENOMEM;
do {
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
struct page *page = pages[*nr];
if (WARN_ON(!pte_none(*pte)))
return -EBUSY;
if (WARN_ON(!page))
return -ENOMEM;
set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
(*nr)++;
} while (pte++, addr += PAGE_SIZE, addr != end);
return 0;
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static int vmap_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_alloc(&init_mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
if (vmap_pte_range(pmd, addr, next, prot, pages, nr))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pud_t *pud;
unsigned long next;
pud = pud_alloc(&init_mm, p4d, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
p4d_t *p4d;
unsigned long next;
p4d = p4d_alloc(&init_mm, pgd, addr);
if (!p4d)
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
* will have pfns corresponding to the "pages" array.
*
* Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
*/
static int vmap_page_range_noflush(unsigned long start, unsigned long end,
pgprot_t prot, struct page **pages)
{
pgd_t *pgd;
unsigned long next;
unsigned long addr = start;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
int err = 0;
int nr = 0;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return nr;
}
static int vmap_page_range(unsigned long start, unsigned long end,
pgprot_t prot, struct page **pages)
{
int ret;
ret = vmap_page_range_noflush(start, end, prot, pages);
flush_cache_vmap(start, end);
return ret;
}
int is_vmalloc_or_module_addr(const void *x)
{
/*
* ARM, x86-64 and sparc64 put modules in a special place,
* and fall back on vmalloc() if that fails. Others
* just put it in the vmalloc space.
*/
#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
unsigned long addr = (unsigned long)x;
if (addr >= MODULES_VADDR && addr < MODULES_END)
return 1;
#endif
return is_vmalloc_addr(x);
}
/*
* Walk a vmap address to the struct page it maps.
*/
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
unsigned long addr = (unsigned long) vmalloc_addr;
struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
/*
* XXX we might need to change this if we add VIRTUAL_BUG_ON for
* architectures that do not vmalloc module space
*/
VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
if (pgd_none(*pgd))
return NULL;
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d))
return NULL;
pud = pud_offset(p4d, addr);
mm/vmalloc.c: huge-vmap: fail gracefully on unexpected huge vmap mappings Existing code that uses vmalloc_to_page() may assume that any address for which is_vmalloc_addr() returns true may be passed into vmalloc_to_page() to retrieve the associated struct page. This is not un unreasonable assumption to make, but on architectures that have CONFIG_HAVE_ARCH_HUGE_VMAP=y, it no longer holds, and we need to ensure that vmalloc_to_page() does not go off into the weeds trying to dereference huge PUDs or PMDs as table entries. Given that vmalloc() and vmap() themselves never create huge mappings or deal with compound pages at all, there is no correct answer in this case, so return NULL instead, and issue a warning. When reading /proc/kcore on arm64, you will hit an oops as soon as you hit the huge mappings used for the various segments that make up the mapping of vmlinux. With this patch applied, you will no longer hit the oops, but the kcore contents willl be incorrect (these regions will be zeroed out) We are fixing this for kcore specifically, so it avoids vread() for those regions. At least one other problematic user exists, i.e., /dev/kmem, but that is currently broken on arm64 for other reasons. Link: http://lkml.kernel.org/r/20170609082226.26152-1-ard.biesheuvel@linaro.org Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Laura Abbott <labbott@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: zhong jiang <zhongjiang@huawei.com> Cc: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-24 06:08:41 +08:00
/*
* Don't dereference bad PUD or PMD (below) entries. This will also
* identify huge mappings, which we may encounter on architectures
* that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
* identified as vmalloc addresses by is_vmalloc_addr(), but are
* not [unambiguously] associated with a struct page, so there is
* no correct value to return for them.
*/
WARN_ON_ONCE(pud_bad(*pud));
if (pud_none(*pud) || pud_bad(*pud))
return NULL;
pmd = pmd_offset(pud, addr);
mm/vmalloc.c: huge-vmap: fail gracefully on unexpected huge vmap mappings Existing code that uses vmalloc_to_page() may assume that any address for which is_vmalloc_addr() returns true may be passed into vmalloc_to_page() to retrieve the associated struct page. This is not un unreasonable assumption to make, but on architectures that have CONFIG_HAVE_ARCH_HUGE_VMAP=y, it no longer holds, and we need to ensure that vmalloc_to_page() does not go off into the weeds trying to dereference huge PUDs or PMDs as table entries. Given that vmalloc() and vmap() themselves never create huge mappings or deal with compound pages at all, there is no correct answer in this case, so return NULL instead, and issue a warning. When reading /proc/kcore on arm64, you will hit an oops as soon as you hit the huge mappings used for the various segments that make up the mapping of vmlinux. With this patch applied, you will no longer hit the oops, but the kcore contents willl be incorrect (these regions will be zeroed out) We are fixing this for kcore specifically, so it avoids vread() for those regions. At least one other problematic user exists, i.e., /dev/kmem, but that is currently broken on arm64 for other reasons. Link: http://lkml.kernel.org/r/20170609082226.26152-1-ard.biesheuvel@linaro.org Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Laura Abbott <labbott@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: zhong jiang <zhongjiang@huawei.com> Cc: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-24 06:08:41 +08:00
WARN_ON_ONCE(pmd_bad(*pmd));
if (pmd_none(*pmd) || pmd_bad(*pmd))
return NULL;
ptep = pte_offset_map(pmd, addr);
pte = *ptep;
if (pte_present(pte))
page = pte_page(pte);
pte_unmap(ptep);
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
/*
* Map a vmalloc()-space virtual address to the physical page frame number.
*/
unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
{
return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*** Global kva allocator ***/
#define DEBUG_AUGMENT_PROPAGATE_CHECK 0
#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static DEFINE_SPINLOCK(vmap_area_lock);
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
static DEFINE_SPINLOCK(free_vmap_area_lock);
/* Export for kexec only */
LIST_HEAD(vmap_area_list);
static LLIST_HEAD(vmap_purge_list);
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
static struct rb_root vmap_area_root = RB_ROOT;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static bool vmap_initialized __read_mostly;
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* This kmem_cache is used for vmap_area objects. Instead of
* allocating from slab we reuse an object from this cache to
* make things faster. Especially in "no edge" splitting of
* free block.
*/
static struct kmem_cache *vmap_area_cachep;
/*
* This linked list is used in pair with free_vmap_area_root.
* It gives O(1) access to prev/next to perform fast coalescing.
*/
static LIST_HEAD(free_vmap_area_list);
/*
* This augment red-black tree represents the free vmap space.
* All vmap_area objects in this tree are sorted by va->va_start
* address. It is used for allocation and merging when a vmap
* object is released.
*
* Each vmap_area node contains a maximum available free block
* of its sub-tree, right or left. Therefore it is possible to
* find a lowest match of free area.
*/
static struct rb_root free_vmap_area_root = RB_ROOT;
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
/*
* Preload a CPU with one object for "no edge" split case. The
* aim is to get rid of allocations from the atomic context, thus
* to use more permissive allocation masks.
*/
static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static __always_inline unsigned long
va_size(struct vmap_area *va)
{
return (va->va_end - va->va_start);
}
static __always_inline unsigned long
get_subtree_max_size(struct rb_node *node)
{
struct vmap_area *va;
va = rb_entry_safe(node, struct vmap_area, rb_node);
return va ? va->subtree_max_size : 0;
}
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* Gets called when remove the node and rotate.
*/
static __always_inline unsigned long
compute_subtree_max_size(struct vmap_area *va)
{
return max3(va_size(va),
get_subtree_max_size(va->rb_node.rb_left),
get_subtree_max_size(va->rb_node.rb_right));
}
RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb,
struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size)
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static void purge_vmap_area_lazy(void);
static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
static unsigned long lazy_max_pages(void);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static atomic_long_t nr_vmalloc_pages;
unsigned long vmalloc_nr_pages(void)
{
return atomic_long_read(&nr_vmalloc_pages);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static struct vmap_area *__find_vmap_area(unsigned long addr)
{
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
struct rb_node *n = vmap_area_root.rb_node;
while (n) {
struct vmap_area *va;
va = rb_entry(n, struct vmap_area, rb_node);
if (addr < va->va_start)
n = n->rb_left;
else if (addr >= va->va_end)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
n = n->rb_right;
else
return va;
}
return NULL;
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* This function returns back addresses of parent node
* and its left or right link for further processing.
*/
static __always_inline struct rb_node **
find_va_links(struct vmap_area *va,
struct rb_root *root, struct rb_node *from,
struct rb_node **parent)
{
struct vmap_area *tmp_va;
struct rb_node **link;
if (root) {
link = &root->rb_node;
if (unlikely(!*link)) {
*parent = NULL;
return link;
}
} else {
link = &from;
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* Go to the bottom of the tree. When we hit the last point
* we end up with parent rb_node and correct direction, i name
* it link, where the new va->rb_node will be attached to.
*/
do {
tmp_va = rb_entry(*link, struct vmap_area, rb_node);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* During the traversal we also do some sanity check.
* Trigger the BUG() if there are sides(left/right)
* or full overlaps.
*/
if (va->va_start < tmp_va->va_end &&
va->va_end <= tmp_va->va_start)
link = &(*link)->rb_left;
else if (va->va_end > tmp_va->va_start &&
va->va_start >= tmp_va->va_end)
link = &(*link)->rb_right;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
else
BUG();
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
} while (*link);
*parent = &tmp_va->rb_node;
return link;
}
static __always_inline struct list_head *
get_va_next_sibling(struct rb_node *parent, struct rb_node **link)
{
struct list_head *list;
if (unlikely(!parent))
/*
* The red-black tree where we try to find VA neighbors
* before merging or inserting is empty, i.e. it means
* there is no free vmap space. Normally it does not
* happen but we handle this case anyway.
*/
return NULL;
list = &rb_entry(parent, struct vmap_area, rb_node)->list;
return (&parent->rb_right == link ? list->next : list);
}
static __always_inline void
link_va(struct vmap_area *va, struct rb_root *root,
struct rb_node *parent, struct rb_node **link, struct list_head *head)
{
/*
* VA is still not in the list, but we can
* identify its future previous list_head node.
*/
if (likely(parent)) {
head = &rb_entry(parent, struct vmap_area, rb_node)->list;
if (&parent->rb_right != link)
head = head->prev;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/* Insert to the rb-tree */
rb_link_node(&va->rb_node, parent, link);
if (root == &free_vmap_area_root) {
/*
* Some explanation here. Just perform simple insertion
* to the tree. We do not set va->subtree_max_size to
* its current size before calling rb_insert_augmented().
* It is because of we populate the tree from the bottom
* to parent levels when the node _is_ in the tree.
*
* Therefore we set subtree_max_size to zero after insertion,
* to let __augment_tree_propagate_from() puts everything to
* the correct order later on.
*/
rb_insert_augmented(&va->rb_node,
root, &free_vmap_area_rb_augment_cb);
va->subtree_max_size = 0;
} else {
rb_insert_color(&va->rb_node, root);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/* Address-sort this list */
list_add(&va->list, head);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static __always_inline void
unlink_va(struct vmap_area *va, struct rb_root *root)
{
if (WARN_ON(RB_EMPTY_NODE(&va->rb_node)))
return;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
if (root == &free_vmap_area_root)
rb_erase_augmented(&va->rb_node,
root, &free_vmap_area_rb_augment_cb);
else
rb_erase(&va->rb_node, root);
list_del(&va->list);
RB_CLEAR_NODE(&va->rb_node);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
}
#if DEBUG_AUGMENT_PROPAGATE_CHECK
static void
augment_tree_propagate_check(struct rb_node *n)
{
struct vmap_area *va;
struct rb_node *node;
unsigned long size;
bool found = false;
if (n == NULL)
return;
va = rb_entry(n, struct vmap_area, rb_node);
size = va->subtree_max_size;
node = n;
while (node) {
va = rb_entry(node, struct vmap_area, rb_node);
if (get_subtree_max_size(node->rb_left) == size) {
node = node->rb_left;
} else {
if (va_size(va) == size) {
found = true;
break;
}
node = node->rb_right;
}
}
if (!found) {
va = rb_entry(n, struct vmap_area, rb_node);
pr_emerg("tree is corrupted: %lu, %lu\n",
va_size(va), va->subtree_max_size);
}
augment_tree_propagate_check(n->rb_left);
augment_tree_propagate_check(n->rb_right);
}
#endif
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* This function populates subtree_max_size from bottom to upper
* levels starting from VA point. The propagation must be done
* when VA size is modified by changing its va_start/va_end. Or
* in case of newly inserting of VA to the tree.
*
* It means that __augment_tree_propagate_from() must be called:
* - After VA has been inserted to the tree(free path);
* - After VA has been shrunk(allocation path);
* - After VA has been increased(merging path).
*
* Please note that, it does not mean that upper parent nodes
* and their subtree_max_size are recalculated all the time up
* to the root node.
*
* 4--8
* /\
* / \
* / \
* 2--2 8--8
*
* For example if we modify the node 4, shrinking it to 2, then
* no any modification is required. If we shrink the node 2 to 1
* its subtree_max_size is updated only, and set to 1. If we shrink
* the node 8 to 6, then its subtree_max_size is set to 6 and parent
* node becomes 4--6.
*/
static __always_inline void
augment_tree_propagate_from(struct vmap_area *va)
{
struct rb_node *node = &va->rb_node;
unsigned long new_va_sub_max_size;
while (node) {
va = rb_entry(node, struct vmap_area, rb_node);
new_va_sub_max_size = compute_subtree_max_size(va);
/*
* If the newly calculated maximum available size of the
* subtree is equal to the current one, then it means that
* the tree is propagated correctly. So we have to stop at
* this point to save cycles.
*/
if (va->subtree_max_size == new_va_sub_max_size)
break;
va->subtree_max_size = new_va_sub_max_size;
node = rb_parent(&va->rb_node);
}
#if DEBUG_AUGMENT_PROPAGATE_CHECK
augment_tree_propagate_check(free_vmap_area_root.rb_node);
#endif
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
}
static void
insert_vmap_area(struct vmap_area *va,
struct rb_root *root, struct list_head *head)
{
struct rb_node **link;
struct rb_node *parent;
link = find_va_links(va, root, NULL, &parent);
link_va(va, root, parent, link, head);
}
static void
insert_vmap_area_augment(struct vmap_area *va,
struct rb_node *from, struct rb_root *root,
struct list_head *head)
{
struct rb_node **link;
struct rb_node *parent;
if (from)
link = find_va_links(va, NULL, from, &parent);
else
link = find_va_links(va, root, NULL, &parent);
link_va(va, root, parent, link, head);
augment_tree_propagate_from(va);
}
/*
* Merge de-allocated chunk of VA memory with previous
* and next free blocks. If coalesce is not done a new
* free area is inserted. If VA has been merged, it is
* freed.
*/
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
static __always_inline struct vmap_area *
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
merge_or_add_vmap_area(struct vmap_area *va,
struct rb_root *root, struct list_head *head)
{
struct vmap_area *sibling;
struct list_head *next;
struct rb_node **link;
struct rb_node *parent;
bool merged = false;
/*
* Find a place in the tree where VA potentially will be
* inserted, unless it is merged with its sibling/siblings.
*/
link = find_va_links(va, root, NULL, &parent);
/*
* Get next node of VA to check if merging can be done.
*/
next = get_va_next_sibling(parent, link);
if (unlikely(next == NULL))
goto insert;
/*
* start end
* | |
* |<------VA------>|<-----Next----->|
* | |
* start end
*/
if (next != head) {
sibling = list_entry(next, struct vmap_area, list);
if (sibling->va_start == va->va_end) {
sibling->va_start = va->va_start;
/* Check and update the tree if needed. */
augment_tree_propagate_from(sibling);
/* Free vmap_area object. */
kmem_cache_free(vmap_area_cachep, va);
/* Point to the new merged area. */
va = sibling;
merged = true;
}
}
/*
* start end
* | |
* |<-----Prev----->|<------VA------>|
* | |
* start end
*/
if (next->prev != head) {
sibling = list_entry(next->prev, struct vmap_area, list);
if (sibling->va_end == va->va_start) {
sibling->va_end = va->va_end;
/* Check and update the tree if needed. */
augment_tree_propagate_from(sibling);
if (merged)
unlink_va(va, root);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/* Free vmap_area object. */
kmem_cache_free(vmap_area_cachep, va);
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
/* Point to the new merged area. */
va = sibling;
merged = true;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
}
}
insert:
if (!merged) {
link_va(va, root, parent, link, head);
augment_tree_propagate_from(va);
}
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
return va;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
}
static __always_inline bool
is_within_this_va(struct vmap_area *va, unsigned long size,
unsigned long align, unsigned long vstart)
{
unsigned long nva_start_addr;
if (va->va_start > vstart)
nva_start_addr = ALIGN(va->va_start, align);
else
nva_start_addr = ALIGN(vstart, align);
/* Can be overflowed due to big size or alignment. */
if (nva_start_addr + size < nva_start_addr ||
nva_start_addr < vstart)
return false;
return (nva_start_addr + size <= va->va_end);
}
/*
* Find the first free block(lowest start address) in the tree,
* that will accomplish the request corresponding to passing
* parameters.
*/
static __always_inline struct vmap_area *
find_vmap_lowest_match(unsigned long size,
unsigned long align, unsigned long vstart)
{
struct vmap_area *va;
struct rb_node *node;
unsigned long length;
/* Start from the root. */
node = free_vmap_area_root.rb_node;
/* Adjust the search size for alignment overhead. */
length = size + align - 1;
while (node) {
va = rb_entry(node, struct vmap_area, rb_node);
if (get_subtree_max_size(node->rb_left) >= length &&
vstart < va->va_start) {
node = node->rb_left;
} else {
if (is_within_this_va(va, size, align, vstart))
return va;
/*
* Does not make sense to go deeper towards the right
* sub-tree if it does not have a free block that is
* equal or bigger to the requested search length.
*/
if (get_subtree_max_size(node->rb_right) >= length) {
node = node->rb_right;
continue;
}
/*
* OK. We roll back and find the first right sub-tree,
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* that will satisfy the search criteria. It can happen
* only once due to "vstart" restriction.
*/
while ((node = rb_parent(node))) {
va = rb_entry(node, struct vmap_area, rb_node);
if (is_within_this_va(va, size, align, vstart))
return va;
if (get_subtree_max_size(node->rb_right) >= length &&
vstart <= va->va_start) {
node = node->rb_right;
break;
}
}
}
}
return NULL;
}
#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
#include <linux/random.h>
static struct vmap_area *
find_vmap_lowest_linear_match(unsigned long size,
unsigned long align, unsigned long vstart)
{
struct vmap_area *va;
list_for_each_entry(va, &free_vmap_area_list, list) {
if (!is_within_this_va(va, size, align, vstart))
continue;
return va;
}
return NULL;
}
static void
find_vmap_lowest_match_check(unsigned long size)
{
struct vmap_area *va_1, *va_2;
unsigned long vstart;
unsigned int rnd;
get_random_bytes(&rnd, sizeof(rnd));
vstart = VMALLOC_START + rnd;
va_1 = find_vmap_lowest_match(size, 1, vstart);
va_2 = find_vmap_lowest_linear_match(size, 1, vstart);
if (va_1 != va_2)
pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n",
va_1, va_2, vstart);
}
#endif
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
enum fit_type {
NOTHING_FIT = 0,
FL_FIT_TYPE = 1, /* full fit */
LE_FIT_TYPE = 2, /* left edge fit */
RE_FIT_TYPE = 3, /* right edge fit */
NE_FIT_TYPE = 4 /* no edge fit */
};
static __always_inline enum fit_type
classify_va_fit_type(struct vmap_area *va,
unsigned long nva_start_addr, unsigned long size)
{
enum fit_type type;
/* Check if it is within VA. */
if (nva_start_addr < va->va_start ||
nva_start_addr + size > va->va_end)
return NOTHING_FIT;
/* Now classify. */
if (va->va_start == nva_start_addr) {
if (va->va_end == nva_start_addr + size)
type = FL_FIT_TYPE;
else
type = LE_FIT_TYPE;
} else if (va->va_end == nva_start_addr + size) {
type = RE_FIT_TYPE;
} else {
type = NE_FIT_TYPE;
}
return type;
}
static __always_inline int
adjust_va_to_fit_type(struct vmap_area *va,
unsigned long nva_start_addr, unsigned long size,
enum fit_type type)
{
struct vmap_area *lva = NULL;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (type == FL_FIT_TYPE) {
/*
* No need to split VA, it fully fits.
*
* | |
* V NVA V
* |---------------|
*/
unlink_va(va, &free_vmap_area_root);
kmem_cache_free(vmap_area_cachep, va);
} else if (type == LE_FIT_TYPE) {
/*
* Split left edge of fit VA.
*
* | |
* V NVA V R
* |-------|-------|
*/
va->va_start += size;
} else if (type == RE_FIT_TYPE) {
/*
* Split right edge of fit VA.
*
* | |
* L V NVA V
* |-------|-------|
*/
va->va_end = nva_start_addr;
} else if (type == NE_FIT_TYPE) {
/*
* Split no edge of fit VA.
*
* | |
* L V NVA V R
* |---|-------|---|
*/
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
lva = __this_cpu_xchg(ne_fit_preload_node, NULL);
if (unlikely(!lva)) {
/*
* For percpu allocator we do not do any pre-allocation
* and leave it as it is. The reason is it most likely
* never ends up with NE_FIT_TYPE splitting. In case of
* percpu allocations offsets and sizes are aligned to
* fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE
* are its main fitting cases.
*
* There are a few exceptions though, as an example it is
* a first allocation (early boot up) when we have "one"
* big free space that has to be split.
*
* Also we can hit this path in case of regular "vmap"
* allocations, if "this" current CPU was not preloaded.
* See the comment in alloc_vmap_area() why. If so, then
* GFP_NOWAIT is used instead to get an extra object for
* split purpose. That is rare and most time does not
* occur.
*
* What happens if an allocation gets failed. Basically,
* an "overflow" path is triggered to purge lazily freed
* areas to free some memory, then, the "retry" path is
* triggered to repeat one more time. See more details
* in alloc_vmap_area() function.
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
*/
lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
if (!lva)
return -1;
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* Build the remainder.
*/
lva->va_start = va->va_start;
lva->va_end = nva_start_addr;
/*
* Shrink this VA to remaining size.
*/
va->va_start = nva_start_addr + size;
} else {
return -1;
}
if (type != FL_FIT_TYPE) {
augment_tree_propagate_from(va);
if (lva) /* type == NE_FIT_TYPE */
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
insert_vmap_area_augment(lva, &va->rb_node,
&free_vmap_area_root, &free_vmap_area_list);
}
return 0;
}
/*
* Returns a start address of the newly allocated area, if success.
* Otherwise a vend is returned that indicates failure.
*/
static __always_inline unsigned long
__alloc_vmap_area(unsigned long size, unsigned long align,
unsigned long vstart, unsigned long vend)
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
{
unsigned long nva_start_addr;
struct vmap_area *va;
enum fit_type type;
int ret;
va = find_vmap_lowest_match(size, align, vstart);
if (unlikely(!va))
return vend;
if (va->va_start > vstart)
nva_start_addr = ALIGN(va->va_start, align);
else
nva_start_addr = ALIGN(vstart, align);
/* Check the "vend" restriction. */
if (nva_start_addr + size > vend)
return vend;
/* Classify what we have found. */
type = classify_va_fit_type(va, nva_start_addr, size);
if (WARN_ON_ONCE(type == NOTHING_FIT))
return vend;
/* Update the free vmap_area. */
ret = adjust_va_to_fit_type(va, nva_start_addr, size, type);
if (ret)
return vend;
#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
find_vmap_lowest_match_check(size);
#endif
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
return nva_start_addr;
}
/*
* Free a region of KVA allocated by alloc_vmap_area
*/
static void free_vmap_area(struct vmap_area *va)
{
/*
* Remove from the busy tree/list.
*/
spin_lock(&vmap_area_lock);
unlink_va(va, &vmap_area_root);
spin_unlock(&vmap_area_lock);
/*
* Insert/Merge it back to the free tree/list.
*/
spin_lock(&free_vmap_area_lock);
merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list);
spin_unlock(&free_vmap_area_lock);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* Allocate a region of KVA of the specified size and alignment, within the
* vstart and vend.
*/
static struct vmap_area *alloc_vmap_area(unsigned long size,
unsigned long align,
unsigned long vstart, unsigned long vend,
int node, gfp_t gfp_mask)
{
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
struct vmap_area *va, *pva;
unsigned long addr;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
int purged = 0;
int ret;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
BUG_ON(!size);
BUG_ON(offset_in_page(size));
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
BUG_ON(!is_power_of_2(align));
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (unlikely(!vmap_initialized))
return ERR_PTR(-EBUSY);
might_sleep();
gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
if (unlikely(!va))
return ERR_PTR(-ENOMEM);
/*
* Only scan the relevant parts containing pointers to other objects
* to avoid false negatives.
*/
kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
retry:
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
/*
mm/vmalloc: remove preempt_disable/enable when doing preloading Some background. The preemption was disabled before to guarantee that a preloaded object is available for a CPU, it was stored for. That was achieved by combining the disabling the preemption and taking the spin lock while the ne_fit_preload_node is checked. The aim was to not allocate in atomic context when spinlock is taken later, for regular vmap allocations. But that approach conflicts with CONFIG_PREEMPT_RT philosophy. It means that calling spin_lock() with disabled preemption is forbidden in the CONFIG_PREEMPT_RT kernel. Therefore, get rid of preempt_disable() and preempt_enable() when the preload is done for splitting purpose. As a result we do not guarantee now that a CPU is preloaded, instead we minimize the case when it is not, with this change, by populating the per cpu preload pointer under the vmap_area_lock. This implies that at least each caller that has done the preallocation will not fallback to an atomic allocation later. It is possible that the preallocation would be pointless or that no preallocation is done because of the race but the data shows that this is really rare. For example i run the special test case that follows the preload pattern and path. 20 "unbind" threads run it and each does 1000000 allocations. Only 3.5 times among 1000000 a CPU was not preloaded. So it can happen but the number is negligible. [mhocko@suse.com: changelog additions] Link: http://lkml.kernel.org/r/20191016095438.12391-1-urezki@gmail.com Fixes: 82dd23e84be3 ("mm/vmalloc.c: preload a CPU with one object for split purpose") Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by: Daniel Wagner <dwagner@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:33 +08:00
* Preload this CPU with one extra vmap_area object. It is used
* when fit type of free area is NE_FIT_TYPE. Please note, it
* does not guarantee that an allocation occurs on a CPU that
* is preloaded, instead we minimize the case when it is not.
* It can happen because of cpu migration, because there is a
* race until the below spinlock is taken.
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
*
* The preload is done in non-atomic context, thus it allows us
* to use more permissive allocation masks to be more stable under
mm/vmalloc: remove preempt_disable/enable when doing preloading Some background. The preemption was disabled before to guarantee that a preloaded object is available for a CPU, it was stored for. That was achieved by combining the disabling the preemption and taking the spin lock while the ne_fit_preload_node is checked. The aim was to not allocate in atomic context when spinlock is taken later, for regular vmap allocations. But that approach conflicts with CONFIG_PREEMPT_RT philosophy. It means that calling spin_lock() with disabled preemption is forbidden in the CONFIG_PREEMPT_RT kernel. Therefore, get rid of preempt_disable() and preempt_enable() when the preload is done for splitting purpose. As a result we do not guarantee now that a CPU is preloaded, instead we minimize the case when it is not, with this change, by populating the per cpu preload pointer under the vmap_area_lock. This implies that at least each caller that has done the preallocation will not fallback to an atomic allocation later. It is possible that the preallocation would be pointless or that no preallocation is done because of the race but the data shows that this is really rare. For example i run the special test case that follows the preload pattern and path. 20 "unbind" threads run it and each does 1000000 allocations. Only 3.5 times among 1000000 a CPU was not preloaded. So it can happen but the number is negligible. [mhocko@suse.com: changelog additions] Link: http://lkml.kernel.org/r/20191016095438.12391-1-urezki@gmail.com Fixes: 82dd23e84be3 ("mm/vmalloc.c: preload a CPU with one object for split purpose") Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by: Daniel Wagner <dwagner@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:33 +08:00
* low memory condition and high memory pressure. In rare case,
* if not preloaded, GFP_NOWAIT is used.
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
*
mm/vmalloc: remove preempt_disable/enable when doing preloading Some background. The preemption was disabled before to guarantee that a preloaded object is available for a CPU, it was stored for. That was achieved by combining the disabling the preemption and taking the spin lock while the ne_fit_preload_node is checked. The aim was to not allocate in atomic context when spinlock is taken later, for regular vmap allocations. But that approach conflicts with CONFIG_PREEMPT_RT philosophy. It means that calling spin_lock() with disabled preemption is forbidden in the CONFIG_PREEMPT_RT kernel. Therefore, get rid of preempt_disable() and preempt_enable() when the preload is done for splitting purpose. As a result we do not guarantee now that a CPU is preloaded, instead we minimize the case when it is not, with this change, by populating the per cpu preload pointer under the vmap_area_lock. This implies that at least each caller that has done the preallocation will not fallback to an atomic allocation later. It is possible that the preallocation would be pointless or that no preallocation is done because of the race but the data shows that this is really rare. For example i run the special test case that follows the preload pattern and path. 20 "unbind" threads run it and each does 1000000 allocations. Only 3.5 times among 1000000 a CPU was not preloaded. So it can happen but the number is negligible. [mhocko@suse.com: changelog additions] Link: http://lkml.kernel.org/r/20191016095438.12391-1-urezki@gmail.com Fixes: 82dd23e84be3 ("mm/vmalloc.c: preload a CPU with one object for split purpose") Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by: Daniel Wagner <dwagner@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:33 +08:00
* Set "pva" to NULL here, because of "retry" path.
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
*/
mm/vmalloc: remove preempt_disable/enable when doing preloading Some background. The preemption was disabled before to guarantee that a preloaded object is available for a CPU, it was stored for. That was achieved by combining the disabling the preemption and taking the spin lock while the ne_fit_preload_node is checked. The aim was to not allocate in atomic context when spinlock is taken later, for regular vmap allocations. But that approach conflicts with CONFIG_PREEMPT_RT philosophy. It means that calling spin_lock() with disabled preemption is forbidden in the CONFIG_PREEMPT_RT kernel. Therefore, get rid of preempt_disable() and preempt_enable() when the preload is done for splitting purpose. As a result we do not guarantee now that a CPU is preloaded, instead we minimize the case when it is not, with this change, by populating the per cpu preload pointer under the vmap_area_lock. This implies that at least each caller that has done the preallocation will not fallback to an atomic allocation later. It is possible that the preallocation would be pointless or that no preallocation is done because of the race but the data shows that this is really rare. For example i run the special test case that follows the preload pattern and path. 20 "unbind" threads run it and each does 1000000 allocations. Only 3.5 times among 1000000 a CPU was not preloaded. So it can happen but the number is negligible. [mhocko@suse.com: changelog additions] Link: http://lkml.kernel.org/r/20191016095438.12391-1-urezki@gmail.com Fixes: 82dd23e84be3 ("mm/vmalloc.c: preload a CPU with one object for split purpose") Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by: Daniel Wagner <dwagner@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:33 +08:00
pva = NULL;
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
mm/vmalloc: remove preempt_disable/enable when doing preloading Some background. The preemption was disabled before to guarantee that a preloaded object is available for a CPU, it was stored for. That was achieved by combining the disabling the preemption and taking the spin lock while the ne_fit_preload_node is checked. The aim was to not allocate in atomic context when spinlock is taken later, for regular vmap allocations. But that approach conflicts with CONFIG_PREEMPT_RT philosophy. It means that calling spin_lock() with disabled preemption is forbidden in the CONFIG_PREEMPT_RT kernel. Therefore, get rid of preempt_disable() and preempt_enable() when the preload is done for splitting purpose. As a result we do not guarantee now that a CPU is preloaded, instead we minimize the case when it is not, with this change, by populating the per cpu preload pointer under the vmap_area_lock. This implies that at least each caller that has done the preallocation will not fallback to an atomic allocation later. It is possible that the preallocation would be pointless or that no preallocation is done because of the race but the data shows that this is really rare. For example i run the special test case that follows the preload pattern and path. 20 "unbind" threads run it and each does 1000000 allocations. Only 3.5 times among 1000000 a CPU was not preloaded. So it can happen but the number is negligible. [mhocko@suse.com: changelog additions] Link: http://lkml.kernel.org/r/20191016095438.12391-1-urezki@gmail.com Fixes: 82dd23e84be3 ("mm/vmalloc.c: preload a CPU with one object for split purpose") Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by: Daniel Wagner <dwagner@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:33 +08:00
if (!this_cpu_read(ne_fit_preload_node))
/*
* Even if it fails we do not really care about that.
* Just proceed as it is. If needed "overflow" path
* will refill the cache we allocate from.
*/
pva = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
mm/vmalloc.c: preload a CPU with one object for split purpose Refactor the NE_FIT_TYPE split case when it comes to an allocation of one extra object. We need it in order to build a remaining space. The preload is done per CPU in non-atomic context with GFP_KERNEL flags. More permissive parameters can be beneficial for systems which are suffer from high memory pressure or low memory condition. For example on my KVM system(4xCPUs, no swap, 256MB RAM) i can simulate the failure of page allocation with GFP_NOWAIT flags. Using "stress-ng" tool and starting N workers spinning on fork() and exit(), i can trigger below trace: <snip> [ 179.815161] stress-ng-fork: page allocation failure: order:0, mode:0x40800(GFP_NOWAIT|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 [ 179.815168] CPU: 0 PID: 12612 Comm: stress-ng-fork Not tainted 5.2.0-rc3+ #1003 [ 179.815170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 179.815171] Call Trace: [ 179.815178] dump_stack+0x5c/0x7b [ 179.815182] warn_alloc+0x108/0x190 [ 179.815187] __alloc_pages_slowpath+0xdc7/0xdf0 [ 179.815191] __alloc_pages_nodemask+0x2de/0x330 [ 179.815194] cache_grow_begin+0x77/0x420 [ 179.815197] fallback_alloc+0x161/0x200 [ 179.815200] kmem_cache_alloc+0x1c9/0x570 [ 179.815202] alloc_vmap_area+0x32c/0x990 [ 179.815206] __get_vm_area_node+0xb0/0x170 [ 179.815208] __vmalloc_node_range+0x6d/0x230 [ 179.815211] ? _do_fork+0xce/0x3d0 [ 179.815213] copy_process.part.46+0x850/0x1b90 [ 179.815215] ? _do_fork+0xce/0x3d0 [ 179.815219] _do_fork+0xce/0x3d0 [ 179.815226] ? __do_page_fault+0x2bf/0x4e0 [ 179.815229] do_syscall_64+0x55/0x130 [ 179.815231] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 179.815234] RIP: 0033:0x7fedec4c738b ... [ 179.815237] RSP: 002b:00007ffda469d730 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 179.815239] RAX: ffffffffffffffda RBX: 00007ffda469d730 RCX: 00007fedec4c738b [ 179.815240] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 179.815241] RBP: 00007ffda469d780 R08: 00007fededd6e300 R09: 00007ffda47f50a0 [ 179.815242] R10: 00007fededd6e5d0 R11: 0000000000000246 R12: 0000000000000000 [ 179.815243] R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000000000 [ 179.815245] Mem-Info: [ 179.815249] active_anon:12686 inactive_anon:14760 isolated_anon:0 active_file:502 inactive_file:61 isolated_file:70 unevictable:2 dirty:0 writeback:0 unstable:0 slab_reclaimable:2380 slab_unreclaimable:7520 mapped:15069 shmem:14813 pagetables:10833 bounce:0 free:1922 free_pcp:229 free_cma:0 <snip> Link: http://lkml.kernel.org/r/20190606120411.8298-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Roman Gushchin <guro@fb.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 11:58:57 +08:00
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_lock(&free_vmap_area_lock);
mm/vmalloc: remove preempt_disable/enable when doing preloading Some background. The preemption was disabled before to guarantee that a preloaded object is available for a CPU, it was stored for. That was achieved by combining the disabling the preemption and taking the spin lock while the ne_fit_preload_node is checked. The aim was to not allocate in atomic context when spinlock is taken later, for regular vmap allocations. But that approach conflicts with CONFIG_PREEMPT_RT philosophy. It means that calling spin_lock() with disabled preemption is forbidden in the CONFIG_PREEMPT_RT kernel. Therefore, get rid of preempt_disable() and preempt_enable() when the preload is done for splitting purpose. As a result we do not guarantee now that a CPU is preloaded, instead we minimize the case when it is not, with this change, by populating the per cpu preload pointer under the vmap_area_lock. This implies that at least each caller that has done the preallocation will not fallback to an atomic allocation later. It is possible that the preallocation would be pointless or that no preallocation is done because of the race but the data shows that this is really rare. For example i run the special test case that follows the preload pattern and path. 20 "unbind" threads run it and each does 1000000 allocations. Only 3.5 times among 1000000 a CPU was not preloaded. So it can happen but the number is negligible. [mhocko@suse.com: changelog additions] Link: http://lkml.kernel.org/r/20191016095438.12391-1-urezki@gmail.com Fixes: 82dd23e84be3 ("mm/vmalloc.c: preload a CPU with one object for split purpose") Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by: Daniel Wagner <dwagner@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:33 +08:00
if (pva && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva))
kmem_cache_free(vmap_area_cachep, pva);
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
/*
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* If an allocation fails, the "vend" address is
* returned. Therefore trigger the overflow path.
*/
addr = __alloc_vmap_area(size, align, vstart, vend);
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_unlock(&free_vmap_area_lock);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (unlikely(addr == vend))
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
goto overflow;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
va->va_start = addr;
va->va_end = addr + size;
va->vm = NULL;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_lock(&vmap_area_lock);
insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
spin_unlock(&vmap_area_lock);
BUG_ON(!IS_ALIGNED(va->va_start, align));
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
BUG_ON(va->va_start < vstart);
BUG_ON(va->va_end > vend);
ret = kasan_populate_vmalloc(addr, size);
if (ret) {
free_vmap_area(va);
return ERR_PTR(ret);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return va;
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
overflow:
if (!purged) {
purge_vmap_area_lazy();
purged = 1;
goto retry;
}
if (gfpflags_allow_blocking(gfp_mask)) {
unsigned long freed = 0;
blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
if (freed > 0) {
purged = 0;
goto retry;
}
}
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
size);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
kmem_cache_free(vmap_area_cachep, va);
mm: vmap area cache Provide a free area cache for the vmalloc virtual address allocator, based on the algorithm used by the user virtual memory allocator. This reduces the number of rbtree operations and linear traversals over the vmap extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for a smaller area or alignment than last time. So allocation patterns are not changed (verified by corner-case and random test cases in userspace testing). This solves a regression caused by lazy vunmap TLB purging introduced in db64fe02 (mm: rewrite vmap layer). That patch will leave extents in the vmap allocator after they are vunmapped, and until a significant number accumulate that can be flushed in a single batch. So in a workload that vmalloc/vfree frequently, a chain of extents will build up from VMALLOC_START address, which have to be iterated over each time (giving an O(n) type of behaviour). After this patch, the search will start from where it left off, giving closer to an amortized O(1). This is verified to solve regressions reported Steven in GFS2, and Avi in KVM. Hugh's update: : I tried out the recent mmotm, and on one machine was fortunate to hit : the BUG_ON(first->va_start < addr) which seems to have been stalling : your vmap area cache patch ever since May. : I can get you addresses etc, I did dump a few out; but once I stared : at them, it was easier just to look at the code: and I cannot see how : you would be so sure that first->va_start < addr, once you've done : that addr = ALIGN(max(...), align) above, if align is over 0x1000 : (align was 0x8000 or 0x4000 in the cases I hit: ioremaps like Steve). : I originally got around it by just changing the : if (first->va_start < addr) { : to : while (first->va_start < addr) { : without thinking about it any further; but that seemed unsatisfactory, : why would we want to loop here when we've got another very similar : loop just below it? : I am never going to admit how long I've spent trying to grasp your : "while (n)" rbtree loop just above this, the one with the peculiar : if (!first && tmp->va_start < addr + size) : in. That's unfamiliar to me, I'm guessing it's designed to save a : subsequent rb_next() in a few circumstances (at risk of then setting : a wrong cached_hole_size?); but they did appear few to me, and I didn't : feel I could sign off something with that in when I don't grasp it, : and it seems responsible for extra code and mistaken BUG_ON below it. : I've reverted to the familiar rbtree loop that find_vma() does (but : with va_end >= addr as you had, to respect the additional guard page): : and then (given that cached_hole_size starts out 0) I don't see the : need for any complications below it. If you do want to keep that loop : as you had it, please add a comment to explain what it's trying to do, : and where addr is relative to first when you emerge from it. : Aren't your tests "size <= cached_hole_size" and : "addr + size > first->va_start" forgetting the guard page we want : before the next area? I've changed those. : I have not changed your many "addr + size - 1 < addr" overflow tests, : but have since come to wonder, shouldn't they be "addr + size < addr" : tests - won't the vend checks go wrong if addr + size is 0? : I have added a few comments - Wolfgang Wander's 2.6.13 description of : 1363c3cd8603a913a27e2995dccbd70d5312d8e6 Avoiding mmap fragmentation : helped me a lot, perhaps a pointer to that would be good too. And I found : it easier to understand when I renamed cached_start slightly and moved the : overflow label down. : This patch would go after your mm-vmap-area-cache.patch in mmotm. : Trivially, nobody is going to get that BUG_ON with this patch, and it : appears to work fine on my machines; but I have not given it anything like : the testing you did on your original, and may have broken all the : performance you were aiming for. Please take a look and test it out : integrate with yours if you're satisfied - thanks. [akpm@linux-foundation.org: add locking comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reported-and-tested-by: Steven Whitehouse <swhiteho@redhat.com> Reported-and-tested-by: Avi Kivity <avi@redhat.com> Tested-by: "Barry J. Marson" <bmarson@redhat.com> Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:30:36 +08:00
return ERR_PTR(-EBUSY);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
int register_vmap_purge_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_vmap_purge_notifier);
int unregister_vmap_purge_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* Clear the pagetable entries of a given vmap_area
*/
static void unmap_vmap_area(struct vmap_area *va)
{
vunmap_page_range(va->va_start, va->va_end);
}
/*
* lazy_max_pages is the maximum amount of virtual address space we gather up
* before attempting to purge with a TLB flush.
*
* There is a tradeoff here: a larger number will cover more kernel page tables
* and take slightly longer to purge, but it will linearly reduce the number of
* global TLB flushes that must be performed. It would seem natural to scale
* this number up linearly with the number of CPUs (because vmapping activity
* could also scale linearly with the number of CPUs), however it is likely
* that in practice, workloads might be constrained in other ways that mean
* vmap activity will not scale linearly with CPUs. Also, I want to be
* conservative and not introduce a big latency on huge systems, so go with
* a less aggressive log scale. It will still be an improvement over the old
* code, and it will be simple to change the scale factor if we find that it
* becomes a problem on bigger systems.
*/
static unsigned long lazy_max_pages(void)
{
unsigned int log;
log = fls(num_online_cpus());
return log * (32UL * 1024 * 1024 / PAGE_SIZE);
}
static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* Serialize vmap purging. There is no actual criticial section protected
* by this look, but we want to avoid concurrent calls for performance
* reasons and to make the pcpu_get_vm_areas more deterministic.
*/
static DEFINE_MUTEX(vmap_purge_lock);
/* for per-CPU blocks */
static void purge_fragmented_blocks_allcpus(void);
/*
* called before a call to iounmap() if the caller wants vm_area_struct's
* immediately freed.
*/
void set_iounmap_nonlazy(void)
{
atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* Purges all lazily-freed vmap areas.
*/
static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
{
unsigned long resched_threshold;
struct llist_node *valist;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
struct vmap_area *va;
mm: fix lazy vmap purging (use-after-free error) I just got this new warning from kmemcheck: WARNING: kmemcheck: Caught 32-bit read from freed memory (c7806a60) a06a80c7ecde70c1a04080c700000000a06709c1000000000000000000000000 f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f f ^ Pid: 0, comm: swapper Not tainted (2.6.29-rc4 #230) EIP: 0060:[<c1096df7>] EFLAGS: 00000286 CPU: 0 EIP is at __purge_vmap_area_lazy+0x117/0x140 EAX: 00070f43 EBX: c7806a40 ECX: c1677080 EDX: 00027b66 ESI: 00002001 EDI: c170df0c EBP: c170df00 ESP: c178830c DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 CR0: 80050033 CR2: c7806b14 CR3: 01775000 CR4: 00000690 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: 00004000 DR7: 00000000 [<c1096f3e>] free_unmap_vmap_area_noflush+0x6e/0x70 [<c1096f6a>] remove_vm_area+0x2a/0x70 [<c1097025>] __vunmap+0x45/0xe0 [<c10970de>] vunmap+0x1e/0x30 [<c1008ba5>] text_poke+0x95/0x150 [<c1008ca9>] alternatives_smp_unlock+0x49/0x60 [<c171ef47>] alternative_instructions+0x11b/0x124 [<c171f991>] check_bugs+0xbd/0xdc [<c17148c5>] start_kernel+0x2ed/0x360 [<c171409e>] __init_begin+0x9e/0xa9 [<ffffffff>] 0xffffffff It happened here: $ addr2line -e vmlinux -i c1096df7 mm/vmalloc.c:540 Code: list_for_each_entry(va, &valist, purge_list) __free_vmap_area(va); It's this instruction: mov 0x20(%ebx),%edx Which corresponds to a dereference of va->purge_list.next: (gdb) p ((struct vmap_area *) 0)->purge_list.next Cannot access memory at address 0x20 It seems that we should use "safe" list traversal here, as the element is freed inside the loop. Please verify that this is the right fix. Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Ingo Molnar <mingo@elte.hu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-28 06:03:04 +08:00
struct vmap_area *n_va;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
lockdep_assert_held(&vmap_purge_lock);
valist = llist_del_all(&vmap_purge_list);
mm/vmalloc.c: add priority threshold to __purge_vmap_area_lazy() Commit 763b218ddfaf ("mm: add preempt points into __purge_vmap_area_lazy()") introduced some preempt points, one of those is making an allocation more prioritized over lazy free of vmap areas. Prioritizing an allocation over freeing does not work well all the time, i.e. it should be rather a compromise. 1) Number of lazy pages directly influences the busy list length thus on operations like: allocation, lookup, unmap, remove, etc. 2) Under heavy stress of vmalloc subsystem I run into a situation when memory usage gets increased hitting out_of_memory -> panic state due to completely blocking of logic that frees vmap areas in the __purge_vmap_area_lazy() function. Establish a threshold passing which the freeing is prioritized back over allocation creating a balance between each other. Using vmalloc test driver in "stress mode", i.e. When all available test cases are run simultaneously on all online CPUs applying a pressure on the vmalloc subsystem, my HiKey 960 board runs out of memory due to the fact that __purge_vmap_area_lazy() logic simply is not able to free pages in time. How I run it: 1) You should build your kernel with CONFIG_TEST_VMALLOC=m 2) ./tools/testing/selftests/vm/test_vmalloc.sh stress During this test "vmap_lazy_nr" pages will go far beyond acceptable lazy_max_pages() threshold, that will lead to enormous busy list size and other problems including allocation time and so on. Link: http://lkml.kernel.org/r/20190124115648.9433-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Cc: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:41:22 +08:00
if (unlikely(valist == NULL))
return false;
/*
* First make sure the mappings are removed from all page-tables
* before they are freed.
*/
vmalloc_sync_all();
mm/vmalloc.c: add priority threshold to __purge_vmap_area_lazy() Commit 763b218ddfaf ("mm: add preempt points into __purge_vmap_area_lazy()") introduced some preempt points, one of those is making an allocation more prioritized over lazy free of vmap areas. Prioritizing an allocation over freeing does not work well all the time, i.e. it should be rather a compromise. 1) Number of lazy pages directly influences the busy list length thus on operations like: allocation, lookup, unmap, remove, etc. 2) Under heavy stress of vmalloc subsystem I run into a situation when memory usage gets increased hitting out_of_memory -> panic state due to completely blocking of logic that frees vmap areas in the __purge_vmap_area_lazy() function. Establish a threshold passing which the freeing is prioritized back over allocation creating a balance between each other. Using vmalloc test driver in "stress mode", i.e. When all available test cases are run simultaneously on all online CPUs applying a pressure on the vmalloc subsystem, my HiKey 960 board runs out of memory due to the fact that __purge_vmap_area_lazy() logic simply is not able to free pages in time. How I run it: 1) You should build your kernel with CONFIG_TEST_VMALLOC=m 2) ./tools/testing/selftests/vm/test_vmalloc.sh stress During this test "vmap_lazy_nr" pages will go far beyond acceptable lazy_max_pages() threshold, that will lead to enormous busy list size and other problems including allocation time and so on. Link: http://lkml.kernel.org/r/20190124115648.9433-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Cc: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:41:22 +08:00
/*
* TODO: to calculate a flush range without looping.
* The list can be up to lazy_max_pages() elements.
*/
llist_for_each_entry(va, valist, purge_list) {
if (va->va_start < start)
start = va->va_start;
if (va->va_end > end)
end = va->va_end;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
flush_tlb_kernel_range(start, end);
resched_threshold = lazy_max_pages() << 1;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_lock(&free_vmap_area_lock);
llist_for_each_entry_safe(va, n_va, valist, purge_list) {
unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
unsigned long orig_start = va->va_start;
unsigned long orig_end = va->va_end;
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
/*
* Finally insert or merge lazily-freed area. It is
* detached and there is no need to "unlink" it from
* anything.
*/
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
va = merge_or_add_vmap_area(va, &free_vmap_area_root,
&free_vmap_area_list);
if (is_vmalloc_or_module_addr((void *)orig_start))
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
atomic_long_sub(nr, &vmap_lazy_nr);
mm/vmalloc.c: add priority threshold to __purge_vmap_area_lazy() Commit 763b218ddfaf ("mm: add preempt points into __purge_vmap_area_lazy()") introduced some preempt points, one of those is making an allocation more prioritized over lazy free of vmap areas. Prioritizing an allocation over freeing does not work well all the time, i.e. it should be rather a compromise. 1) Number of lazy pages directly influences the busy list length thus on operations like: allocation, lookup, unmap, remove, etc. 2) Under heavy stress of vmalloc subsystem I run into a situation when memory usage gets increased hitting out_of_memory -> panic state due to completely blocking of logic that frees vmap areas in the __purge_vmap_area_lazy() function. Establish a threshold passing which the freeing is prioritized back over allocation creating a balance between each other. Using vmalloc test driver in "stress mode", i.e. When all available test cases are run simultaneously on all online CPUs applying a pressure on the vmalloc subsystem, my HiKey 960 board runs out of memory due to the fact that __purge_vmap_area_lazy() logic simply is not able to free pages in time. How I run it: 1) You should build your kernel with CONFIG_TEST_VMALLOC=m 2) ./tools/testing/selftests/vm/test_vmalloc.sh stress During this test "vmap_lazy_nr" pages will go far beyond acceptable lazy_max_pages() threshold, that will lead to enormous busy list size and other problems including allocation time and so on. Link: http://lkml.kernel.org/r/20190124115648.9433-3-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Cc: Joel Fernandes <joel@joelfernandes.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:41:22 +08:00
if (atomic_long_read(&vmap_lazy_nr) < resched_threshold)
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
cond_resched_lock(&free_vmap_area_lock);
}
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_unlock(&free_vmap_area_lock);
return true;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
/*
* Kick off a purge of the outstanding lazy areas. Don't bother if somebody
* is already purging.
*/
static void try_purge_vmap_area_lazy(void)
{
if (mutex_trylock(&vmap_purge_lock)) {
__purge_vmap_area_lazy(ULONG_MAX, 0);
mutex_unlock(&vmap_purge_lock);
}
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
/*
* Kick off a purge of the outstanding lazy areas.
*/
static void purge_vmap_area_lazy(void)
{
mutex_lock(&vmap_purge_lock);
purge_fragmented_blocks_allcpus();
__purge_vmap_area_lazy(ULONG_MAX, 0);
mutex_unlock(&vmap_purge_lock);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
/*
vmalloc: eagerly clear ptes on vunmap On stock 2.6.37-rc4, running: # mount lilith:/export /mnt/lilith # find /mnt/lilith/ -type f -print0 | xargs -0 file crashes the machine fairly quickly under Xen. Often it results in oops messages, but the couple of times I tried just now, it just hung quietly and made Xen print some rude messages: (XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp 3000000000000000) for mfn 1d7058 (pfn 18fa7) (XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms (XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp 1000000000000000) for mfn 1d2e04 (pfn 1d1fb) (XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04 Which means the domain tried to map a pagetable page RW, which would allow it to map arbitrary memory, so Xen stopped it. This is because vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had finished with them, and those pages got recycled as pagetable pages while still having these RW aliases. Removing those mappings immediately removes the Xen-visible aliases, and so it has no problem with those pages being reused as pagetable pages. Deferring the TLB flush doesn't upset Xen because it can flush the TLB itself as needed to maintain its invariants. When unmapping a region in the vmalloc space, clear the ptes immediately. There's no point in deferring this because there's no amortization benefit. The TLBs are left dirty, and they are flushed lazily to amortize the cost of the IPIs. This specific motivation for this patch is an oops-causing regression since 2.6.36 when using NFS under Xen, triggered by the NFS client's use of vm_map_ram() introduced in 56e4ebf877b60 ("NFS: readdir with vmapped pages") . XFS also uses vm_map_ram() and could cause similar problems. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Bryan Schumaker <bjschuma@netapp.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Alex Elder <aelder@sgi.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-12-03 06:31:18 +08:00
* Free a vmap area, caller ensuring that the area has been unmapped
* and flush_cache_vunmap had been called for the correct range
* previously.
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
*/
vmalloc: eagerly clear ptes on vunmap On stock 2.6.37-rc4, running: # mount lilith:/export /mnt/lilith # find /mnt/lilith/ -type f -print0 | xargs -0 file crashes the machine fairly quickly under Xen. Often it results in oops messages, but the couple of times I tried just now, it just hung quietly and made Xen print some rude messages: (XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp 3000000000000000) for mfn 1d7058 (pfn 18fa7) (XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms (XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp 1000000000000000) for mfn 1d2e04 (pfn 1d1fb) (XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04 Which means the domain tried to map a pagetable page RW, which would allow it to map arbitrary memory, so Xen stopped it. This is because vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had finished with them, and those pages got recycled as pagetable pages while still having these RW aliases. Removing those mappings immediately removes the Xen-visible aliases, and so it has no problem with those pages being reused as pagetable pages. Deferring the TLB flush doesn't upset Xen because it can flush the TLB itself as needed to maintain its invariants. When unmapping a region in the vmalloc space, clear the ptes immediately. There's no point in deferring this because there's no amortization benefit. The TLBs are left dirty, and they are flushed lazily to amortize the cost of the IPIs. This specific motivation for this patch is an oops-causing regression since 2.6.36 when using NFS under Xen, triggered by the NFS client's use of vm_map_ram() introduced in 56e4ebf877b60 ("NFS: readdir with vmapped pages") . XFS also uses vm_map_ram() and could cause similar problems. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Bryan Schumaker <bjschuma@netapp.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Alex Elder <aelder@sgi.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-12-03 06:31:18 +08:00
static void free_vmap_area_noflush(struct vmap_area *va)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
{
unsigned long nr_lazy;
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
spin_lock(&vmap_area_lock);
unlink_va(va, &vmap_area_root);
spin_unlock(&vmap_area_lock);
nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
PAGE_SHIFT, &vmap_lazy_nr);
/* After this point, we may free va at any time */
llist_add(&va->purge_list, &vmap_purge_list);
if (unlikely(nr_lazy > lazy_max_pages()))
try_purge_vmap_area_lazy();
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
/*
* Free and unmap a vmap area
*/
static void free_unmap_vmap_area(struct vmap_area *va)
{
flush_cache_vunmap(va->va_start, va->va_end);
unmap_vmap_area(va);
mm, debug_pagealloc: don't rely on static keys too early Commit 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") has introduced a static key to reduce overhead when debug_pagealloc is compiled in but not enabled. It relied on the assumption that jump_label_init() is called before parse_early_param() as in start_kernel(), so when the "debug_pagealloc=on" option is parsed, it is safe to enable the static key. However, it turns out multiple architectures call parse_early_param() earlier from their setup_arch(). x86 also calls jump_label_init() even earlier, so no issue was found while testing the commit, but same is not true for e.g. ppc64 and s390 where the kernel would not boot with debug_pagealloc=on as found by our QA. To fix this without tricky changes to init code of multiple architectures, this patch partially reverts the static key conversion from 96a2b03f281d. Init-time and non-fastpath calls (such as in arch code) of debug_pagealloc_enabled() will again test a simple bool variable. Fastpath mm code is converted to a new debug_pagealloc_enabled_static() variant that relies on the static key, which is enabled in a well-defined point in mm_init() where it's guaranteed that jump_label_init() has been called, regardless of architecture. [sfr@canb.auug.org.au: export _debug_pagealloc_enabled_early] Link: http://lkml.kernel.org/r/20200106164944.063ac07b@canb.auug.org.au Link: http://lkml.kernel.org/r/20191219130612.23171-1-vbabka@suse.cz Fixes: 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Qian Cai <cai@lca.pw> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-14 08:29:20 +08:00
if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range(va->va_start, va->va_end);
free_vmap_area_noflush(va);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static struct vmap_area *find_vmap_area(unsigned long addr)
{
struct vmap_area *va;
spin_lock(&vmap_area_lock);
va = __find_vmap_area(addr);
spin_unlock(&vmap_area_lock);
return va;
}
/*** Per cpu kva allocator ***/
/*
* vmap space is limited especially on 32 bit architectures. Ensure there is
* room for at least 16 percpu vmap blocks per CPU.
*/
/*
* If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
* to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess
* instead (we just need a rough idea)
*/
#if BITS_PER_LONG == 32
#define VMALLOC_SPACE (128UL*1024*1024)
#else
#define VMALLOC_SPACE (128UL*1024*1024*1024)
#endif
#define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE)
#define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */
#define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */
#define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2)
#define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */
#define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */
#define VMAP_BBMAP_BITS \
VMAP_MIN(VMAP_BBMAP_BITS_MAX, \
VMAP_MAX(VMAP_BBMAP_BITS_MIN, \
VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
#define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE)
struct vmap_block_queue {
spinlock_t lock;
struct list_head free;
};
struct vmap_block {
spinlock_t lock;
struct vmap_area *va;
unsigned long free, dirty;
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
unsigned long dirty_min, dirty_max; /*< dirty range */
struct list_head free_list;
struct rcu_head rcu_head;
struct list_head purge;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
};
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
/*
* Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
* in the free path. Could get rid of this if we change the API to return a
* "cookie" from alloc, to be passed to free. But no big deal yet.
*/
static DEFINE_SPINLOCK(vmap_block_tree_lock);
static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);
/*
* We should probably have a fallback mechanism to allocate virtual memory
* out of partially filled vmap blocks. However vmap block sizing should be
* fairly reasonable according to the vmalloc size, so it shouldn't be a
* big problem.
*/
static unsigned long addr_to_vb_idx(unsigned long addr)
{
addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
addr /= VMAP_BLOCK_SIZE;
return addr;
}
static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off)
{
unsigned long addr;
addr = va_start + (pages_off << PAGE_SHIFT);
BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start));
return (void *)addr;
}
/**
* new_vmap_block - allocates new vmap_block and occupies 2^order pages in this
* block. Of course pages number can't exceed VMAP_BBMAP_BITS
* @order: how many 2^order pages should be occupied in newly allocated block
* @gfp_mask: flags for the page level allocator
*
* Return: virtual address in a newly allocated block or ERR_PTR(-errno)
*/
static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
{
struct vmap_block_queue *vbq;
struct vmap_block *vb;
struct vmap_area *va;
unsigned long vb_idx;
int node, err;
void *vaddr;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
node = numa_node_id();
vb = kmalloc_node(sizeof(struct vmap_block),
gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!vb))
return ERR_PTR(-ENOMEM);
va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
VMALLOC_START, VMALLOC_END,
node, gfp_mask);
if (IS_ERR(va)) {
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
kfree(vb);
return ERR_CAST(va);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
err = radix_tree_preload(gfp_mask);
if (unlikely(err)) {
kfree(vb);
free_vmap_area(va);
return ERR_PTR(err);
}
vaddr = vmap_block_vaddr(va->va_start, 0);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
spin_lock_init(&vb->lock);
vb->va = va;
/* At least something should be left free */
BUG_ON(VMAP_BBMAP_BITS <= (1UL << order));
vb->free = VMAP_BBMAP_BITS - (1UL << order);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
vb->dirty = 0;
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
vb->dirty_min = VMAP_BBMAP_BITS;
vb->dirty_max = 0;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
INIT_LIST_HEAD(&vb->free_list);
vb_idx = addr_to_vb_idx(va->va_start);
spin_lock(&vmap_block_tree_lock);
err = radix_tree_insert(&vmap_block_tree, vb_idx, vb);
spin_unlock(&vmap_block_tree_lock);
BUG_ON(err);
radix_tree_preload_end();
vbq = &get_cpu_var(vmap_block_queue);
spin_lock(&vbq->lock);
mm/vmalloc: fix possible exhaustion of vmalloc space caused by vm_map_ram allocator Recently I came across high fragmentation of vm_map_ram allocator: vmap_block has free space, but still new blocks continue to appear. Further investigation showed that certain mapping/unmapping sequences can exhaust vmalloc space. On small 32bit systems that's not a big problem, cause purging will be called soon on a first allocation failure (alloc_vmap_area), but on 64bit machines, e.g. x86_64 has 45 bits of vmalloc space, that can be a disaster. 1) I came up with a simple allocation sequence, which exhausts virtual space very quickly: while (iters) { /* Map/unmap big chunk */ vaddr = vm_map_ram(pages, 16, -1, PAGE_KERNEL); vm_unmap_ram(vaddr, 16); /* Map/unmap small chunks. * * -1 for hole, which should be left at the end of each block * to keep it partially used, with some free space available */ for (i = 0; i < (VMAP_BBMAP_BITS - 16) / 8 - 1; i++) { vaddr = vm_map_ram(pages, 8, -1, PAGE_KERNEL); vm_unmap_ram(vaddr, 8); } } The idea behind is simple: 1. We have to map a big chunk, e.g. 16 pages. 2. Then we have to occupy the remaining space with smaller chunks, i.e. 8 pages. At the end small hole should remain to keep block in free list, but do not let big chunk to occupy remaining space. 3. Goto 1 - allocation request of 16 pages can't be completed (only 8 slots are left free in the block in the #2 step), new block will be allocated, all further requests will lay into newly allocated block. To have some measurement numbers for all further tests I setup ftrace and enabled 4 basic calls in a function profile: echo vm_map_ram > /sys/kernel/debug/tracing/set_ftrace_filter; echo alloc_vmap_area >> /sys/kernel/debug/tracing/set_ftrace_filter; echo vm_unmap_ram >> /sys/kernel/debug/tracing/set_ftrace_filter; echo free_vmap_block >> /sys/kernel/debug/tracing/set_ftrace_filter; So for this scenario I got these results: BEFORE (all new blocks are put to the head of a free list) # cat /sys/kernel/debug/tracing/trace_stat/function0 Function Hit Time Avg s^2 -------- --- ---- --- --- vm_map_ram 126000 30683.30 us 0.243 us 30819.36 us vm_unmap_ram 126000 22003.24 us 0.174 us 340.886 us alloc_vmap_area 1000 4132.065 us 4.132 us 0.903 us AFTER (all new blocks are put to the tail of a free list) # cat /sys/kernel/debug/tracing/trace_stat/function0 Function Hit Time Avg s^2 -------- --- ---- --- --- vm_map_ram 126000 28713.13 us 0.227 us 24944.70 us vm_unmap_ram 126000 20403.96 us 0.161 us 1429.872 us alloc_vmap_area 993 3916.795 us 3.944 us 29.370 us free_vmap_block 992 654.157 us 0.659 us 1.273 us SUMMARY: The most interesting numbers in those tables are numbers of block allocations and deallocations: alloc_vmap_area and free_vmap_block calls, which show that before the change blocks were not freed, and virtual space and physical memory (vmap_block structure allocations, etc) were consumed. Average time which were spent in vm_map_ram/vm_unmap_ram became slightly better. That can be explained with a reasonable amount of blocks in a free list, which we need to iterate to find a suitable free block. 2) Another scenario is a random allocation: while (iters) { /* Randomly take number from a range [1..32/64] */ nr = rand(1, VMAP_MAX_ALLOC); vaddr = vm_map_ram(pages, nr, -1, PAGE_KERNEL); vm_unmap_ram(vaddr, nr); } I chose mersenne twister PRNG to generate persistent random state to guarantee that both runs have the same random sequence. For each vm_map_ram call random number from [1..32/64] was taken to represent amount of pages which I do map. I did 10'000 vm_map_ram calls and got these two tables: BEFORE (all new blocks are put to the head of a free list) # cat /sys/kernel/debug/tracing/trace_stat/function0 Function Hit Time Avg s^2 -------- --- ---- --- --- vm_map_ram 10000 10170.01 us 1.017 us 993.609 us vm_unmap_ram 10000 5321.823 us 0.532 us 59.789 us alloc_vmap_area 420 2150.239 us 5.119 us 3.307 us free_vmap_block 37 159.587 us 4.313 us 134.344 us AFTER (all new blocks are put to the tail of a free list) # cat /sys/kernel/debug/tracing/trace_stat/function0 Function Hit Time Avg s^2 -------- --- ---- --- --- vm_map_ram 10000 7745.637 us 0.774 us 395.229 us vm_unmap_ram 10000 5460.573 us 0.546 us 67.187 us alloc_vmap_area 414 2201.650 us 5.317 us 5.591 us free_vmap_block 412 574.421 us 1.394 us 15.138 us SUMMARY: 'BEFORE' table shows, that 420 blocks were allocated and only 37 were freed. Remained 383 blocks are still in a free list, consuming virtual space and physical memory. 'AFTER' table shows, that 414 blocks were allocated and 412 were really freed. 2 blocks remained in a free list. So fragmentation was dramatically reduced. Why? Because when we put newly allocated block to the head, all further requests will occupy new block, regardless remained space in other blocks. In this scenario all requests come randomly. Eventually remained free space will be less than requested size, free list will be iterated and it is possible that nothing will be found there - finally new block will be created. So exhaustion in random scenario happens for the maximum possible allocation size: 32 pages for 32-bit system and 64 pages for 64-bit system. Also average cost of vm_map_ram was reduced from 1.017 us to 0.774 us. Again this can be explained by iteration through smaller list of free blocks. 3) Next simple scenario is a sequential allocation, when the allocation order is increased for each block. This scenario forces allocator to reach maximum amount of partially free blocks in a free list: while (iters) { /* Populate free list with blocks with remaining space */ for (order = 0; order <= ilog2(VMAP_MAX_ALLOC); order++) { nr = VMAP_BBMAP_BITS / (1 << order); /* Leave a hole */ nr -= 1; for (i = 0; i < nr; i++) { vaddr = vm_map_ram(pages, (1 << order), -1, PAGE_KERNEL); vm_unmap_ram(vaddr, (1 << order)); } /* Completely occupy blocks from a free list */ for (order = 0; order <= ilog2(VMAP_MAX_ALLOC); order++) { vaddr = vm_map_ram(pages, (1 << order), -1, PAGE_KERNEL); vm_unmap_ram(vaddr, (1 << order)); } } Results which I got: BEFORE (all new blocks are put to the head of a free list) # cat /sys/kernel/debug/tracing/trace_stat/function0 Function Hit Time Avg s^2 -------- --- ---- --- --- vm_map_ram 2032000 399545.2 us 0.196 us 467123.7 us vm_unmap_ram 2032000 363225.7 us 0.178 us 111405.9 us alloc_vmap_area 7001 30627.76 us 4.374 us 495.755 us free_vmap_block 6993 7011.685 us 1.002 us 159.090 us AFTER (all new blocks are put to the tail of a free list) # cat /sys/kernel/debug/tracing/trace_stat/function0 Function Hit Time Avg s^2 -------- --- ---- --- --- vm_map_ram 2032000 394259.7 us 0.194 us 589395.9 us vm_unmap_ram 2032000 292500.7 us 0.143 us 94181.08 us alloc_vmap_area 7000 31103.11 us 4.443 us 703.225 us free_vmap_block 7000 6750.844 us 0.964 us 119.112 us SUMMARY: No surprises here, almost all numbers are the same. Fixing this fragmentation problem I also did some improvements in a allocation logic of a new vmap block: occupy block immediately and get rid of extra search in a free list. Also I replaced dirty bitmap with min/max dirty range values to make the logic simpler and slightly faster, since two longs comparison costs less, than loop thru bitmap. This patchset raises several questions: Q: Think the problem you comments is already known so that I wrote comments about it as "it could consume lots of address space through fragmentation". Could you tell me about your situation and reason why it should be avoided? Gioh Kim A: Indeed, there was a commit 364376383 which adds explicit comment about fragmentation. But fragmentation which is described in this comment caused by mixing of long-lived and short-lived objects, when a whole block is pinned in memory because some page slots are still in use. But here I am talking about blocks which are free, nobody uses them, and allocator keeps them alive forever, continuously allocating new blocks. Q: I think that if you put newly allocated block to the tail of a free list, below example would results in enormous performance degradation. new block: 1MB (256 pages) while (iters--) { vm_map_ram(3 or something else not dividable for 256) * 85 vm_unmap_ram(3) * 85 } On every iteration, it needs newly allocated block and it is put to the tail of a free list so finding it consumes large amount of time. Joonsoo Kim A: Second patch in current patchset gets rid of extra search in a free list, so new block will be immediately occupied.. Also, the scenario above is impossible, cause vm_map_ram allocates virtual range in orders, i.e. 2^n. I.e. passing 3 to vm_map_ram you will allocate 4 slots in a block and 256 slots (capacity of a block) of course dividable on 4, so block will be completely occupied. But there is a worst case which we can achieve: each free block has a hole equal to order size. The maximum size of allocation is 64 pages for 64-bit system (if you try to map more, original alloc_vmap_area will be called). So the maximum order is 6. That means that worst case, before allocator makes a decision to allocate a new block, is to iterate 7 blocks: HEAD 1st block - has 1 page slot free (order 0) 2nd block - has 2 page slots free (order 1) 3rd block - has 4 page slots free (order 2) 4th block - has 8 page slots free (order 3) 5th block - has 16 page slots free (order 4) 6th block - has 32 page slots free (order 5) 7th block - has 64 page slots free (order 6) TAIL So the worst scenario on 64-bit system is that each CPU queue can have 7 blocks in a free list. This can happen only and only if you allocate blocks increasing the order. (as I did in the function written in the comment of the first patch) This is weird and rare case, but still it is possible. Afterwards you will get 7 blocks in a list. All further requests should be placed in a newly allocated block or some free slots should be found in a free list. Seems it does not look dramatically awful. This patch (of 3): If suitable block can't be found, new block is allocated and put into a head of a free list, so on next iteration this new block will be found first. That's bad, because old blocks in a free list will not get a chance to be fully used, thus fragmentation will grow. Let's consider this simple example: #1 We have one block in a free list which is partially used, and where only one page is free: HEAD |xxxxxxxxx-| TAIL ^ free space for 1 page, order 0 #2 New allocation request of order 1 (2 pages) comes, new block is allocated since we do not have free space to complete this request. New block is put into a head of a free list: HEAD |----------|xxxxxxxxx-| TAIL #3 Two pages were occupied in a new found block: HEAD |xx--------|xxxxxxxxx-| TAIL ^ two pages mapped here #4 New allocation request of order 0 (1 page) comes. Block, which was created on #2 step, is located at the beginning of a free list, so it will be found first: HEAD |xxX-------|xxxxxxxxx-| TAIL ^ ^ page mapped here, but better to use this hole It is obvious, that it is better to complete request of #4 step using the old block, where free space is left, because in other case fragmentation will be highly increased. But fragmentation is not only the case. The worst thing is that I can easily create scenario, when the whole vmalloc space is exhausted by blocks, which are not used, but already dirty and have several free pages. Let's consider this function which execution should be pinned to one CPU: static void exhaust_virtual_space(struct page *pages[16], int iters) { /* Firstly we have to map a big chunk, e.g. 16 pages. * Then we have to occupy the remaining space with smaller * chunks, i.e. 8 pages. At the end small hole should remain. * So at the end of our allocation sequence block looks like * this: * XX big chunk * |XXxxxxxxx-| x small chunk * - hole, which is enough for a small chunk, * but is not enough for a big chunk */ while (iters--) { int i; void *vaddr; /* Map/unmap big chunk */ vaddr = vm_map_ram(pages, 16, -1, PAGE_KERNEL); vm_unmap_ram(vaddr, 16); /* Map/unmap small chunks. * * -1 for hole, which should be left at the end of each block * to keep it partially used, with some free space available */ for (i = 0; i < (VMAP_BBMAP_BITS - 16) / 8 - 1; i++) { vaddr = vm_map_ram(pages, 8, -1, PAGE_KERNEL); vm_unmap_ram(vaddr, 8); } } } On every iteration new block (1MB of vm area in my case) will be allocated and then will be occupied, without attempt to resolve small allocation request using previously allocated blocks in a free list. In case of random allocation (size should be randomly taken from the range [1..64] in 64-bit case or [1..32] in 32-bit case) situation is the same: new blocks continue to appear if maximum possible allocation size (32 or 64) passed to the allocator, because all remaining blocks in a free list do not have enough free space to complete this allocation request. In summary if new blocks are put into the head of a free list eventually virtual space will be exhausted. In current patch I simply put newly allocated block to the tail of a free list, thus reduce fragmentation, giving a chance to resolve allocation request using older blocks with possible holes left. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:48 +08:00
list_add_tail_rcu(&vb->free_list, &vbq->free);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
spin_unlock(&vbq->lock);
put_cpu_var(vmap_block_queue);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return vaddr;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
static void free_vmap_block(struct vmap_block *vb)
{
struct vmap_block *tmp;
unsigned long vb_idx;
vb_idx = addr_to_vb_idx(vb->va->va_start);
spin_lock(&vmap_block_tree_lock);
tmp = radix_tree_delete(&vmap_block_tree, vb_idx);
spin_unlock(&vmap_block_tree_lock);
BUG_ON(tmp != vb);
vmalloc: eagerly clear ptes on vunmap On stock 2.6.37-rc4, running: # mount lilith:/export /mnt/lilith # find /mnt/lilith/ -type f -print0 | xargs -0 file crashes the machine fairly quickly under Xen. Often it results in oops messages, but the couple of times I tried just now, it just hung quietly and made Xen print some rude messages: (XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp 3000000000000000) for mfn 1d7058 (pfn 18fa7) (XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms (XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp 1000000000000000) for mfn 1d2e04 (pfn 1d1fb) (XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04 Which means the domain tried to map a pagetable page RW, which would allow it to map arbitrary memory, so Xen stopped it. This is because vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had finished with them, and those pages got recycled as pagetable pages while still having these RW aliases. Removing those mappings immediately removes the Xen-visible aliases, and so it has no problem with those pages being reused as pagetable pages. Deferring the TLB flush doesn't upset Xen because it can flush the TLB itself as needed to maintain its invariants. When unmapping a region in the vmalloc space, clear the ptes immediately. There's no point in deferring this because there's no amortization benefit. The TLBs are left dirty, and they are flushed lazily to amortize the cost of the IPIs. This specific motivation for this patch is an oops-causing regression since 2.6.36 when using NFS under Xen, triggered by the NFS client's use of vm_map_ram() introduced in 56e4ebf877b60 ("NFS: readdir with vmapped pages") . XFS also uses vm_map_ram() and could cause similar problems. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Bryan Schumaker <bjschuma@netapp.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Alex Elder <aelder@sgi.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-12-03 06:31:18 +08:00
free_vmap_area_noflush(vb->va);
kfree_rcu(vb, rcu_head);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
static void purge_fragmented_blocks(int cpu)
{
LIST_HEAD(purge);
struct vmap_block *vb;
struct vmap_block *n_vb;
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
rcu_read_lock();
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS))
continue;
spin_lock(&vb->lock);
if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) {
vb->free = 0; /* prevent further allocs after releasing lock */
vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
vb->dirty_min = 0;
vb->dirty_max = VMAP_BBMAP_BITS;
spin_lock(&vbq->lock);
list_del_rcu(&vb->free_list);
spin_unlock(&vbq->lock);
spin_unlock(&vb->lock);
list_add_tail(&vb->purge, &purge);
} else
spin_unlock(&vb->lock);
}
rcu_read_unlock();
list_for_each_entry_safe(vb, n_vb, &purge, purge) {
list_del(&vb->purge);
free_vmap_block(vb);
}
}
static void purge_fragmented_blocks_allcpus(void)
{
int cpu;
for_each_possible_cpu(cpu)
purge_fragmented_blocks(cpu);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
{
struct vmap_block_queue *vbq;
struct vmap_block *vb;
void *vaddr = NULL;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
unsigned int order;
BUG_ON(offset_in_page(size));
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
if (WARN_ON(size == 0)) {
/*
* Allocating 0 bytes isn't what caller wants since
* get_order(0) returns funny result. Just warn and terminate
* early.
*/
return NULL;
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
order = get_order(size);
rcu_read_lock();
vbq = &get_cpu_var(vmap_block_queue);
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
unsigned long pages_off;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
spin_lock(&vb->lock);
if (vb->free < (1UL << order)) {
spin_unlock(&vb->lock);
continue;
}
pages_off = VMAP_BBMAP_BITS - vb->free;
vaddr = vmap_block_vaddr(vb->va->va_start, pages_off);
vb->free -= 1UL << order;
if (vb->free == 0) {
spin_lock(&vbq->lock);
list_del_rcu(&vb->free_list);
spin_unlock(&vbq->lock);
}
spin_unlock(&vb->lock);
break;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
put_cpu_var(vmap_block_queue);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
rcu_read_unlock();
/* Allocate new block if nothing was found */
if (!vaddr)
vaddr = new_vmap_block(order, gfp_mask);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return vaddr;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
static void vb_free(const void *addr, unsigned long size)
{
unsigned long offset;
unsigned long vb_idx;
unsigned int order;
struct vmap_block *vb;
BUG_ON(offset_in_page(size));
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
order = get_order(size);
offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
offset >>= PAGE_SHIFT;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
vb_idx = addr_to_vb_idx((unsigned long)addr);
rcu_read_lock();
vb = radix_tree_lookup(&vmap_block_tree, vb_idx);
rcu_read_unlock();
BUG_ON(!vb);
vmalloc: eagerly clear ptes on vunmap On stock 2.6.37-rc4, running: # mount lilith:/export /mnt/lilith # find /mnt/lilith/ -type f -print0 | xargs -0 file crashes the machine fairly quickly under Xen. Often it results in oops messages, but the couple of times I tried just now, it just hung quietly and made Xen print some rude messages: (XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp 3000000000000000) for mfn 1d7058 (pfn 18fa7) (XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms (XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp 1000000000000000) for mfn 1d2e04 (pfn 1d1fb) (XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04 Which means the domain tried to map a pagetable page RW, which would allow it to map arbitrary memory, so Xen stopped it. This is because vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had finished with them, and those pages got recycled as pagetable pages while still having these RW aliases. Removing those mappings immediately removes the Xen-visible aliases, and so it has no problem with those pages being reused as pagetable pages. Deferring the TLB flush doesn't upset Xen because it can flush the TLB itself as needed to maintain its invariants. When unmapping a region in the vmalloc space, clear the ptes immediately. There's no point in deferring this because there's no amortization benefit. The TLBs are left dirty, and they are flushed lazily to amortize the cost of the IPIs. This specific motivation for this patch is an oops-causing regression since 2.6.36 when using NFS under Xen, triggered by the NFS client's use of vm_map_ram() introduced in 56e4ebf877b60 ("NFS: readdir with vmapped pages") . XFS also uses vm_map_ram() and could cause similar problems. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Bryan Schumaker <bjschuma@netapp.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Alex Elder <aelder@sgi.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-12-03 06:31:18 +08:00
vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
mm, debug_pagealloc: don't rely on static keys too early Commit 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") has introduced a static key to reduce overhead when debug_pagealloc is compiled in but not enabled. It relied on the assumption that jump_label_init() is called before parse_early_param() as in start_kernel(), so when the "debug_pagealloc=on" option is parsed, it is safe to enable the static key. However, it turns out multiple architectures call parse_early_param() earlier from their setup_arch(). x86 also calls jump_label_init() even earlier, so no issue was found while testing the commit, but same is not true for e.g. ppc64 and s390 where the kernel would not boot with debug_pagealloc=on as found by our QA. To fix this without tricky changes to init code of multiple architectures, this patch partially reverts the static key conversion from 96a2b03f281d. Init-time and non-fastpath calls (such as in arch code) of debug_pagealloc_enabled() will again test a simple bool variable. Fastpath mm code is converted to a new debug_pagealloc_enabled_static() variant that relies on the static key, which is enabled in a well-defined point in mm_init() where it's guaranteed that jump_label_init() has been called, regardless of architecture. [sfr@canb.auug.org.au: export _debug_pagealloc_enabled_early] Link: http://lkml.kernel.org/r/20200106164944.063ac07b@canb.auug.org.au Link: http://lkml.kernel.org/r/20191219130612.23171-1-vbabka@suse.cz Fixes: 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Qian Cai <cai@lca.pw> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-01-14 08:29:20 +08:00
if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range((unsigned long)addr,
(unsigned long)addr + size);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
spin_lock(&vb->lock);
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
/* Expand dirty range */
vb->dirty_min = min(vb->dirty_min, offset);
vb->dirty_max = max(vb->dirty_max, offset + (1UL << order));
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
vb->dirty += 1UL << order;
if (vb->dirty == VMAP_BBMAP_BITS) {
BUG_ON(vb->free);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
spin_unlock(&vb->lock);
free_vmap_block(vb);
} else
spin_unlock(&vb->lock);
}
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
{
int cpu;
if (unlikely(!vmap_initialized))
return;
might_sleep();
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
for_each_possible_cpu(cpu) {
struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
struct vmap_block *vb;
rcu_read_lock();
list_for_each_entry_rcu(vb, &vbq->free, free_list) {
spin_lock(&vb->lock);
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
if (vb->dirty) {
unsigned long va_start = vb->va->va_start;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
unsigned long s, e;
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
s = va_start + (vb->dirty_min << PAGE_SHIFT);
e = va_start + (vb->dirty_max << PAGE_SHIFT);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
start = min(s, start);
end = max(e, end);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
mm/vmalloc: get rid of dirty bitmap inside vmap_block structure In original implementation of vm_map_ram made by Nick Piggin there were two bitmaps: alloc_map and dirty_map. None of them were used as supposed to be: finding a suitable free hole for next allocation in block. vm_map_ram allocates space sequentially in block and on free call marks pages as dirty, so freed space can't be reused anymore. Actually it would be very interesting to know the real meaning of those bitmaps, maybe implementation was incomplete, etc. But long time ago Zhang Yanfei removed alloc_map by these two commits: mm/vmalloc.c: remove dead code in vb_alloc 3fcd76e8028e0be37b02a2002b4f56755daeda06 mm/vmalloc.c: remove alloc_map from vmap_block b8e748b6c32999f221ea4786557b8e7e6c4e4e7a In this patch I replaced dirty_map with two range variables: dirty min and max. These variables store minimum and maximum position of dirty space in a block, since we need only to know the dirty range, not exact position of dirty pages. Why it was made? Several reasons: at first glance it seems that vm_map_ram allocator concerns about fragmentation thus it uses bitmaps for finding free hole, but it is not true. To avoid complexity seems it is better to use something simple, like min or max range values. Secondly, code also becomes simpler, without iteration over bitmap, just comparing values in min and max macros. Thirdly, bitmap occupies up to 1024 bits (4MB is a max size of a block). Here I replaced the whole bitmap with two longs. Finally vm_unmap_aliases should be slightly faster and the whole vmap_block structure occupies less memory. Signed-off-by: Roman Pen <r.peniaev@gmail.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Fabian Frederick <fabf@skynet.be> Cc: Christoph Lameter <cl@linux.com> Cc: Gioh Kim <gioh.kim@lge.com> Cc: Rob Jones <rob.jones@codethink.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:13:55 +08:00
flush = 1;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
spin_unlock(&vb->lock);
}
rcu_read_unlock();
}
mutex_lock(&vmap_purge_lock);
purge_fragmented_blocks_allcpus();
if (!__purge_vmap_area_lazy(start, end) && flush)
flush_tlb_kernel_range(start, end);
mutex_unlock(&vmap_purge_lock);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
/**
* vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
*
* The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
* to amortize TLB flushing overheads. What this means is that any page you
* have now, may, in a former life, have been mapped into kernel virtual
* address by the vmap layer and so there might be some CPUs with TLB entries
* still referencing that page (additional to the regular 1:1 kernel mapping).
*
* vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
* be sure that none of the pages we have control over will have any aliases
* from the vmap layer.
*/
void vm_unmap_aliases(void)
{
unsigned long start = ULONG_MAX, end = 0;
int flush = 0;
_vm_unmap_aliases(start, end, flush);
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
/**
* vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
* @mem: the pointer returned by vm_map_ram
* @count: the count passed to that vm_map_ram call (cannot unmap partial)
*/
void vm_unmap_ram(const void *mem, unsigned int count)
{
unsigned long size = (unsigned long)count << PAGE_SHIFT;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
unsigned long addr = (unsigned long)mem;
struct vmap_area *va;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
might_sleep();
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
BUG_ON(!addr);
BUG_ON(addr < VMALLOC_START);
BUG_ON(addr > VMALLOC_END);
BUG_ON(!PAGE_ALIGNED(addr));
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
kasan_poison_vmalloc(mem, size);
if (likely(count <= VMAP_MAX_ALLOC)) {
debug_check_no_locks_freed(mem, size);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
vb_free(mem, size);
return;
}
va = find_vmap_area(addr);
BUG_ON(!va);
debug_check_no_locks_freed((void *)va->va_start,
(va->va_end - va->va_start));
free_unmap_vmap_area(va);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
EXPORT_SYMBOL(vm_unmap_ram);
/**
* vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
* @pages: an array of pointers to the pages to be mapped
* @count: number of pages
* @node: prefer to allocate data structures on this node
* @prot: memory protection to use. PAGE_KERNEL for regular RAM
*
mm/vmalloc.c: enhance vm_map_ram() comment vm_map_ram() has a fragmentation problem when it cannot purge a chunk(ie, 4M address space) if there is a pinning object in that addresss space. So it could consume all VMALLOC address space easily. We can fix the fragmentation problem by using vmap instead of vm_map_ram() but vmap() is known to be slow compared to vm_map_ram(). Minchan said vm_map_ram is 5 times faster than vmap in his tests. So I thought we should fix fragment problem of vm_map_ram because our proprietary GPU driver has used it heavily. On second thought, it's not an easy because we should reuse freed space for solving the problem and it could make more IPI and bitmap operation for searching hole. It could mitigate API's goal which is very fast mapping. And even fragmentation problem wouldn't show in 64 bit machine. Another option is that the user should separate long-life and short-life object and use vmap for long-life but vm_map_ram for short-life. If we inform the user about the characteristic of vm_map_ram the user can choose one according to the page lifetime. Let's add some notice messages to user. [akpm@linux-foundation.org: tweak comment text] Signed-off-by: Gioh Kim <gioh.kim@lge.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 06:37:37 +08:00
* If you use this function for less than VMAP_MAX_ALLOC pages, it could be
* faster than vmap so it's good. But if you mix long-life and short-life
* objects with vm_map_ram(), it could consume lots of address space through
* fragmentation (especially on a 32bit machine). You could see failures in
* the end. Please use this function for short-lived objects.
*
* Returns: a pointer to the address that has been mapped, or %NULL on failure
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
*/
void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
{
unsigned long size = (unsigned long)count << PAGE_SHIFT;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
unsigned long addr;
void *mem;
if (likely(count <= VMAP_MAX_ALLOC)) {
mem = vb_alloc(size, GFP_KERNEL);
if (IS_ERR(mem))
return NULL;
addr = (unsigned long)mem;
} else {
struct vmap_area *va;
va = alloc_vmap_area(size, PAGE_SIZE,
VMALLOC_START, VMALLOC_END, node, GFP_KERNEL);
if (IS_ERR(va))
return NULL;
addr = va->va_start;
mem = (void *)addr;
}
kasan_unpoison_vmalloc(mem, size);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
vm_unmap_ram(mem, count);
return NULL;
}
return mem;
}
EXPORT_SYMBOL(vm_map_ram);
static struct vm_struct *vmlist __initdata;
/**
* vm_area_add_early - add vmap area early during boot
* @vm: vm_struct to add
*
* This function is used to add fixed kernel vm area to vmlist before
* vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags
* should contain proper values and the other fields should be zero.
*
* DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
*/
void __init vm_area_add_early(struct vm_struct *vm)
{
struct vm_struct *tmp, **p;
BUG_ON(vmap_initialized);
for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
if (tmp->addr >= vm->addr) {
BUG_ON(tmp->addr < vm->addr + vm->size);
break;
} else
BUG_ON(tmp->addr + tmp->size > vm->addr);
}
vm->next = *p;
*p = vm;
}
/**
* vm_area_register_early - register vmap area early during boot
* @vm: vm_struct to register
* @align: requested alignment
*
* This function is used to register kernel vm area before
* vmalloc_init() is called. @vm->size and @vm->flags should contain
* proper values on entry and other fields should be zero. On return,
* vm->addr contains the allocated address.
*
* DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
*/
void __init vm_area_register_early(struct vm_struct *vm, size_t align)
{
static size_t vm_init_off __initdata;
unsigned long addr;
addr = ALIGN(VMALLOC_START + vm_init_off, align);
vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;
vm->addr = (void *)addr;
vm_area_add_early(vm);
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static void vmap_init_free_space(void)
{
unsigned long vmap_start = 1;
const unsigned long vmap_end = ULONG_MAX;
struct vmap_area *busy, *free;
/*
* B F B B B F
* -|-----|.....|-----|-----|-----|.....|-
* | The KVA space |
* |<--------------------------------->|
*/
list_for_each_entry(busy, &vmap_area_list, list) {
if (busy->va_start - vmap_start > 0) {
free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
if (!WARN_ON_ONCE(!free)) {
free->va_start = vmap_start;
free->va_end = busy->va_start;
insert_vmap_area_augment(free, NULL,
&free_vmap_area_root,
&free_vmap_area_list);
}
}
vmap_start = busy->va_end;
}
if (vmap_end - vmap_start > 0) {
free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
if (!WARN_ON_ONCE(!free)) {
free->va_start = vmap_start;
free->va_end = vmap_end;
insert_vmap_area_augment(free, NULL,
&free_vmap_area_root,
&free_vmap_area_list);
}
}
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
void __init vmalloc_init(void)
{
struct vmap_area *va;
struct vm_struct *tmp;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
int i;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* Create the cache for vmap_area objects.
*/
vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
for_each_possible_cpu(i) {
struct vmap_block_queue *vbq;
struct vfree_deferred *p;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
vbq = &per_cpu(vmap_block_queue, i);
spin_lock_init(&vbq->lock);
INIT_LIST_HEAD(&vbq->free);
p = &per_cpu(vfree_deferred, i);
init_llist_head(&p->list);
INIT_WORK(&p->wq, free_work);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
/* Import existing vmlist entries. */
for (tmp = vmlist; tmp; tmp = tmp->next) {
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
if (WARN_ON_ONCE(!va))
continue;
va->va_start = (unsigned long)tmp->addr;
va->va_end = va->va_start + tmp->size;
va->vm = tmp;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/*
* Now we can initialize a free vmap space.
*/
vmap_init_free_space();
vmap_initialized = true;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
/**
* map_kernel_range_noflush - map kernel VM area with the specified pages
* @addr: start of the VM area to map
* @size: size of the VM area to map
* @prot: page protection flags to use
* @pages: pages to map
*
* Map PFN_UP(@size) pages at @addr. The VM area @addr and @size
* specify should have been allocated using get_vm_area() and its
* friends.
*
* NOTE:
* This function does NOT do any cache flushing. The caller is
* responsible for calling flush_cache_vmap() on to-be-mapped areas
* before calling this function.
*
* RETURNS:
* The number of pages mapped on success, -errno on failure.
*/
int map_kernel_range_noflush(unsigned long addr, unsigned long size,
pgprot_t prot, struct page **pages)
{
return vmap_page_range_noflush(addr, addr + size, prot, pages);
}
/**
* unmap_kernel_range_noflush - unmap kernel VM area
* @addr: start of the VM area to unmap
* @size: size of the VM area to unmap
*
* Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size
* specify should have been allocated using get_vm_area() and its
* friends.
*
* NOTE:
* This function does NOT do any cache flushing. The caller is
* responsible for calling flush_cache_vunmap() on to-be-mapped areas
* before calling this function and flush_tlb_kernel_range() after.
*/
void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
{
vunmap_page_range(addr, addr + size);
}
EXPORT_SYMBOL_GPL(unmap_kernel_range_noflush);
/**
* unmap_kernel_range - unmap kernel VM area and flush cache and TLB
* @addr: start of the VM area to unmap
* @size: size of the VM area to unmap
*
* Similar to unmap_kernel_range_noflush() but flushes vcache before
* the unmapping and tlb after.
*/
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
void unmap_kernel_range(unsigned long addr, unsigned long size)
{
unsigned long end = addr + size;
flush_cache_vunmap(addr, end);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
vunmap_page_range(addr, end);
flush_tlb_kernel_range(addr, end);
}
EXPORT_SYMBOL_GPL(unmap_kernel_range);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
{
unsigned long addr = (unsigned long)area->addr;
unsigned long end = addr + get_vm_area_size(area);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
int err;
err = vmap_page_range(addr, end, prot, pages);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return err > 0 ? 0 : err;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
}
EXPORT_SYMBOL_GPL(map_vm_area);
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
static inline void setup_vmalloc_vm_locked(struct vm_struct *vm,
struct vmap_area *va, unsigned long flags, const void *caller)
{
vm->flags = flags;
vm->addr = (void *)va->va_start;
vm->size = va->va_end - va->va_start;
vm->caller = caller;
va->vm = vm;
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
}
static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
unsigned long flags, const void *caller)
{
spin_lock(&vmap_area_lock);
setup_vmalloc_vm_locked(vm, va, flags, caller);
spin_unlock(&vmap_area_lock);
}
static void clear_vm_uninitialized_flag(struct vm_struct *vm)
{
2013-04-30 06:07:35 +08:00
/*
* Before removing VM_UNINITIALIZED,
2013-04-30 06:07:35 +08:00
* we should make sure that vm has proper values.
* Pair with smp_rmb() in show_numa_info().
*/
smp_wmb();
vm->flags &= ~VM_UNINITIALIZED;
}
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
static struct vm_struct *__get_vm_area_node(unsigned long size,
unsigned long align, unsigned long flags, unsigned long start,
unsigned long end, int node, gfp_t gfp_mask, const void *caller)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
{
struct vmap_area *va;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
struct vm_struct *area;
unsigned long requested_size = size;
BUG_ON(in_interrupt());
size = PAGE_ALIGN(size);
if (unlikely(!size))
return NULL;
if (flags & VM_IOREMAP)
align = 1ul << clamp_t(int, get_count_order_long(size),
PAGE_SHIFT, IOREMAP_MAX_ORDER);
area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!area))
return NULL;
mm: vmalloc: add flag preventing guard hole allocation For instrumenting global variables KASan will shadow memory backing memory for modules. So on module loading we will need to allocate memory for shadow and map it at address in shadow that corresponds to the address allocated in module_alloc(). __vmalloc_node_range() could be used for this purpose, except it puts a guard hole after allocated area. Guard hole in shadow memory should be a problem because at some future point we might need to have a shadow memory at address occupied by guard hole. So we could fail to allocate shadow for module_alloc(). Add a new vm_struct flag 'VM_NO_GUARD' indicating that vm area doesn't have a guard hole. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 06:40:03 +08:00
if (!(flags & VM_NO_GUARD))
size += PAGE_SIZE;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
va = alloc_vmap_area(size, align, start, end, node, gfp_mask);
if (IS_ERR(va)) {
kfree(area);
return NULL;
}
kasan_unpoison_vmalloc((void *)va->va_start, requested_size);
setup_vmalloc_vm(area, va, flags, caller);
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
return area;
}
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end)
{
return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
GFP_KERNEL, __builtin_return_address(0));
}
EXPORT_SYMBOL_GPL(__get_vm_area);
struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end,
const void *caller)
{
return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
GFP_KERNEL, caller);
}
/**
* get_vm_area - reserve a contiguous kernel virtual area
* @size: size of the area
* @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC
*
* Search an area of @size in the kernel virtual mapping area,
* and reserved it for out purposes. Returns the area descriptor
* on success or %NULL on failure.
*
* Return: the area descriptor on success or %NULL on failure.
*/
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
{
return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
NUMA_NO_NODE, GFP_KERNEL,
__builtin_return_address(0));
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
}
struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
const void *caller)
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
{
return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
NUMA_NO_NODE, GFP_KERNEL, caller);
}
/**
* find_vm_area - find a continuous kernel virtual area
* @addr: base address
*
* Search for the kernel VM area starting at @addr, and return it.
* It is up to the caller to do all required locking to keep the returned
* pointer valid.
*
* Return: pointer to the found area or %NULL on faulure
*/
struct vm_struct *find_vm_area(const void *addr)
{
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
struct vmap_area *va;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
va = find_vmap_area((unsigned long)addr);
if (!va)
return NULL;
return va->vm;
}
/**
* remove_vm_area - find and remove a continuous kernel virtual area
* @addr: base address
*
* Search for the kernel VM area starting at @addr, and remove it.
* This function returns the found VM area, but using it is NOT safe
* on SMP machines, except for its size or flags.
*
* Return: pointer to the found area or %NULL on faulure
*/
struct vm_struct *remove_vm_area(const void *addr)
{
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
struct vmap_area *va;
might_sleep();
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
spin_lock(&vmap_area_lock);
va = __find_vmap_area((unsigned long)addr);
if (va && va->vm) {
struct vm_struct *vm = va->vm;
va->vm = NULL;
spin_unlock(&vmap_area_lock);
kasan_free_shadow(vm);
free_unmap_vmap_area(va);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return vm;
}
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
spin_unlock(&vmap_area_lock);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return NULL;
}
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
static inline void set_area_direct_map(const struct vm_struct *area,
int (*set_direct_map)(struct page *page))
{
int i;
for (i = 0; i < area->nr_pages; i++)
if (page_address(area->pages[i]))
set_direct_map(area->pages[i]);
}
/* Handle removing and resetting vm mappings related to the vm_struct. */
static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
{
unsigned long start = ULONG_MAX, end = 0;
int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
mm/vmalloc: Avoid rare case of flushing TLB with weird arguments In a rare case, flush_tlb_kernel_range() could be called with a start higher than the end. In vm_remove_mappings(), in case page_address() returns 0 for all pages (for example they were all in highmem), _vm_unmap_aliases() will be called with start = ULONG_MAX, end = 0 and flush = 1. If at the same time, the vmalloc purge operation is triggered by something else while the current operation is between remove_vm_area() and _vm_unmap_aliases(), then the vm mapping just removed will be already purged. In this case the call of vm_unmap_aliases() may not find any other mappings to flush and so end up flushing start = ULONG_MAX, end = 0. So only set flush = true if we find something in the direct mapping that we need to flush, and this way this can't happen. Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Meelis Roos <mroos@linux.ee> Cc: Nadav Amit <namit@vmware.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 868b104d7379 ("mm/vmalloc: Add flag for freeing of special permsissions") Link: https://lkml.kernel.org/r/20190527211058.2729-3-rick.p.edgecombe@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-05-28 05:10:58 +08:00
int flush_dmap = 0;
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
int i;
remove_vm_area(area->addr);
/* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
if (!flush_reset)
return;
/*
* If not deallocating pages, just do the flush of the VM area and
* return.
*/
if (!deallocate_pages) {
vm_unmap_aliases();
return;
}
/*
* If execution gets here, flush the vm mapping and reset the direct
* map. Find the start and end range of the direct mappings to make sure
* the vm_unmap_aliases() flush includes the direct map.
*/
for (i = 0; i < area->nr_pages; i++) {
unsigned long addr = (unsigned long)page_address(area->pages[i]);
if (addr) {
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
start = min(addr, start);
end = max(addr + PAGE_SIZE, end);
mm/vmalloc: Avoid rare case of flushing TLB with weird arguments In a rare case, flush_tlb_kernel_range() could be called with a start higher than the end. In vm_remove_mappings(), in case page_address() returns 0 for all pages (for example they were all in highmem), _vm_unmap_aliases() will be called with start = ULONG_MAX, end = 0 and flush = 1. If at the same time, the vmalloc purge operation is triggered by something else while the current operation is between remove_vm_area() and _vm_unmap_aliases(), then the vm mapping just removed will be already purged. In this case the call of vm_unmap_aliases() may not find any other mappings to flush and so end up flushing start = ULONG_MAX, end = 0. So only set flush = true if we find something in the direct mapping that we need to flush, and this way this can't happen. Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Meelis Roos <mroos@linux.ee> Cc: Nadav Amit <namit@vmware.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 868b104d7379 ("mm/vmalloc: Add flag for freeing of special permsissions") Link: https://lkml.kernel.org/r/20190527211058.2729-3-rick.p.edgecombe@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-05-28 05:10:58 +08:00
flush_dmap = 1;
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
}
}
/*
* Set direct map to something invalid so that it won't be cached if
* there are any accesses after the TLB flush, then flush the TLB and
* reset the direct map permissions to the default.
*/
set_area_direct_map(area, set_direct_map_invalid_noflush);
mm/vmalloc: Avoid rare case of flushing TLB with weird arguments In a rare case, flush_tlb_kernel_range() could be called with a start higher than the end. In vm_remove_mappings(), in case page_address() returns 0 for all pages (for example they were all in highmem), _vm_unmap_aliases() will be called with start = ULONG_MAX, end = 0 and flush = 1. If at the same time, the vmalloc purge operation is triggered by something else while the current operation is between remove_vm_area() and _vm_unmap_aliases(), then the vm mapping just removed will be already purged. In this case the call of vm_unmap_aliases() may not find any other mappings to flush and so end up flushing start = ULONG_MAX, end = 0. So only set flush = true if we find something in the direct mapping that we need to flush, and this way this can't happen. Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Meelis Roos <mroos@linux.ee> Cc: Nadav Amit <namit@vmware.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 868b104d7379 ("mm/vmalloc: Add flag for freeing of special permsissions") Link: https://lkml.kernel.org/r/20190527211058.2729-3-rick.p.edgecombe@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-05-28 05:10:58 +08:00
_vm_unmap_aliases(start, end, flush_dmap);
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
set_area_direct_map(area, set_direct_map_default_noflush);
}
static void __vunmap(const void *addr, int deallocate_pages)
{
struct vm_struct *area;
if (!addr)
return;
if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
addr))
return;
area = find_vm_area(addr);
if (unlikely(!area)) {
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
addr);
return;
}
debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
kasan_poison_vmalloc(area->addr, area->size);
kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework] Signed-off-by: Daniel Axtens <dja@axtens.net> Co-developed-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Vasily Gorbik <gor@linux.ibm.com> Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Qian Cai <cai@lca.pw> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:50 +08:00
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
vm_remove_mappings(area, deallocate_pages);
if (deallocate_pages) {
int i;
for (i = 0; i < area->nr_pages; i++) {
struct page *page = area->pages[i];
BUG_ON(!page);
mm: charge/uncharge kmemcg from generic page allocator paths Currently, to charge a non-slab allocation to kmemcg one has to use alloc_kmem_pages helper with __GFP_ACCOUNT flag. A page allocated with this helper should finally be freed using free_kmem_pages, otherwise it won't be uncharged. This API suits its current users fine, but it turns out to be impossible to use along with page reference counting, i.e. when an allocation is supposed to be freed with put_page, as it is the case with pipe or unix socket buffers. To overcome this limitation, this patch moves charging/uncharging to generic page allocator paths, i.e. to __alloc_pages_nodemask and free_pages_prepare, and zaps alloc/free_kmem_pages helpers. This way, one can use any of the available page allocation functions to get the allocated page charged to kmemcg - it's enough to pass __GFP_ACCOUNT, just like in case of kmalloc and friends. A charged page will be automatically uncharged on free. To make it possible, we need to mark pages charged to kmemcg somehow. To avoid introducing a new page flag, we make use of page->_mapcount for marking such pages. Since pages charged to kmemcg are not supposed to be mapped to userspace, it should work just fine. There are other (ab)users of page->_mapcount - buddy and balloon pages - but we don't conflict with them. In case kmemcg is compiled out or not used at runtime, this patch introduces no overhead to generic page allocator paths. If kmemcg is used, it will be plus one gfp flags check on alloc and plus one page->_mapcount check on free, which shouldn't hurt performance, because the data accessed are hot. Link: http://lkml.kernel.org/r/a9736d856f895bcb465d9f257b54efe32eda6f99.1464079538.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-27 06:24:24 +08:00
__free_pages(page, 0);
}
atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
kvfree(area->pages);
}
kfree(area);
return;
}
static inline void __vfree_deferred(const void *addr)
{
/*
* Use raw_cpu_ptr() because this can be called from preemptible
* context. Preemption is absolutely fine here, because the llist_add()
* implementation is lockless, so it works even if we are adding to
* nother cpu's list. schedule_work() should be fine with this too.
*/
struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred);
if (llist_add((struct llist_node *)addr, &p->list))
schedule_work(&p->wq);
}
/**
* vfree_atomic - release memory allocated by vmalloc()
* @addr: memory base address
*
* This one is just like vfree() but can be called in any atomic context
* except NMIs.
*/
void vfree_atomic(const void *addr)
{
BUG_ON(in_nmi());
kmemleak_free(addr);
if (!addr)
return;
__vfree_deferred(addr);
}
static void __vfree(const void *addr)
{
if (unlikely(in_interrupt()))
__vfree_deferred(addr);
else
__vunmap(addr, 1);
}
/**
* vfree - release memory allocated by vmalloc()
* @addr: memory base address
*
* Free the virtually continuous memory area starting at @addr, as
* obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
* NULL, no operation is performed.
*
* Must not be called in NMI context (strictly speaking, only if we don't
* have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
* conventions for vfree() arch-depenedent would be a really bad idea)
*
* May sleep if called *not* from interrupt context.
*
* NOTE: assumes that the object at @addr has a size >= sizeof(llist_node)
*/
void vfree(const void *addr)
{
BUG_ON(in_nmi());
kmemleak_free(addr);
might_sleep_if(!in_interrupt());
if (!addr)
return;
__vfree(addr);
}
EXPORT_SYMBOL(vfree);
/**
* vunmap - release virtual mapping obtained by vmap()
* @addr: memory base address
*
* Free the virtually contiguous memory area starting at @addr,
* which was created from the page array passed to vmap().
*
* Must not be called in interrupt context.
*/
void vunmap(const void *addr)
{
BUG_ON(in_interrupt());
might_sleep();
if (addr)
__vunmap(addr, 0);
}
EXPORT_SYMBOL(vunmap);
/**
* vmap - map an array of pages into virtually contiguous space
* @pages: array of page pointers
* @count: number of pages to map
* @flags: vm_area->flags
* @prot: page protection for the mapping
*
* Maps @count pages from @pages into contiguous kernel virtual
* space.
*
* Return: the address of the area or %NULL on failure
*/
void *vmap(struct page **pages, unsigned int count,
unsigned long flags, pgprot_t prot)
{
struct vm_struct *area;
unsigned long size; /* In bytes */
might_sleep();
if (count > totalram_pages())
return NULL;
size = (unsigned long)count << PAGE_SHIFT;
area = get_vm_area_caller(size, flags, __builtin_return_address(0));
if (!area)
return NULL;
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
if (map_vm_area(area, prot, pages)) {
vunmap(area->addr);
return NULL;
}
return area->addr;
}
EXPORT_SYMBOL(vmap);
mm, vmalloc: fix vmalloc users tracking properly Commit 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") has pulled asm/pgtable.h include dependency to linux/vmalloc.h and that turned out to be a bad idea for some architectures. E.g. m68k fails with In file included from arch/m68k/include/asm/pgtable_mm.h:145:0, from arch/m68k/include/asm/pgtable.h:4, from include/linux/vmalloc.h:9, from arch/m68k/kernel/module.c:9: arch/m68k/include/asm/mcf_pgtable.h: In function 'nocache_page': >> arch/m68k/include/asm/mcf_pgtable.h:339:43: error: 'init_mm' undeclared (first use in this function) #define pgd_offset_k(address) pgd_offset(&init_mm, address) as spotted by kernel build bot. nios2 fails for other reason In file included from include/asm-generic/io.h:767:0, from arch/nios2/include/asm/io.h:61, from include/linux/io.h:25, from arch/nios2/include/asm/pgtable.h:18, from include/linux/mm.h:70, from include/linux/pid_namespace.h:6, from include/linux/ptrace.h:9, from arch/nios2/include/uapi/asm/elf.h:23, from arch/nios2/include/asm/elf.h:22, from include/linux/elf.h:4, from include/linux/module.h:15, from init/main.c:16: include/linux/vmalloc.h: In function '__vmalloc_node_flags': include/linux/vmalloc.h:99:40: error: 'PAGE_KERNEL' undeclared (first use in this function); did you mean 'GFP_KERNEL'? which is due to the newly added #include <asm/pgtable.h>, which on nios2 includes <linux/io.h> and thus <asm/io.h> and <asm-generic/io.h> which again includes <linux/vmalloc.h>. Tweaking that around just turns out a bigger headache than necessary. This patch reverts 1f5307b1e094 and reimplements the original fix in a different way. __vmalloc_node_flags can stay static inline which will cover vmalloc* functions. We only have one external user (kvmalloc_node) and we can export __vmalloc_node_flags_caller and provide the caller directly. This is much simpler and it doesn't really need any games with header files. [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: revert old comment] Link: http://lkml.kernel.org/r/20170509211054.GB16325@dhcp22.suse.cz Fixes: 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") Link: http://lkml.kernel.org/r/20170509153702.GR6481@dhcp22.suse.cz Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-13 06:46:41 +08:00
static void *__vmalloc_node(unsigned long size, unsigned long align,
gfp_t gfp_mask, pgprot_t prot,
int node, const void *caller);
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
pgprot_t prot, int node)
{
struct page **pages;
unsigned int nr_pages, array_size, i;
const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ?
0 :
__GFP_HIGHMEM;
nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
array_size = (nr_pages * sizeof(struct page *));
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask,
PAGE_KERNEL, node, area->caller);
} else {
pages = kmalloc_node(array_size, nested_gfp, node);
}
if (!pages) {
remove_vm_area(area->addr);
kfree(area);
return NULL;
}
area->pages = pages;
area->nr_pages = nr_pages;
for (i = 0; i < area->nr_pages; i++) {
struct page *page;
if (node == NUMA_NO_NODE)
page = alloc_page(alloc_mask|highmem_mask);
else
page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vunmap() */
area->nr_pages = i;
atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
goto fail;
}
area->pages[i] = page;
if (gfpflags_allow_blocking(gfp_mask))
cond_resched();
}
atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
if (map_vm_area(area, prot, pages))
goto fail;
return area->addr;
fail:
warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure, allocated %ld of %ld bytes",
mm: print vmalloc() state after allocation failures I was tracking down a page allocation failure that ended up in vmalloc(). Since vmalloc() uses 0-order pages, if somebody asks for an insane amount of memory, we'll still get a warning with "order:0" in it. That's not very useful. During recovery, vmalloc() also nicely frees all of the memory that it got up to the point of the failure. That is wonderful, but it also quickly hides any issues. We have a much different sitation if vmalloc() repeatedly fails 10GB in to: vmalloc(100 * 1<<30); versus repeatedly failing 4096 bytes in to a: vmalloc(8192); This patch will print out messages that look like this: [ 68.123503] vmalloc: allocation failure, allocated 6680576 of 13426688 bytes [ 68.124218] bash: page allocation failure: order:0, mode:0xd2 [ 68.124811] Pid: 3770, comm: bash Not tainted 2.6.39-rc3-00082-g85f2e68-dirty #333 [ 68.125579] Call Trace: [ 68.125853] [<ffffffff810f6da6>] warn_alloc_failed+0x146/0x170 [ 68.126464] [<ffffffff8107e05c>] ? printk+0x6c/0x70 [ 68.126791] [<ffffffff8112b5d4>] ? alloc_pages_current+0x94/0xe0 [ 68.127661] [<ffffffff8111ed37>] __vmalloc_node_range+0x237/0x290 ... The 'order' variable is added for clarity when calling warn_alloc_failed() to avoid having an unexplained '0' as an argument. The 'tmp_mask' is because adding an open-coded '| __GFP_NOWARN' would take us over 80 columns for the alloc_pages_node() call. If we are going to add a line, it might as well be one that makes the sucker easier to read. As a side issue, I also noticed that ctl_ioctl() does vmalloc() based solely on an unverified value passed in from userspace. Granted, it's under CAP_SYS_ADMIN, but it still frightens me a bit. Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Cc: Michal Nazarewicz <mina86@mina86.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:12:18 +08:00
(area->nr_pages*PAGE_SIZE), area->size);
__vfree(area->addr);
return NULL;
}
/**
* __vmalloc_node_range - allocate virtually contiguous memory
* @size: allocation size
* @align: desired alignment
* @start: vm area range start
* @end: vm area range end
* @gfp_mask: flags for the page level allocator
* @prot: protection mask for the allocated pages
* @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD)
* @node: node to use for allocation or NUMA_NO_NODE
* @caller: caller's return address
*
* Allocate enough pages to cover @size from the page level
* allocator with @gfp_mask flags. Map them into contiguous
* kernel virtual space, using a pagetable protection of @prot.
*
* Return: the address of the area or %NULL on failure
*/
void *__vmalloc_node_range(unsigned long size, unsigned long align,
unsigned long start, unsigned long end, gfp_t gfp_mask,
mm: vmalloc: pass additional vm_flags to __vmalloc_node_range() For instrumenting global variables KASan will shadow memory backing memory for modules. So on module loading we will need to allocate memory for shadow and map it at address in shadow that corresponds to the address allocated in module_alloc(). __vmalloc_node_range() could be used for this purpose, except it puts a guard hole after allocated area. Guard hole in shadow memory should be a problem because at some future point we might need to have a shadow memory at address occupied by guard hole. So we could fail to allocate shadow for module_alloc(). Now we have VM_NO_GUARD flag disabling guard page, so we need to pass into __vmalloc_node_range(). Add new parameter 'vm_flags' to __vmalloc_node_range() function. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 06:40:07 +08:00
pgprot_t prot, unsigned long vm_flags, int node,
const void *caller)
{
struct vm_struct *area;
void *addr;
unsigned long real_size = size;
size = PAGE_ALIGN(size);
if (!size || (size >> PAGE_SHIFT) > totalram_pages())
goto fail;
area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |
mm: vmalloc: pass additional vm_flags to __vmalloc_node_range() For instrumenting global variables KASan will shadow memory backing memory for modules. So on module loading we will need to allocate memory for shadow and map it at address in shadow that corresponds to the address allocated in module_alloc(). __vmalloc_node_range() could be used for this purpose, except it puts a guard hole after allocated area. Guard hole in shadow memory should be a problem because at some future point we might need to have a shadow memory at address occupied by guard hole. So we could fail to allocate shadow for module_alloc(). Now we have VM_NO_GUARD flag disabling guard page, so we need to pass into __vmalloc_node_range(). Add new parameter 'vm_flags' to __vmalloc_node_range() function. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 06:40:07 +08:00
vm_flags, start, end, node, gfp_mask, caller);
if (!area)
goto fail;
addr = __vmalloc_area_node(area, gfp_mask, prot, node);
if (!addr)
return NULL;
/*
* In this function, newly allocated vm_struct has VM_UNINITIALIZED
* flag. It means that vm_struct is not fully initialized.
* Now, it is fully initialized, so remove this flag here.
*/
clear_vm_uninitialized_flag(area);
kmemleak_vmalloc(area, size, gfp_mask);
return addr;
fail:
warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure: %lu bytes", real_size);
return NULL;
}
/*
* This is only for performance analysis of vmalloc and stress purpose.
* It is required by vmalloc test module, therefore do not use it other
* than that.
*/
#ifdef CONFIG_TEST_VMALLOC_MODULE
EXPORT_SYMBOL_GPL(__vmalloc_node_range);
#endif
/**
* __vmalloc_node - allocate virtually contiguous memory
* @size: allocation size
* @align: desired alignment
* @gfp_mask: flags for the page level allocator
* @prot: protection mask for the allocated pages
* @node: node to use for allocation or NUMA_NO_NODE
* @caller: caller's return address
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:57:09 +08:00
*
* Allocate enough pages to cover @size from the page level
* allocator with @gfp_mask flags. Map them into contiguous
* kernel virtual space, using a pagetable protection of @prot.
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:57:09 +08:00
*
* Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
* and __GFP_NOFAIL are not supported
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:57:09 +08:00
*
* Any use of gfp flags outside of GFP_KERNEL should be consulted
* with mm people.
*
* Return: pointer to the allocated memory or %NULL on error
*/
mm, vmalloc: fix vmalloc users tracking properly Commit 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") has pulled asm/pgtable.h include dependency to linux/vmalloc.h and that turned out to be a bad idea for some architectures. E.g. m68k fails with In file included from arch/m68k/include/asm/pgtable_mm.h:145:0, from arch/m68k/include/asm/pgtable.h:4, from include/linux/vmalloc.h:9, from arch/m68k/kernel/module.c:9: arch/m68k/include/asm/mcf_pgtable.h: In function 'nocache_page': >> arch/m68k/include/asm/mcf_pgtable.h:339:43: error: 'init_mm' undeclared (first use in this function) #define pgd_offset_k(address) pgd_offset(&init_mm, address) as spotted by kernel build bot. nios2 fails for other reason In file included from include/asm-generic/io.h:767:0, from arch/nios2/include/asm/io.h:61, from include/linux/io.h:25, from arch/nios2/include/asm/pgtable.h:18, from include/linux/mm.h:70, from include/linux/pid_namespace.h:6, from include/linux/ptrace.h:9, from arch/nios2/include/uapi/asm/elf.h:23, from arch/nios2/include/asm/elf.h:22, from include/linux/elf.h:4, from include/linux/module.h:15, from init/main.c:16: include/linux/vmalloc.h: In function '__vmalloc_node_flags': include/linux/vmalloc.h:99:40: error: 'PAGE_KERNEL' undeclared (first use in this function); did you mean 'GFP_KERNEL'? which is due to the newly added #include <asm/pgtable.h>, which on nios2 includes <linux/io.h> and thus <asm/io.h> and <asm-generic/io.h> which again includes <linux/vmalloc.h>. Tweaking that around just turns out a bigger headache than necessary. This patch reverts 1f5307b1e094 and reimplements the original fix in a different way. __vmalloc_node_flags can stay static inline which will cover vmalloc* functions. We only have one external user (kvmalloc_node) and we can export __vmalloc_node_flags_caller and provide the caller directly. This is much simpler and it doesn't really need any games with header files. [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: revert old comment] Link: http://lkml.kernel.org/r/20170509211054.GB16325@dhcp22.suse.cz Fixes: 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") Link: http://lkml.kernel.org/r/20170509153702.GR6481@dhcp22.suse.cz Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-13 06:46:41 +08:00
static void *__vmalloc_node(unsigned long size, unsigned long align,
gfp_t gfp_mask, pgprot_t prot,
int node, const void *caller)
{
return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
mm: vmalloc: pass additional vm_flags to __vmalloc_node_range() For instrumenting global variables KASan will shadow memory backing memory for modules. So on module loading we will need to allocate memory for shadow and map it at address in shadow that corresponds to the address allocated in module_alloc(). __vmalloc_node_range() could be used for this purpose, except it puts a guard hole after allocated area. Guard hole in shadow memory should be a problem because at some future point we might need to have a shadow memory at address occupied by guard hole. So we could fail to allocate shadow for module_alloc(). Now we have VM_NO_GUARD flag disabling guard page, so we need to pass into __vmalloc_node_range(). Add new parameter 'vm_flags' to __vmalloc_node_range() function. Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Konstantin Serebryany <kcc@google.com> Cc: Dmitry Chernenkov <dmitryc@google.com> Signed-off-by: Andrey Konovalov <adech.fo@gmail.com> Cc: Yuri Gribov <tetra2005@gmail.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-14 06:40:07 +08:00
gfp_mask, prot, 0, node, caller);
}
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE,
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
__builtin_return_address(0));
}
EXPORT_SYMBOL(__vmalloc);
mm, vmalloc: fix vmalloc users tracking properly Commit 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") has pulled asm/pgtable.h include dependency to linux/vmalloc.h and that turned out to be a bad idea for some architectures. E.g. m68k fails with In file included from arch/m68k/include/asm/pgtable_mm.h:145:0, from arch/m68k/include/asm/pgtable.h:4, from include/linux/vmalloc.h:9, from arch/m68k/kernel/module.c:9: arch/m68k/include/asm/mcf_pgtable.h: In function 'nocache_page': >> arch/m68k/include/asm/mcf_pgtable.h:339:43: error: 'init_mm' undeclared (first use in this function) #define pgd_offset_k(address) pgd_offset(&init_mm, address) as spotted by kernel build bot. nios2 fails for other reason In file included from include/asm-generic/io.h:767:0, from arch/nios2/include/asm/io.h:61, from include/linux/io.h:25, from arch/nios2/include/asm/pgtable.h:18, from include/linux/mm.h:70, from include/linux/pid_namespace.h:6, from include/linux/ptrace.h:9, from arch/nios2/include/uapi/asm/elf.h:23, from arch/nios2/include/asm/elf.h:22, from include/linux/elf.h:4, from include/linux/module.h:15, from init/main.c:16: include/linux/vmalloc.h: In function '__vmalloc_node_flags': include/linux/vmalloc.h:99:40: error: 'PAGE_KERNEL' undeclared (first use in this function); did you mean 'GFP_KERNEL'? which is due to the newly added #include <asm/pgtable.h>, which on nios2 includes <linux/io.h> and thus <asm/io.h> and <asm-generic/io.h> which again includes <linux/vmalloc.h>. Tweaking that around just turns out a bigger headache than necessary. This patch reverts 1f5307b1e094 and reimplements the original fix in a different way. __vmalloc_node_flags can stay static inline which will cover vmalloc* functions. We only have one external user (kvmalloc_node) and we can export __vmalloc_node_flags_caller and provide the caller directly. This is much simpler and it doesn't really need any games with header files. [akpm@linux-foundation.org: coding-style fixes] [mhocko@kernel.org: revert old comment] Link: http://lkml.kernel.org/r/20170509211054.GB16325@dhcp22.suse.cz Fixes: 1f5307b1e094 ("mm, vmalloc: properly track vmalloc users") Link: http://lkml.kernel.org/r/20170509153702.GR6481@dhcp22.suse.cz Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-13 06:46:41 +08:00
static inline void *__vmalloc_node_flags(unsigned long size,
int node, gfp_t flags)
{
return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
node, __builtin_return_address(0));
}
void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags,
void *caller)
{
return __vmalloc_node(size, 1, flags, PAGE_KERNEL, node, caller);
}
/**
* vmalloc - allocate virtually contiguous memory
* @size: allocation size
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc(unsigned long size)
{
return __vmalloc_node_flags(size, NUMA_NO_NODE,
GFP_KERNEL);
}
EXPORT_SYMBOL(vmalloc);
/**
* vzalloc - allocate virtually contiguous memory with zero fill
* @size: allocation size
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
* The memory allocated is set to zero.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vzalloc(unsigned long size)
{
return __vmalloc_node_flags(size, NUMA_NO_NODE,
GFP_KERNEL | __GFP_ZERO);
}
EXPORT_SYMBOL(vzalloc);
/**
* vmalloc_user - allocate zeroed virtually contiguous memory for userspace
* @size: allocation size
*
* The resulting memory area is zeroed so it can be mapped to userspace
* without leaking data.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_user(unsigned long size)
{
return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END,
GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_user);
/**
* vmalloc_node - allocate memory on a specific node
* @size: allocation size
* @node: numa node
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_node(unsigned long size, int node)
{
return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL,
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
node, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node);
/**
* vzalloc_node - allocate memory on a specific node with zero fill
* @size: allocation size
* @node: numa node
*
* Allocate enough pages to cover @size from the page level
* allocator and map them into contiguous kernel virtual space.
* The memory allocated is set to zero.
*
* For tight control over page level allocator and protection flags
* use __vmalloc_node() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vzalloc_node(unsigned long size, int node)
{
return __vmalloc_node_flags(size, node,
GFP_KERNEL | __GFP_ZERO);
}
EXPORT_SYMBOL(vzalloc_node);
bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-18 01:28:04 +08:00
/**
* vmalloc_user_node_flags - allocate memory for userspace on a specific node
* @size: allocation size
* @node: numa node
* @flags: flags for the page level allocator
*
* The resulting memory area is zeroed so it can be mapped to userspace
* without leaking data.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags)
{
return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END,
flags | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_user_node_flags);
/**
* vmalloc_exec - allocate virtually contiguous, executable memory
* @size: allocation size
*
* Kernel-internal function to allocate enough pages to cover @size
* the page level allocator and map them into contiguous and
* executable kernel virtual space.
*
* For tight control over page level allocator and protection flags
* use __vmalloc() instead.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_exec(unsigned long size)
{
mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen <dave.hansen@intel.com> Suggested-by: Andy Lutomirski <luto@kernel.org> Suggested-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <akpm@linux-foundation.org> Cc: <ard.biesheuvel@linaro.org> Cc: <deneen.t.dock@intel.com> Cc: <kernel-hardening@lists.openwall.com> Cc: <kristen@linux.intel.com> Cc: <linux_dti@icloud.com> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-26 08:11:36 +08:00
return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
NUMA_NO_NODE, __builtin_return_address(0));
}
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
#elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
#define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL)
#else
/*
* 64b systems should always have either DMA or DMA32 zones. For others
* GFP_DMA32 should do the right thing and use the normal zone.
*/
#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL
#endif
/**
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
* @size: allocation size
*
* Allocate enough 32bit PA addressable pages to cover @size from the
* page level allocator and map them into contiguous kernel virtual space.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_32(unsigned long size)
{
return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
NUMA_NO_NODE, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32);
/**
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
* @size: allocation size
*
* The resulting memory area is 32bit addressable and zeroed so it can be
* mapped to userspace without leaking data.
*
* Return: pointer to the allocated memory or %NULL on error
*/
void *vmalloc_32_user(unsigned long size)
{
return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END,
GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_user);
/*
* small helper routine , copy contents to buf from addr.
* If the page is not present, fill zero.
*/
static int aligned_vread(char *buf, char *addr, unsigned long count)
{
struct page *p;
int copied = 0;
while (count) {
unsigned long offset, length;
offset = offset_in_page(addr);
length = PAGE_SIZE - offset;
if (length > count)
length = count;
p = vmalloc_to_page(addr);
/*
* To do safe access to this _mapped_ area, we need
* lock. But adding lock here means that we need to add
* overhead of vmalloc()/vfree() calles for this _debug_
* interface, rarely used. Instead of that, we'll use
* kmap() and get small overhead in this access function.
*/
if (p) {
/*
* we can expect USER0 is not used (see vread/vwrite's
* function description)
*/
void *map = kmap_atomic(p);
memcpy(buf, map + offset, length);
kunmap_atomic(map);
} else
memset(buf, 0, length);
addr += length;
buf += length;
copied += length;
count -= length;
}
return copied;
}
static int aligned_vwrite(char *buf, char *addr, unsigned long count)
{
struct page *p;
int copied = 0;
while (count) {
unsigned long offset, length;
offset = offset_in_page(addr);
length = PAGE_SIZE - offset;
if (length > count)
length = count;
p = vmalloc_to_page(addr);
/*
* To do safe access to this _mapped_ area, we need
* lock. But adding lock here means that we need to add
* overhead of vmalloc()/vfree() calles for this _debug_
* interface, rarely used. Instead of that, we'll use
* kmap() and get small overhead in this access function.
*/
if (p) {
/*
* we can expect USER0 is not used (see vread/vwrite's
* function description)
*/
void *map = kmap_atomic(p);
memcpy(map + offset, buf, length);
kunmap_atomic(map);
}
addr += length;
buf += length;
copied += length;
count -= length;
}
return copied;
}
/**
* vread() - read vmalloc area in a safe way.
* @buf: buffer for reading data
* @addr: vm address.
* @count: number of bytes to be read.
*
* This function checks that addr is a valid vmalloc'ed area, and
* copy data from that area to a given buffer. If the given memory range
* of [addr...addr+count) includes some valid address, data is copied to
* proper area of @buf. If there are memory holes, they'll be zero-filled.
* IOREMAP area is treated as memory hole and no copy is done.
*
* If [addr...addr+count) doesn't includes any intersects with alive
* vm_struct area, returns 0. @buf should be kernel's buffer.
*
* Note: In usual ops, vread() is never necessary because the caller
* should know vmalloc() area is valid and can use memcpy().
* This is for routines which have to access vmalloc area without
* any information, as /dev/kmem.
*
* Return: number of bytes for which addr and buf should be increased
* (same number as @count) or %0 if [addr...addr+count) doesn't
* include any intersection with valid vmalloc area
*/
long vread(char *buf, char *addr, unsigned long count)
{
struct vmap_area *va;
struct vm_struct *vm;
char *vaddr, *buf_start = buf;
unsigned long buflen = count;
unsigned long n;
/* Don't allow overflow */
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
spin_lock(&vmap_area_lock);
list_for_each_entry(va, &vmap_area_list, list) {
if (!count)
break;
if (!va->vm)
continue;
vm = va->vm;
vaddr = (char *) vm->addr;
if (addr >= vaddr + get_vm_area_size(vm))
continue;
while (addr < vaddr) {
if (count == 0)
goto finished;
*buf = '\0';
buf++;
addr++;
count--;
}
n = vaddr + get_vm_area_size(vm) - addr;
if (n > count)
n = count;
if (!(vm->flags & VM_IOREMAP))
aligned_vread(buf, addr, n);
else /* IOREMAP area is treated as memory hole */
memset(buf, 0, n);
buf += n;
addr += n;
count -= n;
}
finished:
spin_unlock(&vmap_area_lock);
if (buf == buf_start)
return 0;
/* zero-fill memory holes */
if (buf != buf_start + buflen)
memset(buf, 0, buflen - (buf - buf_start));
return buflen;
}
/**
* vwrite() - write vmalloc area in a safe way.
* @buf: buffer for source data
* @addr: vm address.
* @count: number of bytes to be read.
*
* This function checks that addr is a valid vmalloc'ed area, and
* copy data from a buffer to the given addr. If specified range of
* [addr...addr+count) includes some valid address, data is copied from
* proper area of @buf. If there are memory holes, no copy to hole.
* IOREMAP area is treated as memory hole and no copy is done.
*
* If [addr...addr+count) doesn't includes any intersects with alive
* vm_struct area, returns 0. @buf should be kernel's buffer.
*
* Note: In usual ops, vwrite() is never necessary because the caller
* should know vmalloc() area is valid and can use memcpy().
* This is for routines which have to access vmalloc area without
* any information, as /dev/kmem.
*
* Return: number of bytes for which addr and buf should be
* increased (same number as @count) or %0 if [addr...addr+count)
* doesn't include any intersection with valid vmalloc area
*/
long vwrite(char *buf, char *addr, unsigned long count)
{
struct vmap_area *va;
struct vm_struct *vm;
char *vaddr;
unsigned long n, buflen;
int copied = 0;
/* Don't allow overflow */
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
buflen = count;
spin_lock(&vmap_area_lock);
list_for_each_entry(va, &vmap_area_list, list) {
if (!count)
break;
if (!va->vm)
continue;
vm = va->vm;
vaddr = (char *) vm->addr;
if (addr >= vaddr + get_vm_area_size(vm))
continue;
while (addr < vaddr) {
if (count == 0)
goto finished;
buf++;
addr++;
count--;
}
n = vaddr + get_vm_area_size(vm) - addr;
if (n > count)
n = count;
if (!(vm->flags & VM_IOREMAP)) {
aligned_vwrite(buf, addr, n);
copied++;
}
buf += n;
addr += n;
count -= n;
}
finished:
spin_unlock(&vmap_area_lock);
if (!copied)
return 0;
return buflen;
}
/**
* remap_vmalloc_range_partial - map vmalloc pages to userspace
* @vma: vma to cover
* @uaddr: target user address to start at
* @kaddr: virtual address of vmalloc kernel memory
* @size: size of map area
*
* Returns: 0 for success, -Exxx on failure
*
* This function checks that @kaddr is a valid vmalloc'ed area,
* and that it is big enough to cover the range starting at
* @uaddr in @vma. Will return failure if that criteria isn't
* met.
*
* Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
void *kaddr, unsigned long size)
{
struct vm_struct *area;
size = PAGE_ALIGN(size);
if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr))
return -EINVAL;
area = find_vm_area(kaddr);
if (!area)
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return -EINVAL;
if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return -EINVAL;
mm/vmalloc: fix size check for remap_vmalloc_range_partial() When VM_NO_GUARD is not set area->size includes adjacent guard page, thus for correct size checking get_vm_area_size() should be used, but not area->size. This fixes possible kernel oops when userspace tries to mmap an area on 1 page bigger than was allocated by vmalloc_user() call: the size check inside remap_vmalloc_range_partial() accounts non-existing guard page also, so check successfully passes but vmalloc_to_page() returns NULL (guard page does not physically exist). The following code pattern example should trigger an oops: static int oops_mmap(struct file *file, struct vm_area_struct *vma) { void *mem; mem = vmalloc_user(4096); BUG_ON(!mem); /* Do not care about mem leak */ return remap_vmalloc_range(vma, mem, 0); } And userspace simply mmaps size + PAGE_SIZE: mmap(NULL, 8192, PROT_WRITE|PROT_READ, MAP_PRIVATE, fd, 0); Possible candidates for oops which do not have any explicit size checks: *** drivers/media/usb/stkwebcam/stk-webcam.c: v4l_stk_mmap[789] ret = remap_vmalloc_range(vma, sbuf->buffer, 0); Or the following one: *** drivers/video/fbdev/core/fbmem.c static int fb_mmap(struct file *file, struct vm_area_struct * vma) ... res = fb->fb_mmap(info, vma); Where fb_mmap callback calls remap_vmalloc_range() directly without any explicit checks: *** drivers/video/fbdev/vfb.c static int vfb_mmap(struct fb_info *info, struct vm_area_struct *vma) { return remap_vmalloc_range(vma, (void *)info->fix.smem_start, vma->vm_pgoff); } Link: http://lkml.kernel.org/r/20190103145954.16942-2-rpenyaev@suse.de Signed-off-by: Roman Penyaev <rpenyaev@suse.de> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Joe Perches <joe@perches.com> Cc: "Luis R. Rodriguez" <mcgrof@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:43:20 +08:00
if (kaddr + size > area->addr + get_vm_area_size(area))
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return -EINVAL;
do {
struct page *page = vmalloc_to_page(kaddr);
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
int ret;
ret = vm_insert_page(vma, uaddr, page);
if (ret)
return ret;
uaddr += PAGE_SIZE;
kaddr += PAGE_SIZE;
size -= PAGE_SIZE;
} while (size > 0);
mm: kill vma flag VM_RESERVED and mm->reserved_vm counter A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA, currently it lost original meaning but still has some effects: | effect | alternative flags -+------------------------+--------------------------------------------- 1| account as reserved_vm | VM_IO 2| skip in core dump | VM_IO, VM_DONTDUMP 3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP 4| do not mlock | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP This patch removes reserved_vm counter from mm_struct. Seems like nobody cares about it, it does not exported into userspace directly, it only reduces total_vm showed in proc. Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP. remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP. remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP. [akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup] Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Carsten Otte <cotte@de.ibm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Eric Paris <eparis@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morris <james.l.morris@oracle.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Kentaro Takeda <takedakn@nttdata.co.jp> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Venkatesh Pallipadi <venki@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:29:02 +08:00
vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
return 0;
}
EXPORT_SYMBOL(remap_vmalloc_range_partial);
/**
* remap_vmalloc_range - map vmalloc pages to userspace
* @vma: vma to cover (map full range of vma)
* @addr: vmalloc memory
* @pgoff: number of pages into addr before first page to map
*
* Returns: 0 for success, -Exxx on failure
*
* This function checks that addr is a valid vmalloc'ed area, and
* that it is big enough to cover the vma. Will return failure if
* that criteria isn't met.
*
* Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff)
{
return remap_vmalloc_range_partial(vma, vma->vm_start,
addr + (pgoff << PAGE_SHIFT),
vma->vm_end - vma->vm_start);
}
EXPORT_SYMBOL(remap_vmalloc_range);
/*
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
* have one.
*
* The purpose of this function is to make sure the vmalloc area
* mappings are identical in all page-tables in the system.
*/
void __weak vmalloc_sync_all(void)
{
}
static int f(pte_t *pte, unsigned long addr, void *data)
{
pte_t ***p = data;
if (p) {
*(*p) = pte;
(*p)++;
}
return 0;
}
/**
* alloc_vm_area - allocate a range of kernel address space
* @size: size of the area
* @ptes: returns the PTEs for the address space
*
* Returns: NULL on failure, vm_struct on success
*
* This function reserves a range of kernel address space, and
* allocates pagetables to map that range. No actual mappings
* are created.
*
* If @ptes is non-NULL, pointers to the PTEs (in init_mm)
* allocated for the VM area are returned.
*/
struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
{
struct vm_struct *area;
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
area = get_vm_area_caller(size, VM_IOREMAP,
__builtin_return_address(0));
if (area == NULL)
return NULL;
/*
* This ensures that page tables are constructed for this region
* of kernel virtual address space and mapped into init_mm.
*/
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
size, f, ptes ? &ptes : NULL)) {
free_vm_area(area);
return NULL;
}
return area;
}
EXPORT_SYMBOL_GPL(alloc_vm_area);
void free_vm_area(struct vm_struct *area)
{
struct vm_struct *ret;
ret = remove_vm_area(area->addr);
BUG_ON(ret != area);
kfree(area);
}
EXPORT_SYMBOL_GPL(free_vm_area);
2008-04-28 17:12:40 +08:00
#ifdef CONFIG_SMP
static struct vmap_area *node_to_va(struct rb_node *n)
{
return rb_entry_safe(n, struct vmap_area, rb_node);
}
/**
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* pvm_find_va_enclose_addr - find the vmap_area @addr belongs to
* @addr: target address
*
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* Returns: vmap_area if it is found. If there is no such area
* the first highest(reverse order) vmap_area is returned
* i.e. va->va_start < addr && va->va_end < addr or NULL
* if there are no any areas before @addr.
*/
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static struct vmap_area *
pvm_find_va_enclose_addr(unsigned long addr)
{
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
struct vmap_area *va, *tmp;
struct rb_node *n;
n = free_vmap_area_root.rb_node;
va = NULL;
while (n) {
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
tmp = rb_entry(n, struct vmap_area, rb_node);
if (tmp->va_start <= addr) {
va = tmp;
if (tmp->va_end >= addr)
break;
n = n->rb_right;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
} else {
n = n->rb_left;
}
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
return va;
}
/**
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* pvm_determine_end_from_reverse - find the highest aligned address
* of free block below VMALLOC_END
* @va:
* in - the VA we start the search(reverse order);
* out - the VA with the highest aligned end address.
*
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* Returns: determined end address within vmap_area
*/
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
static unsigned long
pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align)
{
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
unsigned long addr;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (likely(*va)) {
list_for_each_entry_from_reverse((*va),
&free_vmap_area_list, list) {
addr = min((*va)->va_end & ~(align - 1), vmalloc_end);
if ((*va)->va_start < addr)
return addr;
}
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
return 0;
}
/**
* pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator
* @offsets: array containing offset of each area
* @sizes: array containing size of each area
* @nr_vms: the number of areas to allocate
* @align: alignment, all entries in @offsets and @sizes must be aligned to this
*
* Returns: kmalloc'd vm_struct pointer array pointing to allocated
* vm_structs on success, %NULL on failure
*
* Percpu allocator wants to use congruent vm areas so that it can
* maintain the offsets among percpu areas. This function allocates
* congruent vmalloc areas for it with GFP_KERNEL. These areas tend to
* be scattered pretty far, distance between two areas easily going up
* to gigabytes. To avoid interacting with regular vmallocs, these
* areas are allocated from top.
*
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* Despite its complicated look, this allocator is rather simple. It
* does everything top-down and scans free blocks from the end looking
* for matching base. While scanning, if any of the areas do not fit the
* base address is pulled down to fit the area. Scanning is repeated till
* all the areas fit and then all necessary data structures are inserted
* and the result is returned.
*/
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align)
{
const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
struct vmap_area **vas, *va;
struct vm_struct **vms;
int area, area2, last_area, term_area;
unsigned long base, start, size, end, last_end, orig_start, orig_end;
bool purged = false;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
enum fit_type type;
/* verify parameters and allocate data structures */
BUG_ON(offset_in_page(align) || !is_power_of_2(align));
for (last_area = 0, area = 0; area < nr_vms; area++) {
start = offsets[area];
end = start + sizes[area];
/* is everything aligned properly? */
BUG_ON(!IS_ALIGNED(offsets[area], align));
BUG_ON(!IS_ALIGNED(sizes[area], align));
/* detect the area with the highest address */
if (start > offsets[last_area])
last_area = area;
for (area2 = area + 1; area2 < nr_vms; area2++) {
unsigned long start2 = offsets[area2];
unsigned long end2 = start2 + sizes[area2];
BUG_ON(start2 < end && start < end2);
}
}
last_end = offsets[last_area] + sizes[last_area];
if (vmalloc_end - vmalloc_start < last_end) {
WARN_ON(true);
return NULL;
}
vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL);
vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL);
if (!vas || !vms)
goto err_free2;
for (area = 0; area < nr_vms; area++) {
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL);
vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL);
if (!vas[area] || !vms[area])
goto err_free;
}
retry:
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_lock(&free_vmap_area_lock);
/* start scanning - we scan from the top, begin with the last area */
area = term_area = last_area;
start = offsets[area];
end = start + sizes[area];
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
va = pvm_find_va_enclose_addr(vmalloc_end);
base = pvm_determine_end_from_reverse(&va, align) - end;
while (true) {
/*
* base might have underflowed, add last_end before
* comparing.
*/
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (base + last_end < vmalloc_start + last_end)
goto overflow;
/*
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* Fitting base has not been found.
*/
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (va == NULL)
goto overflow;
mm/vmalloc.c: fix percpu free VM area search criteria Recent changes to the vmalloc code by commit 68ad4a330433 ("mm/vmalloc.c: keep track of free blocks for vmap allocation") can cause spurious percpu allocation failures. These, in turn, can result in panic()s in the slub code. One such possible panic was reported by Dave Hansen in following link https://lkml.org/lkml/2019/6/19/939. Another related panic observed is, RIP: 0033:0x7f46f7441b9b Call Trace: dump_stack+0x61/0x80 pcpu_alloc.cold.30+0x22/0x4f mem_cgroup_css_alloc+0x110/0x650 cgroup_apply_control_enable+0x133/0x330 cgroup_mkdir+0x41b/0x500 kernfs_iop_mkdir+0x5a/0x90 vfs_mkdir+0x102/0x1b0 do_mkdirat+0x7d/0xf0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 VMALLOC memory manager divides the entire VMALLOC space (VMALLOC_START to VMALLOC_END) into multiple VM areas (struct vm_areas), and it mainly uses two lists (vmap_area_list & free_vmap_area_list) to track the used and free VM areas in VMALLOC space. And pcpu_get_vm_areas(offsets[], sizes[], nr_vms, align) function is used for allocating congruent VM areas for percpu memory allocator. In order to not conflict with VMALLOC users, pcpu_get_vm_areas allocates VM areas near the end of the VMALLOC space. So the search for free vm_area for the given requirement starts near VMALLOC_END and moves upwards towards VMALLOC_START. Prior to commit 68ad4a330433, the search for free vm_area in pcpu_get_vm_areas() involves following two main steps. Step 1: Find a aligned "base" adress near VMALLOC_END. va = free vm area near VMALLOC_END Step 2: Loop through number of requested vm_areas and check, Step 2.1: if (base < VMALLOC_START) 1. fail with error Step 2.2: // end is offsets[area] + sizes[area] if (base + end > va->vm_end) 1. Move the base downwards and repeat Step 2 Step 2.3: if (base + start < va->vm_start) 1. Move to previous free vm_area node, find aligned base address and repeat Step 2 But Commit 68ad4a330433 removed Step 2.2 and modified Step 2.3 as below: Step 2.3: if (base + start < va->vm_start || base + end > va->vm_end) 1. Move to previous free vm_area node, find aligned base address and repeat Step 2 Above change is the root cause of spurious percpu memory allocation failures. For example, consider a case where a relatively large vm_area (~ 30 TB) was ignored in free vm_area search because it did not pass the base + end < vm->vm_end boundary check. Ignoring such large free vm_area's would lead to not finding free vm_area within boundary of VMALLOC_start to VMALLOC_END which in turn leads to allocation failures. So modify the search algorithm to include Step 2.2. Link: http://lkml.kernel.org/r/20190729232139.91131-1-sathyanarayanan.kuppuswamy@linux.intel.com Fixes: 68ad4a330433 ("mm/vmalloc.c: keep track of free blocks for vmap allocation") Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com> Reported-by: Dave Hansen <dave.hansen@intel.com> Acked-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: sathyanarayanan kuppuswamy <sathyanarayanan.kuppuswamy@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-08-14 06:37:31 +08:00
/*
* If required width exeeds current VA block, move
* base downwards and then recheck.
*/
if (base + end > va->va_end) {
base = pvm_determine_end_from_reverse(&va, align) - end;
term_area = area;
continue;
}
/*
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
* If this VA does not fit, move base downwards and recheck.
*/
mm/vmalloc.c: fix percpu free VM area search criteria Recent changes to the vmalloc code by commit 68ad4a330433 ("mm/vmalloc.c: keep track of free blocks for vmap allocation") can cause spurious percpu allocation failures. These, in turn, can result in panic()s in the slub code. One such possible panic was reported by Dave Hansen in following link https://lkml.org/lkml/2019/6/19/939. Another related panic observed is, RIP: 0033:0x7f46f7441b9b Call Trace: dump_stack+0x61/0x80 pcpu_alloc.cold.30+0x22/0x4f mem_cgroup_css_alloc+0x110/0x650 cgroup_apply_control_enable+0x133/0x330 cgroup_mkdir+0x41b/0x500 kernfs_iop_mkdir+0x5a/0x90 vfs_mkdir+0x102/0x1b0 do_mkdirat+0x7d/0xf0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 VMALLOC memory manager divides the entire VMALLOC space (VMALLOC_START to VMALLOC_END) into multiple VM areas (struct vm_areas), and it mainly uses two lists (vmap_area_list & free_vmap_area_list) to track the used and free VM areas in VMALLOC space. And pcpu_get_vm_areas(offsets[], sizes[], nr_vms, align) function is used for allocating congruent VM areas for percpu memory allocator. In order to not conflict with VMALLOC users, pcpu_get_vm_areas allocates VM areas near the end of the VMALLOC space. So the search for free vm_area for the given requirement starts near VMALLOC_END and moves upwards towards VMALLOC_START. Prior to commit 68ad4a330433, the search for free vm_area in pcpu_get_vm_areas() involves following two main steps. Step 1: Find a aligned "base" adress near VMALLOC_END. va = free vm area near VMALLOC_END Step 2: Loop through number of requested vm_areas and check, Step 2.1: if (base < VMALLOC_START) 1. fail with error Step 2.2: // end is offsets[area] + sizes[area] if (base + end > va->vm_end) 1. Move the base downwards and repeat Step 2 Step 2.3: if (base + start < va->vm_start) 1. Move to previous free vm_area node, find aligned base address and repeat Step 2 But Commit 68ad4a330433 removed Step 2.2 and modified Step 2.3 as below: Step 2.3: if (base + start < va->vm_start || base + end > va->vm_end) 1. Move to previous free vm_area node, find aligned base address and repeat Step 2 Above change is the root cause of spurious percpu memory allocation failures. For example, consider a case where a relatively large vm_area (~ 30 TB) was ignored in free vm_area search because it did not pass the base + end < vm->vm_end boundary check. Ignoring such large free vm_area's would lead to not finding free vm_area within boundary of VMALLOC_start to VMALLOC_END which in turn leads to allocation failures. So modify the search algorithm to include Step 2.2. Link: http://lkml.kernel.org/r/20190729232139.91131-1-sathyanarayanan.kuppuswamy@linux.intel.com Fixes: 68ad4a330433 ("mm/vmalloc.c: keep track of free blocks for vmap allocation") Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com> Reported-by: Dave Hansen <dave.hansen@intel.com> Acked-by: Dennis Zhou <dennis@kernel.org> Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: sathyanarayanan kuppuswamy <sathyanarayanan.kuppuswamy@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-08-14 06:37:31 +08:00
if (base + start < va->va_start) {
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
va = node_to_va(rb_prev(&va->rb_node));
base = pvm_determine_end_from_reverse(&va, align) - end;
term_area = area;
continue;
}
/*
* This area fits, move on to the previous one. If
* the previous one is the terminal one, we're done.
*/
area = (area + nr_vms - 1) % nr_vms;
if (area == term_area)
break;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
start = offsets[area];
end = start + sizes[area];
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
va = pvm_find_va_enclose_addr(base + end);
}
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
/* we've found a fitting base, insert all va's */
for (area = 0; area < nr_vms; area++) {
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
int ret;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
start = base + offsets[area];
size = sizes[area];
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
va = pvm_find_va_enclose_addr(start);
if (WARN_ON_ONCE(va == NULL))
/* It is a BUG(), but trigger recovery instead. */
goto recovery;
type = classify_va_fit_type(va, start, size);
if (WARN_ON_ONCE(type == NOTHING_FIT))
/* It is a BUG(), but trigger recovery instead. */
goto recovery;
ret = adjust_va_to_fit_type(va, start, size, type);
if (unlikely(ret))
goto recovery;
/* Allocated area. */
va = vas[area];
va->va_start = start;
va->va_end = start + size;
}
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_unlock(&free_vmap_area_lock);
/* populate the kasan shadow space */
for (area = 0; area < nr_vms; area++) {
if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
goto err_free_shadow;
kasan_unpoison_vmalloc((void *)vas[area]->va_start,
sizes[area]);
}
/* insert all vm's */
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_lock(&vmap_area_lock);
for (area = 0; area < nr_vms; area++) {
insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list);
setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC,
pcpu_get_vm_areas);
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
}
spin_unlock(&vmap_area_lock);
kfree(vas);
return vms;
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
recovery:
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
/*
* Remove previously allocated areas. There is no
* need in removing these areas from the busy tree,
* because they are inserted only on the final step
* and when pcpu_get_vm_areas() is success.
*/
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
while (area--) {
orig_start = vas[area]->va_start;
orig_end = vas[area]->va_end;
va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
&free_vmap_area_list);
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
vas[area] = NULL;
}
overflow:
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
spin_unlock(&free_vmap_area_lock);
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (!purged) {
purge_vmap_area_lazy();
purged = true;
/* Before "retry", check if we recover. */
for (area = 0; area < nr_vms; area++) {
if (vas[area])
continue;
vas[area] = kmem_cache_zalloc(
vmap_area_cachep, GFP_KERNEL);
if (!vas[area])
goto err_free;
}
goto retry;
}
err_free:
for (area = 0; area < nr_vms; area++) {
mm/vmalloc.c: keep track of free blocks for vmap allocation Patch series "improve vmap allocation", v3. Objective --------- Please have a look for the description at: https://lkml.org/lkml/2018/10/19/786 but let me also summarize it a bit here as well. The current implementation has O(N) complexity. Requests with different permissive parameters can lead to long allocation time. When i say "long" i mean milliseconds. Description ----------- This approach organizes the KVA memory layout into free areas of the 1-ULONG_MAX range, i.e. an allocation is done over free areas lookups, instead of finding a hole between two busy blocks. It allows to have lower number of objects which represent the free space, therefore to have less fragmented memory allocator. Because free blocks are always as large as possible. It uses the augment tree where all free areas are sorted in ascending order of va->va_start address in pair with linked list that provides O(1) access to prev/next elements. Since the tree is augment, we also maintain the "subtree_max_size" of VA that reflects a maximum available free block in its left or right sub-tree. Knowing that, we can easily traversal toward the lowest (left most path) free area. Allocation: ~O(log(N)) complexity. It is sequential allocation method therefore tends to maximize locality. The search is done until a first suitable block is large enough to encompass the requested parameters. Bigger areas are split. I copy paste here the description of how the area is split, since i described it in https://lkml.org/lkml/2018/10/19/786 <snip> A free block can be split by three different ways. Their names are FL_FIT_TYPE, LE_FIT_TYPE/RE_FIT_TYPE and NE_FIT_TYPE, i.e. they correspond to how requested size and alignment fit to a free block. FL_FIT_TYPE - in this case a free block is just removed from the free list/tree because it fully fits. Comparing with current design there is an extra work with rb-tree updating. LE_FIT_TYPE/RE_FIT_TYPE - left/right edges fit. In this case what we do is just cutting a free block. It is as fast as a current design. Most of the vmalloc allocations just end up with this case, because the edge is always aligned to 1. NE_FIT_TYPE - Is much less common case. Basically it happens when requested size and alignment does not fit left nor right edges, i.e. it is between them. In this case during splitting we have to build a remaining left free area and place it back to the free list/tree. Comparing with current design there are two extra steps. First one is we have to allocate a new vmap_area structure. Second one we have to insert that remaining free block to the address sorted list/tree. In order to optimize a first case there is a cache with free_vmap objects. Instead of allocating from slab we just take an object from the cache and reuse it. Second one is pretty optimized. Since we know a start point in the tree we do not do a search from the top. Instead a traversal begins from a rb-tree node we split. <snip> De-allocation. ~O(log(N)) complexity. An area is not inserted straight away to the tree/list, instead we identify the spot first, checking if it can be merged around neighbors. The list provides O(1) access to prev/next, so it is pretty fast to check it. Summarizing. If merged then large coalesced areas are created, if not the area is just linked making more fragments. There is one more thing that i should mention here. After modification of VA node, its subtree_max_size is updated if it was/is the biggest area in its left or right sub-tree. Apart of that it can also be populated back to upper levels to fix the tree. For more details please have a look at the __augment_tree_propagate_from() function and the description. Tests and stressing ------------------- I use the "test_vmalloc.sh" test driver available under "tools/testing/selftests/vm/" since 5.1-rc1 kernel. Just trigger "sudo ./test_vmalloc.sh" to find out how to deal with it. Tested on different platforms including x86_64/i686/ARM64/x86_64_NUMA. Regarding last one, i do not have any physical access to NUMA system, therefore i emulated it. The time of stressing is days. If you run the test driver in "stress mode", you also need the patch that is in Andrew's tree but not in Linux 5.1-rc1. So, please apply it: http://git.cmpxchg.org/cgit.cgi/linux-mmotm.git/commit/?id=e0cf7749bade6da318e98e934a24d8b62fab512c After massive testing, i have not identified any problems like memory leaks, crashes or kernel panics. I find it stable, but more testing would be good. Performance analysis -------------------- I have used two systems to test. One is i5-3320M CPU @ 2.60GHz and another is HiKey960(arm64) board. i5-3320M runs on 4.20 kernel, whereas Hikey960 uses 4.15 kernel. I have both system which could run on 5.1-rc1 as well, but the results have not been ready by time i an writing this. Currently it consist of 8 tests. There are three of them which correspond to different types of splitting(to compare with default). We have 3 ones(see above). Another 5 do allocations in different conditions. a) sudo ./test_vmalloc.sh performance When the test driver is run in "performance" mode, it runs all available tests pinned to first online CPU with sequential execution test order. We do it in order to get stable and repeatable results. Take a look at time difference in "long_busy_list_alloc_test". It is not surprising because the worst case is O(N). # i5-3320M How many cycles all tests took: CPU0=646919905370(default) cycles vs CPU0=193290498550(patched) cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_performance_patched.txt # Hikey960 8x CPUs How many cycles all tests took: CPU0=3478683207 cycles vs CPU0=463767978 cycles # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/HiKey960_performance_patched.txt b) time sudo ./test_vmalloc.sh test_repeat_count=1 With this configuration, all tests are run on all available online CPUs. Before running each CPU shuffles its tests execution order. It gives random allocation behaviour. So it is rough comparison, but it puts in the picture for sure. # i5-3320M <default> vs <patched> real 101m22.813s real 0m56.805s user 0m0.011s user 0m0.015s sys 0m5.076s sys 0m0.023s # See detailed table with results here: ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_default.txt ftp://vps418301.ovh.net/incoming/vmap_test_results_v2/i5-3320M_test_repeat_count_1_patched.txt # Hikey960 8x CPUs <default> vs <patched> real unknown real 4m25.214s user unknown user 0m0.011s sys unknown sys 0m0.670s I did not manage to complete this test on "default Hikey960" kernel version. After 24 hours it was still running, therefore i had to cancel it. That is why real/user/sys are "unknown". This patch (of 3): Currently an allocation of the new vmap area is done over busy list iteration(complexity O(n)) until a suitable hole is found between two busy areas. Therefore each new allocation causes the list being grown. Due to over fragmented list and different permissive parameters an allocation can take a long time. For example on embedded devices it is milliseconds. This patch organizes the KVA memory layout into free areas of the 1-ULONG_MAX range. It uses an augment red-black tree that keeps blocks sorted by their offsets in pair with linked list keeping the free space in order of increasing addresses. Nodes are augmented with the size of the maximum available free block in its left or right sub-tree. Thus, that allows to take a decision and traversal toward the block that will fit and will have the lowest start address, i.e. it is sequential allocation. Allocation: to allocate a new block a search is done over the tree until a suitable lowest(left most) block is large enough to encompass: the requested size, alignment and vstart point. If the block is bigger than requested size - it is split. De-allocation: when a busy vmap area is freed it can either be merged or inserted to the tree. Red-black tree allows efficiently find a spot whereas a linked list provides a constant-time access to previous and next blocks to check if merging can be done. In case of merging of de-allocated memory chunk a large coalesced area is created. Complexity: ~O(log(N)) [urezki@gmail.com: v3] Link: http://lkml.kernel.org/r/20190402162531.10888-2-urezki@gmail.com [urezki@gmail.com: v4] Link: http://lkml.kernel.org/r/20190406183508.25273-2-urezki@gmail.com Link: http://lkml.kernel.org/r/20190321190327.11813-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Reviewed-by: Roman Gushchin <guro@fb.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Thomas Garnier <thgarnie@google.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Joel Fernandes <joelaf@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-18 05:31:31 +08:00
if (vas[area])
kmem_cache_free(vmap_area_cachep, vas[area]);
kfree(vms[area]);
}
err_free2:
kfree(vas);
kfree(vms);
return NULL;
err_free_shadow:
spin_lock(&free_vmap_area_lock);
/*
* We release all the vmalloc shadows, even the ones for regions that
* hadn't been successfully added. This relies on kasan_release_vmalloc
* being able to tolerate this case.
*/
for (area = 0; area < nr_vms; area++) {
orig_start = vas[area]->va_start;
orig_end = vas[area]->va_end;
va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
&free_vmap_area_list);
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end);
vas[area] = NULL;
kfree(vms[area]);
}
spin_unlock(&free_vmap_area_lock);
kfree(vas);
kfree(vms);
return NULL;
}
/**
* pcpu_free_vm_areas - free vmalloc areas for percpu allocator
* @vms: vm_struct pointer array returned by pcpu_get_vm_areas()
* @nr_vms: the number of allocated areas
*
* Free vm_structs and the array allocated by pcpu_get_vm_areas().
*/
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
int i;
for (i = 0; i < nr_vms; i++)
free_vm_area(vms[i]);
kfree(vms);
}
#endif /* CONFIG_SMP */
2008-04-28 17:12:40 +08:00
#ifdef CONFIG_PROC_FS
static void *s_start(struct seq_file *m, loff_t *pos)
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
__acquires(&vmap_purge_lock)
2013-04-30 06:07:35 +08:00
__acquires(&vmap_area_lock)
2008-04-28 17:12:40 +08:00
{
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
mutex_lock(&vmap_purge_lock);
2013-04-30 06:07:35 +08:00
spin_lock(&vmap_area_lock);
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
return seq_list_start(&vmap_area_list, *pos);
2008-04-28 17:12:40 +08:00
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
return seq_list_next(p, &vmap_area_list, pos);
2008-04-28 17:12:40 +08:00
}
static void s_stop(struct seq_file *m, void *p)
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
__releases(&vmap_purge_lock)
2013-04-30 06:07:35 +08:00
__releases(&vmap_area_lock)
2008-04-28 17:12:40 +08:00
{
mm/vmalloc: rework vmap_area_lock With the new allocation approach introduced in the 5.2 kernel, it becomes possible to get rid of one global spinlock. By doing that we can further improve the KVA from the performance point of view. Basically we can have two independent locks, one for allocation part and another one for deallocation, because of two different entities: "free data structures" and "busy data structures". As a result, allocation/deallocation operations can still interfere between each other in case of running simultaneously on different CPUs, it means there is still dependency, but with two locks it becomes lower. Summarizing: - it reduces the high lock contention - it allows to perform operations on "free" and "busy" trees in parallel on different CPUs. Please note it does not solve scalability issue. Test results: In order to evaluate this patch, we can run "vmalloc test driver" to see how many CPU cycles it takes to complete all test cases running sequentially. All online CPUs run it so it will cause a high lock contention. HiKey 960, ARM64, 8xCPUs, big.LITTLE: <snip> sudo ./test_vmalloc.sh sequential_test_order=1 <snip> <default> [ 390.950557] All test took CPU0=457126382 cycles [ 391.046690] All test took CPU1=454763452 cycles [ 391.128586] All test took CPU2=454539334 cycles [ 391.222669] All test took CPU3=455649517 cycles [ 391.313946] All test took CPU4=388272196 cycles [ 391.410425] All test took CPU5=384036264 cycles [ 391.492219] All test took CPU6=387432964 cycles [ 391.578433] All test took CPU7=387201996 cycles <default> <patched> [ 304.721224] All test took CPU0=391521310 cycles [ 304.821219] All test took CPU1=393533002 cycles [ 304.917120] All test took CPU2=392243032 cycles [ 305.008986] All test took CPU3=392353853 cycles [ 305.108944] All test took CPU4=297630721 cycles [ 305.196406] All test took CPU5=297548736 cycles [ 305.288602] All test took CPU6=297092392 cycles [ 305.381088] All test took CPU7=297293597 cycles <patched> ~14%-23% patched variant is better. Link: http://lkml.kernel.org/r/20191022155800.20468-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 09:54:47 +08:00
mutex_unlock(&vmap_purge_lock);
2013-04-30 06:07:35 +08:00
spin_unlock(&vmap_area_lock);
2008-04-28 17:12:40 +08:00
}
vmallocinfo: add NUMA information Christoph recently added /proc/vmallocinfo file to get information about vmalloc allocations. This patch adds NUMA specific information, giving number of pages allocated on each memory node. This should help to check that vmalloc() is able to respect NUMA policies. Example of output on a four nodes machine (one cpu per node) 1) network hash tables are evenly spreaded on four nodes (OK) (Same point for inodes and dentries hash tables) 2) iptables tables (x_tables) are correctly allocated on each cpu node (OK). 3) sys_swapon() allocates its memory from one node only. 4) each loaded module is using memory on one node. Sysadmins could tune their setup to change points 3) and 4) if necessary. grep "pages=" /proc/vmallocinfo 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204/0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc2000031a000-0xffffc2000031d000 12288 alloc_large_system_hash+0x204/0x2c0 pages=2 vmalloc N1=1 N2=1 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e/0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 0xffffc2000033e000-0xffffc20000341000 12288 sys_swapon+0x640/0xac0 pages=2 vmalloc N0=2 0xffffc20000341000-0xffffc20000344000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N0=2 0xffffc20000344000-0xffffc20000347000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N1=2 0xffffc20000347000-0xffffc2000034a000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N2=2 0xffffc2000034a000-0xffffc2000034d000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N3=2 0xffffc20004381000-0xffffc20004402000 528384 alloc_large_system_hash+0x204/0x2c0 pages=128 vmalloc N0=32 N1=32 N2=32 N3=32 0xffffc20004402000-0xffffc20004803000 4198400 alloc_large_system_hash+0x204/0x2c0 pages=1024 vmalloc vpages N0=256 N1=256 N2=256 N3=256 0xffffc20004803000-0xffffc20004904000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc20004904000-0xffffc20004bec000 3047424 sys_swapon+0x640/0xac0 pages=743 vmalloc vpages N0=743 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 pages=14 vmalloc N1=14 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 pages=4 vmalloc N0=4 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N0=2 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N1=10 0xffffffffa0022000-0xffffffffa0028000 24576 sys_init_module+0xc27/0x1d00 pages=5 vmalloc N3=5 0xffffffffa0028000-0xffffffffa0050000 163840 sys_init_module+0xc27/0x1d00 pages=39 vmalloc N1=39 0xffffffffa0050000-0xffffffffa0052000 8192 sys_init_module+0xc27/0x1d00 pages=1 vmalloc N1=1 0xffffffffa0052000-0xffffffffa0056000 16384 sys_init_module+0xc27/0x1d00 pages=3 vmalloc N1=3 0xffffffffa0056000-0xffffffffa0081000 176128 sys_init_module+0xc27/0x1d00 pages=42 vmalloc N3=42 0xffffffffa0081000-0xffffffffa00ae000 184320 sys_init_module+0xc27/0x1d00 pages=44 vmalloc N3=44 0xffffffffa00ae000-0xffffffffa00b1000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00b1000-0xffffffffa00b9000 32768 sys_init_module+0xc27/0x1d00 pages=7 vmalloc N0=7 0xffffffffa00b9000-0xffffffffa00c4000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N3=10 0xffffffffa00c6000-0xffffffffa00e0000 106496 sys_init_module+0xc27/0x1d00 pages=25 vmalloc N2=25 0xffffffffa00e0000-0xffffffffa00f1000 69632 sys_init_module+0xc27/0x1d00 pages=16 vmalloc N2=16 0xffffffffa00f1000-0xffffffffa00f4000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00f4000-0xffffffffa00f7000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 [akpm@linux-foundation.org: fix comment] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:38 +08:00
static void show_numa_info(struct seq_file *m, struct vm_struct *v)
{
if (IS_ENABLED(CONFIG_NUMA)) {
vmallocinfo: add NUMA information Christoph recently added /proc/vmallocinfo file to get information about vmalloc allocations. This patch adds NUMA specific information, giving number of pages allocated on each memory node. This should help to check that vmalloc() is able to respect NUMA policies. Example of output on a four nodes machine (one cpu per node) 1) network hash tables are evenly spreaded on four nodes (OK) (Same point for inodes and dentries hash tables) 2) iptables tables (x_tables) are correctly allocated on each cpu node (OK). 3) sys_swapon() allocates its memory from one node only. 4) each loaded module is using memory on one node. Sysadmins could tune their setup to change points 3) and 4) if necessary. grep "pages=" /proc/vmallocinfo 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204/0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc2000031a000-0xffffc2000031d000 12288 alloc_large_system_hash+0x204/0x2c0 pages=2 vmalloc N1=1 N2=1 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e/0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 0xffffc2000033e000-0xffffc20000341000 12288 sys_swapon+0x640/0xac0 pages=2 vmalloc N0=2 0xffffc20000341000-0xffffc20000344000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N0=2 0xffffc20000344000-0xffffc20000347000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N1=2 0xffffc20000347000-0xffffc2000034a000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N2=2 0xffffc2000034a000-0xffffc2000034d000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N3=2 0xffffc20004381000-0xffffc20004402000 528384 alloc_large_system_hash+0x204/0x2c0 pages=128 vmalloc N0=32 N1=32 N2=32 N3=32 0xffffc20004402000-0xffffc20004803000 4198400 alloc_large_system_hash+0x204/0x2c0 pages=1024 vmalloc vpages N0=256 N1=256 N2=256 N3=256 0xffffc20004803000-0xffffc20004904000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc20004904000-0xffffc20004bec000 3047424 sys_swapon+0x640/0xac0 pages=743 vmalloc vpages N0=743 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 pages=14 vmalloc N1=14 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 pages=4 vmalloc N0=4 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N0=2 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N1=10 0xffffffffa0022000-0xffffffffa0028000 24576 sys_init_module+0xc27/0x1d00 pages=5 vmalloc N3=5 0xffffffffa0028000-0xffffffffa0050000 163840 sys_init_module+0xc27/0x1d00 pages=39 vmalloc N1=39 0xffffffffa0050000-0xffffffffa0052000 8192 sys_init_module+0xc27/0x1d00 pages=1 vmalloc N1=1 0xffffffffa0052000-0xffffffffa0056000 16384 sys_init_module+0xc27/0x1d00 pages=3 vmalloc N1=3 0xffffffffa0056000-0xffffffffa0081000 176128 sys_init_module+0xc27/0x1d00 pages=42 vmalloc N3=42 0xffffffffa0081000-0xffffffffa00ae000 184320 sys_init_module+0xc27/0x1d00 pages=44 vmalloc N3=44 0xffffffffa00ae000-0xffffffffa00b1000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00b1000-0xffffffffa00b9000 32768 sys_init_module+0xc27/0x1d00 pages=7 vmalloc N0=7 0xffffffffa00b9000-0xffffffffa00c4000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N3=10 0xffffffffa00c6000-0xffffffffa00e0000 106496 sys_init_module+0xc27/0x1d00 pages=25 vmalloc N2=25 0xffffffffa00e0000-0xffffffffa00f1000 69632 sys_init_module+0xc27/0x1d00 pages=16 vmalloc N2=16 0xffffffffa00f1000-0xffffffffa00f4000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00f4000-0xffffffffa00f7000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 [akpm@linux-foundation.org: fix comment] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:38 +08:00
unsigned int nr, *counters = m->private;
if (!counters)
return;
if (v->flags & VM_UNINITIALIZED)
return;
/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
smp_rmb();
vmallocinfo: add NUMA information Christoph recently added /proc/vmallocinfo file to get information about vmalloc allocations. This patch adds NUMA specific information, giving number of pages allocated on each memory node. This should help to check that vmalloc() is able to respect NUMA policies. Example of output on a four nodes machine (one cpu per node) 1) network hash tables are evenly spreaded on four nodes (OK) (Same point for inodes and dentries hash tables) 2) iptables tables (x_tables) are correctly allocated on each cpu node (OK). 3) sys_swapon() allocates its memory from one node only. 4) each loaded module is using memory on one node. Sysadmins could tune their setup to change points 3) and 4) if necessary. grep "pages=" /proc/vmallocinfo 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204/0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc2000031a000-0xffffc2000031d000 12288 alloc_large_system_hash+0x204/0x2c0 pages=2 vmalloc N1=1 N2=1 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e/0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 0xffffc2000033e000-0xffffc20000341000 12288 sys_swapon+0x640/0xac0 pages=2 vmalloc N0=2 0xffffc20000341000-0xffffc20000344000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N0=2 0xffffc20000344000-0xffffc20000347000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N1=2 0xffffc20000347000-0xffffc2000034a000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N2=2 0xffffc2000034a000-0xffffc2000034d000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N3=2 0xffffc20004381000-0xffffc20004402000 528384 alloc_large_system_hash+0x204/0x2c0 pages=128 vmalloc N0=32 N1=32 N2=32 N3=32 0xffffc20004402000-0xffffc20004803000 4198400 alloc_large_system_hash+0x204/0x2c0 pages=1024 vmalloc vpages N0=256 N1=256 N2=256 N3=256 0xffffc20004803000-0xffffc20004904000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc20004904000-0xffffc20004bec000 3047424 sys_swapon+0x640/0xac0 pages=743 vmalloc vpages N0=743 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 pages=14 vmalloc N1=14 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 pages=4 vmalloc N0=4 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N0=2 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N1=10 0xffffffffa0022000-0xffffffffa0028000 24576 sys_init_module+0xc27/0x1d00 pages=5 vmalloc N3=5 0xffffffffa0028000-0xffffffffa0050000 163840 sys_init_module+0xc27/0x1d00 pages=39 vmalloc N1=39 0xffffffffa0050000-0xffffffffa0052000 8192 sys_init_module+0xc27/0x1d00 pages=1 vmalloc N1=1 0xffffffffa0052000-0xffffffffa0056000 16384 sys_init_module+0xc27/0x1d00 pages=3 vmalloc N1=3 0xffffffffa0056000-0xffffffffa0081000 176128 sys_init_module+0xc27/0x1d00 pages=42 vmalloc N3=42 0xffffffffa0081000-0xffffffffa00ae000 184320 sys_init_module+0xc27/0x1d00 pages=44 vmalloc N3=44 0xffffffffa00ae000-0xffffffffa00b1000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00b1000-0xffffffffa00b9000 32768 sys_init_module+0xc27/0x1d00 pages=7 vmalloc N0=7 0xffffffffa00b9000-0xffffffffa00c4000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N3=10 0xffffffffa00c6000-0xffffffffa00e0000 106496 sys_init_module+0xc27/0x1d00 pages=25 vmalloc N2=25 0xffffffffa00e0000-0xffffffffa00f1000 69632 sys_init_module+0xc27/0x1d00 pages=16 vmalloc N2=16 0xffffffffa00f1000-0xffffffffa00f4000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00f4000-0xffffffffa00f7000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 [akpm@linux-foundation.org: fix comment] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:38 +08:00
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
for (nr = 0; nr < v->nr_pages; nr++)
counters[page_to_nid(v->pages[nr])]++;
for_each_node_state(nr, N_HIGH_MEMORY)
if (counters[nr])
seq_printf(m, " N%u=%u", nr, counters[nr]);
}
}
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
static void show_purge_info(struct seq_file *m)
{
struct llist_node *head;
struct vmap_area *va;
head = READ_ONCE(vmap_purge_list.first);
if (head == NULL)
return;
llist_for_each_entry(va, head, purge_list) {
seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
(void *)va->va_start, (void *)va->va_end,
va->va_end - va->va_start);
}
}
2008-04-28 17:12:40 +08:00
static int s_show(struct seq_file *m, void *p)
{
struct vmap_area *va;
2013-04-30 06:07:35 +08:00
struct vm_struct *v;
va = list_entry(p, struct vmap_area, list);
mm/vmalloc: fix show vmap_area information race with vmap_area tear down There is a race window between vmap_area tear down and show vmap_area information. A B remove_vm_area spin_lock(&vmap_area_lock); va->vm = NULL; va->flags &= ~VM_VM_AREA; spin_unlock(&vmap_area_lock); spin_lock(&vmap_area_lock); if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEZING)) return 0; if (!(va->flags & VM_VM_AREA)) { seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); return 0; } free_unmap_vmap_area(va); flush_cache_vunmap free_unmap_vmap_area_noflush unmap_vmap_area free_vmap_area_noflush va->flags |= VM_LAZY_FREE The assumption !VM_VM_AREA represents vm_map_ram allocation is introduced by d4033afdf828 ("mm, vmalloc: iterate vmap_area_list, instead of vmlist, in vmallocinfo()"). However, !VM_VM_AREA also represents vmap_area is being tear down in race window mentioned above. This patch fix it by don't dump any information for !VM_VM_AREA case and also remove (VM_LAZY_FREE | VM_LAZY_FREEING) check since they are not possible for !VM_VM_AREA case. Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Mitsuo Hayasaka <mitsuo.hayasaka.hu@hitachi.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:31 +08:00
/*
* s_show can encounter race with remove_vm_area, !vm on behalf
* of vmap area is being tear down or vm_map_ram allocation.
mm/vmalloc: fix show vmap_area information race with vmap_area tear down There is a race window between vmap_area tear down and show vmap_area information. A B remove_vm_area spin_lock(&vmap_area_lock); va->vm = NULL; va->flags &= ~VM_VM_AREA; spin_unlock(&vmap_area_lock); spin_lock(&vmap_area_lock); if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEZING)) return 0; if (!(va->flags & VM_VM_AREA)) { seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va->va_end - va->va_start); return 0; } free_unmap_vmap_area(va); flush_cache_vunmap free_unmap_vmap_area_noflush unmap_vmap_area free_vmap_area_noflush va->flags |= VM_LAZY_FREE The assumption !VM_VM_AREA represents vm_map_ram allocation is introduced by d4033afdf828 ("mm, vmalloc: iterate vmap_area_list, instead of vmlist, in vmallocinfo()"). However, !VM_VM_AREA also represents vmap_area is being tear down in race window mentioned above. This patch fix it by don't dump any information for !VM_VM_AREA case and also remove (VM_LAZY_FREE | VM_LAZY_FREEING) check since they are not possible for !VM_VM_AREA case. Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Mitsuo Hayasaka <mitsuo.hayasaka.hu@hitachi.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:31 +08:00
*/
if (!va->vm) {
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
vmalloc: show lazy-purged vma info in vmallocinfo When ioremap a 67112960 bytes vm_area with the vmallocinfo: [..] 0xec79b000-0xec7fa000 389120 ftl_add_mtd+0x4d0/0x754 pages=94 vmalloc 0xec800000-0xecbe1000 4067328 kbox_proc_mem_write+0x104/0x1c4 phys=8b520000 ioremap we get the result: 0xf1000000-0xf5001000 67112960 devm_ioremap+0x38/0x7c phys=40000000 ioremap For the align for ioremap must be less than '1 << IOREMAP_MAX_ORDER': if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); So it makes idiot like me a litte puzzled why this was a jump the vm_area from 0xec800000-0xecbe1000 to 0xf1000000-0xf5001000, and leaving 0xed000000-0xf1000000 as a big hole. This patch is to show all of vm_area, including vmas which are freeing but still in the vmap_area_list, to make it more clear about why we will get 0xf1000000-0xf5001000 in the above case. And we will get a vmallocinfo like: [..] 0xec79b000-0xec7fa000 389120 ftl_add_mtd+0x4d0/0x754 pages=94 vmalloc 0xec800000-0xecbe1000 4067328 kbox_proc_mem_write+0x104/0x1c4 phys=8b520000 ioremap [..] 0xece7c000-0xece7e000 8192 unpurged vm_area 0xece7e000-0xece83000 20480 vm_map_ram 0xf0099000-0xf00aa000 69632 vm_map_ram after this patch. Link: http://lkml.kernel.org/r/1496649682-20710-1-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: zijun_hu <zijun_hu@htc.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 06:48:09 +08:00
(void *)va->va_start, (void *)va->va_end,
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
va->va_end - va->va_start);
vmalloc: show lazy-purged vma info in vmallocinfo When ioremap a 67112960 bytes vm_area with the vmallocinfo: [..] 0xec79b000-0xec7fa000 389120 ftl_add_mtd+0x4d0/0x754 pages=94 vmalloc 0xec800000-0xecbe1000 4067328 kbox_proc_mem_write+0x104/0x1c4 phys=8b520000 ioremap we get the result: 0xf1000000-0xf5001000 67112960 devm_ioremap+0x38/0x7c phys=40000000 ioremap For the align for ioremap must be less than '1 << IOREMAP_MAX_ORDER': if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); So it makes idiot like me a litte puzzled why this was a jump the vm_area from 0xec800000-0xecbe1000 to 0xf1000000-0xf5001000, and leaving 0xed000000-0xf1000000 as a big hole. This patch is to show all of vm_area, including vmas which are freeing but still in the vmap_area_list, to make it more clear about why we will get 0xf1000000-0xf5001000 in the above case. And we will get a vmallocinfo like: [..] 0xec79b000-0xec7fa000 389120 ftl_add_mtd+0x4d0/0x754 pages=94 vmalloc 0xec800000-0xecbe1000 4067328 kbox_proc_mem_write+0x104/0x1c4 phys=8b520000 ioremap [..] 0xece7c000-0xece7e000 8192 unpurged vm_area 0xece7e000-0xece83000 20480 vm_map_ram 0xf0099000-0xf00aa000 69632 vm_map_ram after this patch. Link: http://lkml.kernel.org/r/1496649682-20710-1-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: zijun_hu <zijun_hu@htc.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 06:48:09 +08:00
2013-04-30 06:07:35 +08:00
return 0;
vmalloc: show lazy-purged vma info in vmallocinfo When ioremap a 67112960 bytes vm_area with the vmallocinfo: [..] 0xec79b000-0xec7fa000 389120 ftl_add_mtd+0x4d0/0x754 pages=94 vmalloc 0xec800000-0xecbe1000 4067328 kbox_proc_mem_write+0x104/0x1c4 phys=8b520000 ioremap we get the result: 0xf1000000-0xf5001000 67112960 devm_ioremap+0x38/0x7c phys=40000000 ioremap For the align for ioremap must be less than '1 << IOREMAP_MAX_ORDER': if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); So it makes idiot like me a litte puzzled why this was a jump the vm_area from 0xec800000-0xecbe1000 to 0xf1000000-0xf5001000, and leaving 0xed000000-0xf1000000 as a big hole. This patch is to show all of vm_area, including vmas which are freeing but still in the vmap_area_list, to make it more clear about why we will get 0xf1000000-0xf5001000 in the above case. And we will get a vmallocinfo like: [..] 0xec79b000-0xec7fa000 389120 ftl_add_mtd+0x4d0/0x754 pages=94 vmalloc 0xec800000-0xecbe1000 4067328 kbox_proc_mem_write+0x104/0x1c4 phys=8b520000 ioremap [..] 0xece7c000-0xece7e000 8192 unpurged vm_area 0xece7e000-0xece83000 20480 vm_map_ram 0xf0099000-0xf00aa000 69632 vm_map_ram after this patch. Link: http://lkml.kernel.org/r/1496649682-20710-1-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: zijun_hu <zijun_hu@htc.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 06:48:09 +08:00
}
2013-04-30 06:07:35 +08:00
v = va->vm;
2008-04-28 17:12:40 +08:00
seq_printf(m, "0x%pK-0x%pK %7ld",
2008-04-28 17:12:40 +08:00
v->addr, v->addr + v->size, v->size);
if (v->caller)
seq_printf(m, " %pS", v->caller);
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
2008-04-28 17:12:40 +08:00
if (v->nr_pages)
seq_printf(m, " pages=%d", v->nr_pages);
if (v->phys_addr)
seq_printf(m, " phys=%pa", &v->phys_addr);
2008-04-28 17:12:40 +08:00
if (v->flags & VM_IOREMAP)
seq_puts(m, " ioremap");
2008-04-28 17:12:40 +08:00
if (v->flags & VM_ALLOC)
seq_puts(m, " vmalloc");
2008-04-28 17:12:40 +08:00
if (v->flags & VM_MAP)
seq_puts(m, " vmap");
2008-04-28 17:12:40 +08:00
if (v->flags & VM_USERMAP)
seq_puts(m, " user");
2008-04-28 17:12:40 +08:00
if (v->flags & VM_DMA_COHERENT)
seq_puts(m, " dma-coherent");
if (is_vmalloc_addr(v->pages))
seq_puts(m, " vpages");
2008-04-28 17:12:40 +08:00
vmallocinfo: add NUMA information Christoph recently added /proc/vmallocinfo file to get information about vmalloc allocations. This patch adds NUMA specific information, giving number of pages allocated on each memory node. This should help to check that vmalloc() is able to respect NUMA policies. Example of output on a four nodes machine (one cpu per node) 1) network hash tables are evenly spreaded on four nodes (OK) (Same point for inodes and dentries hash tables) 2) iptables tables (x_tables) are correctly allocated on each cpu node (OK). 3) sys_swapon() allocates its memory from one node only. 4) each loaded module is using memory on one node. Sysadmins could tune their setup to change points 3) and 4) if necessary. grep "pages=" /proc/vmallocinfo 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204/0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc2000031a000-0xffffc2000031d000 12288 alloc_large_system_hash+0x204/0x2c0 pages=2 vmalloc N1=1 N2=1 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e/0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 0xffffc2000033e000-0xffffc20000341000 12288 sys_swapon+0x640/0xac0 pages=2 vmalloc N0=2 0xffffc20000341000-0xffffc20000344000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N0=2 0xffffc20000344000-0xffffc20000347000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N1=2 0xffffc20000347000-0xffffc2000034a000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N2=2 0xffffc2000034a000-0xffffc2000034d000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N3=2 0xffffc20004381000-0xffffc20004402000 528384 alloc_large_system_hash+0x204/0x2c0 pages=128 vmalloc N0=32 N1=32 N2=32 N3=32 0xffffc20004402000-0xffffc20004803000 4198400 alloc_large_system_hash+0x204/0x2c0 pages=1024 vmalloc vpages N0=256 N1=256 N2=256 N3=256 0xffffc20004803000-0xffffc20004904000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc20004904000-0xffffc20004bec000 3047424 sys_swapon+0x640/0xac0 pages=743 vmalloc vpages N0=743 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 pages=14 vmalloc N1=14 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 pages=4 vmalloc N0=4 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N0=2 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N1=10 0xffffffffa0022000-0xffffffffa0028000 24576 sys_init_module+0xc27/0x1d00 pages=5 vmalloc N3=5 0xffffffffa0028000-0xffffffffa0050000 163840 sys_init_module+0xc27/0x1d00 pages=39 vmalloc N1=39 0xffffffffa0050000-0xffffffffa0052000 8192 sys_init_module+0xc27/0x1d00 pages=1 vmalloc N1=1 0xffffffffa0052000-0xffffffffa0056000 16384 sys_init_module+0xc27/0x1d00 pages=3 vmalloc N1=3 0xffffffffa0056000-0xffffffffa0081000 176128 sys_init_module+0xc27/0x1d00 pages=42 vmalloc N3=42 0xffffffffa0081000-0xffffffffa00ae000 184320 sys_init_module+0xc27/0x1d00 pages=44 vmalloc N3=44 0xffffffffa00ae000-0xffffffffa00b1000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00b1000-0xffffffffa00b9000 32768 sys_init_module+0xc27/0x1d00 pages=7 vmalloc N0=7 0xffffffffa00b9000-0xffffffffa00c4000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N3=10 0xffffffffa00c6000-0xffffffffa00e0000 106496 sys_init_module+0xc27/0x1d00 pages=25 vmalloc N2=25 0xffffffffa00e0000-0xffffffffa00f1000 69632 sys_init_module+0xc27/0x1d00 pages=16 vmalloc N2=16 0xffffffffa00f1000-0xffffffffa00f4000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00f4000-0xffffffffa00f7000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 [akpm@linux-foundation.org: fix comment] Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:38 +08:00
show_numa_info(m, v);
2008-04-28 17:12:40 +08:00
seq_putc(m, '\n');
mm/vmalloc: do not keep unpurged areas in the busy tree The busy tree can be quite big, even though the area is freed or unmapped it still stays there until "purge" logic removes it. 1) Optimize and reduce the size of "busy" tree by removing a node from it right away as soon as user triggers free paths. It is possible to do so, because the allocation is done using another augmented tree. The vmalloc test driver shows the difference, for example the "fix_size_alloc_test" is ~11% better comparing with default configuration: sudo ./test_vmalloc.sh performance <default> Summary: fix_size_alloc_test loops: 1000000 avg: 993985 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973554 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12617652 usec <default> <this patch> Summary: fix_size_alloc_test loops: 1000000 avg: 882263 usec Summary: full_fit_alloc_test loops: 1000000 avg: 973407 usec Summary: long_busy_list_alloc_test loops: 1000000 avg: 12593929 usec <this patch> 2) Since the busy tree now contains allocated areas only and does not interfere with lazily free nodes, introduce the new function show_purge_info() that dumps "unpurged" areas that is propagated through "/proc/vmallocinfo". 3) Eliminate VM_LAZY_FREE flag. Link: http://lkml.kernel.org/r/20190716152656.12255-2-lpf.vector@gmail.com Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Pengfei Li <lpf.vector@gmail.com> Cc: Roman Gushchin <guro@fb.com> Cc: Uladzislau Rezki <urezki@gmail.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 06:36:36 +08:00
/*
* As a final step, dump "unpurged" areas. Note,
* that entire "/proc/vmallocinfo" output will not
* be address sorted, because the purge list is not
* sorted.
*/
if (list_is_last(&va->list, &vmap_area_list))
show_purge_info(m);
2008-04-28 17:12:40 +08:00
return 0;
}
static const struct seq_operations vmalloc_op = {
2008-04-28 17:12:40 +08:00
.start = s_start,
.next = s_next,
.stop = s_stop,
.show = s_show,
};
static int __init proc_vmalloc_init(void)
{
if (IS_ENABLED(CONFIG_NUMA))
proc_create_seq_private("vmallocinfo", 0400, NULL,
&vmalloc_op,
nr_node_ids * sizeof(unsigned int), NULL);
else
proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op);
return 0;
}
module_init(proc_vmalloc_init);
2008-04-28 17:12:40 +08:00
#endif