linux-sg2042/mm/page_cgroup.c

574 lines
13 KiB
C
Raw Normal View History

#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/bootmem.h>
#include <linux/bit_spinlock.h>
#include <linux/page_cgroup.h>
#include <linux/hash.h>
#include <linux/slab.h>
#include <linux/memory.h>
#include <linux/vmalloc.h>
#include <linux/cgroup.h>
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
#include <linux/swapops.h>
#include <linux/kmemleak.h>
static void __meminit init_page_cgroup(struct page_cgroup *pc, unsigned long id)
{
pc->flags = 0;
set_page_cgroup_array_id(pc, id);
pc->mem_cgroup = NULL;
memcg: synchronized LRU A big patch for changing memcg's LRU semantics. Now, - page_cgroup is linked to mem_cgroup's its own LRU (per zone). - LRU of page_cgroup is not synchronous with global LRU. - page and page_cgroup is one-to-one and statically allocated. - To find page_cgroup is on what LRU, you have to check pc->mem_cgroup as - lru = page_cgroup_zoneinfo(pc, nid_of_pc, zid_of_pc); - SwapCache is handled. And, when we handle LRU list of page_cgroup, we do following. pc = lookup_page_cgroup(page); lock_page_cgroup(pc); .....................(1) mz = page_cgroup_zoneinfo(pc); spin_lock(&mz->lru_lock); .....add to LRU spin_unlock(&mz->lru_lock); unlock_page_cgroup(pc); But (1) is spin_lock and we have to be afraid of dead-lock with zone->lru_lock. So, trylock() is used at (1), now. Without (1), we can't trust "mz" is correct. This is a trial to remove this dirty nesting of locks. This patch changes mz->lru_lock to be zone->lru_lock. Then, above sequence will be written as spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU mem_cgroup_add/remove/etc_lru() { pc = lookup_page_cgroup(page); mz = page_cgroup_zoneinfo(pc); if (PageCgroupUsed(pc)) { ....add to LRU } spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU This is much simpler. (*) We're safe even if we don't take lock_page_cgroup(pc). Because.. 1. When pc->mem_cgroup can be modified. - at charge. - at account_move(). 2. at charge the PCG_USED bit is not set before pc->mem_cgroup is fixed. 3. at account_move() the page is isolated and not on LRU. Pros. - easy for maintenance. - memcg can make use of laziness of pagevec. - we don't have to duplicated LRU/Active/Unevictable bit in page_cgroup. - LRU status of memcg will be synchronized with global LRU's one. - # of locks are reduced. - account_move() is simplified very much. Cons. - may increase cost of LRU rotation. (no impact if memcg is not configured.) Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:08:01 +08:00
INIT_LIST_HEAD(&pc->lru);
}
static unsigned long total_usage;
#if !defined(CONFIG_SPARSEMEM)
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
{
pgdat->node_page_cgroup = NULL;
}
struct page_cgroup *lookup_page_cgroup(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
unsigned long offset;
struct page_cgroup *base;
base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
if (unlikely(!base))
return NULL;
offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
return base + offset;
}
struct page *lookup_cgroup_page(struct page_cgroup *pc)
{
unsigned long pfn;
struct page *page;
pg_data_t *pgdat;
pgdat = NODE_DATA(page_cgroup_array_id(pc));
pfn = pc - pgdat->node_page_cgroup + pgdat->node_start_pfn;
page = pfn_to_page(pfn);
VM_BUG_ON(pc != lookup_page_cgroup(page));
return page;
}
static int __init alloc_node_page_cgroup(int nid)
{
struct page_cgroup *base, *pc;
unsigned long table_size;
unsigned long start_pfn, nr_pages, index;
start_pfn = NODE_DATA(nid)->node_start_pfn;
nr_pages = NODE_DATA(nid)->node_spanned_pages;
if (!nr_pages)
return 0;
table_size = sizeof(struct page_cgroup) * nr_pages;
base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
if (!base)
return -ENOMEM;
for (index = 0; index < nr_pages; index++) {
pc = base + index;
init_page_cgroup(pc, nid);
}
NODE_DATA(nid)->node_page_cgroup = base;
total_usage += table_size;
return 0;
}
void __init page_cgroup_init_flatmem(void)
{
int nid, fail;
if (mem_cgroup_disabled())
return;
for_each_online_node(nid) {
fail = alloc_node_page_cgroup(nid);
if (fail)
goto fail;
}
printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
" don't want memory cgroups\n");
return;
fail:
printk(KERN_CRIT "allocation of page_cgroup failed.\n");
printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
panic("Out of memory");
}
#else /* CONFIG_FLAT_NODE_MEM_MAP */
struct page_cgroup *lookup_page_cgroup(struct page *page)
{
unsigned long pfn = page_to_pfn(page);
struct mem_section *section = __pfn_to_section(pfn);
if (!section->page_cgroup)
return NULL;
return section->page_cgroup + pfn;
}
struct page *lookup_cgroup_page(struct page_cgroup *pc)
{
struct mem_section *section;
struct page *page;
unsigned long nr;
nr = page_cgroup_array_id(pc);
section = __nr_to_section(nr);
page = pfn_to_page(pc - section->page_cgroup);
VM_BUG_ON(pc != lookup_page_cgroup(page));
return page;
}
static void *__meminit alloc_page_cgroup(size_t size, int nid)
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
{
void *addr = NULL;
cgroup/kmemleak: Annotate alloc_page() for cgroup allocations When the cgroup base was allocated with kmalloc, it was necessary to annotate the variable with kmemleak_not_leak(). But because it has recently been changed to be allocated with alloc_page() (which skips kmemleak checks) causes a warning on boot up. I was triggering this output: allocated 8388608 bytes of page_cgroup please try 'cgroup_disable=memory' option if you don't want memory cgroups kmemleak: Trying to color unknown object at 0xf5840000 as Grey Pid: 0, comm: swapper Not tainted 3.0.0-test #12 Call Trace: [<c17e34e6>] ? printk+0x1d/0x1f^M [<c10e2941>] paint_ptr+0x4f/0x78 [<c178ab57>] kmemleak_not_leak+0x58/0x7d [<c108ae9f>] ? __rcu_read_unlock+0x9/0x7d [<c1cdb462>] kmemleak_init+0x19d/0x1e9 [<c1cbf771>] start_kernel+0x346/0x3ec [<c1cbf1b4>] ? loglevel+0x18/0x18 [<c1cbf0aa>] i386_start_kernel+0xaa/0xb0 After a bit of debugging I tracked the object 0xf840000 (and others) down to the cgroup code. The change from allocating base with kmalloc to alloc_page() has the base not calling kmemleak_alloc() which adds the pointer to the object_tree_root, but kmemleak_not_leak() adds it to the crt_early_log[] table. On kmemleak_init(), the entry is found in the early_log[] but not the object_tree_root, and this error message is displayed. If alloc_page() fails then it defaults back to vmalloc() which still uses the kmemleak_alloc() which makes us still need the kmemleak_not_leak() call. The solution is to call the kmemleak_alloc() directly if the alloc_page() succeeds. Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-03 04:38:11 +08:00
gfp_t flags = GFP_KERNEL | __GFP_NOWARN;
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
cgroup/kmemleak: Annotate alloc_page() for cgroup allocations When the cgroup base was allocated with kmalloc, it was necessary to annotate the variable with kmemleak_not_leak(). But because it has recently been changed to be allocated with alloc_page() (which skips kmemleak checks) causes a warning on boot up. I was triggering this output: allocated 8388608 bytes of page_cgroup please try 'cgroup_disable=memory' option if you don't want memory cgroups kmemleak: Trying to color unknown object at 0xf5840000 as Grey Pid: 0, comm: swapper Not tainted 3.0.0-test #12 Call Trace: [<c17e34e6>] ? printk+0x1d/0x1f^M [<c10e2941>] paint_ptr+0x4f/0x78 [<c178ab57>] kmemleak_not_leak+0x58/0x7d [<c108ae9f>] ? __rcu_read_unlock+0x9/0x7d [<c1cdb462>] kmemleak_init+0x19d/0x1e9 [<c1cbf771>] start_kernel+0x346/0x3ec [<c1cbf1b4>] ? loglevel+0x18/0x18 [<c1cbf0aa>] i386_start_kernel+0xaa/0xb0 After a bit of debugging I tracked the object 0xf840000 (and others) down to the cgroup code. The change from allocating base with kmalloc to alloc_page() has the base not calling kmemleak_alloc() which adds the pointer to the object_tree_root, but kmemleak_not_leak() adds it to the crt_early_log[] table. On kmemleak_init(), the entry is found in the early_log[] but not the object_tree_root, and this error message is displayed. If alloc_page() fails then it defaults back to vmalloc() which still uses the kmemleak_alloc() which makes us still need the kmemleak_not_leak() call. The solution is to call the kmemleak_alloc() directly if the alloc_page() succeeds. Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-03 04:38:11 +08:00
addr = alloc_pages_exact_nid(nid, size, flags);
if (addr) {
kmemleak_alloc(addr, size, 1, flags);
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
return addr;
cgroup/kmemleak: Annotate alloc_page() for cgroup allocations When the cgroup base was allocated with kmalloc, it was necessary to annotate the variable with kmemleak_not_leak(). But because it has recently been changed to be allocated with alloc_page() (which skips kmemleak checks) causes a warning on boot up. I was triggering this output: allocated 8388608 bytes of page_cgroup please try 'cgroup_disable=memory' option if you don't want memory cgroups kmemleak: Trying to color unknown object at 0xf5840000 as Grey Pid: 0, comm: swapper Not tainted 3.0.0-test #12 Call Trace: [<c17e34e6>] ? printk+0x1d/0x1f^M [<c10e2941>] paint_ptr+0x4f/0x78 [<c178ab57>] kmemleak_not_leak+0x58/0x7d [<c108ae9f>] ? __rcu_read_unlock+0x9/0x7d [<c1cdb462>] kmemleak_init+0x19d/0x1e9 [<c1cbf771>] start_kernel+0x346/0x3ec [<c1cbf1b4>] ? loglevel+0x18/0x18 [<c1cbf0aa>] i386_start_kernel+0xaa/0xb0 After a bit of debugging I tracked the object 0xf840000 (and others) down to the cgroup code. The change from allocating base with kmalloc to alloc_page() has the base not calling kmemleak_alloc() which adds the pointer to the object_tree_root, but kmemleak_not_leak() adds it to the crt_early_log[] table. On kmemleak_init(), the entry is found in the early_log[] but not the object_tree_root, and this error message is displayed. If alloc_page() fails then it defaults back to vmalloc() which still uses the kmemleak_alloc() which makes us still need the kmemleak_not_leak() call. The solution is to call the kmemleak_alloc() directly if the alloc_page() succeeds. Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-03 04:38:11 +08:00
}
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
if (node_state(nid, N_HIGH_MEMORY))
addr = vmalloc_node(size, nid);
else
addr = vmalloc(size);
return addr;
}
#ifdef CONFIG_MEMORY_HOTPLUG
static void free_page_cgroup(void *addr)
{
if (is_vmalloc_addr(addr)) {
vfree(addr);
} else {
struct page *page = virt_to_page(addr);
size_t table_size =
sizeof(struct page_cgroup) * PAGES_PER_SECTION;
BUG_ON(PageReserved(page));
free_pages_exact(addr, table_size);
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
}
}
#endif
static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
{
struct page_cgroup *base, *pc;
struct mem_section *section;
unsigned long table_size;
unsigned long nr;
int index;
nr = pfn_to_section_nr(pfn);
section = __nr_to_section(nr);
if (section->page_cgroup)
return 0;
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
base = alloc_page_cgroup(table_size, nid);
/*
* The value stored in section->page_cgroup is (base - pfn)
* and it does not point to the memory block allocated above,
* causing kmemleak false positives.
*/
kmemleak_not_leak(base);
if (!base) {
printk(KERN_ERR "page cgroup allocation failure\n");
return -ENOMEM;
}
for (index = 0; index < PAGES_PER_SECTION; index++) {
pc = base + index;
init_page_cgroup(pc, nr);
}
/*
* The passed "pfn" may not be aligned to SECTION. For the calculation
* we need to apply a mask.
*/
pfn &= PAGE_SECTION_MASK;
section->page_cgroup = base - pfn;
total_usage += table_size;
return 0;
}
#ifdef CONFIG_MEMORY_HOTPLUG
void __free_page_cgroup(unsigned long pfn)
{
struct mem_section *ms;
struct page_cgroup *base;
ms = __pfn_to_section(pfn);
if (!ms || !ms->page_cgroup)
return;
base = ms->page_cgroup + pfn;
page_cgroup: reduce allocation overhead for page_cgroup array for CONFIG_SPARSEMEM Currently we are allocating a single page_cgroup array per memory section (stored in mem_section->base) when CONFIG_SPARSEMEM is selected. This is correct but memory inefficient solution because the allocated memory (unless we fall back to vmalloc) is not kmalloc friendly: - 32b - 16384 entries (20B per entry) fit into 327680B so the 524288B slab cache is used - 32b with PAE - 131072 entries with 2621440B fit into 4194304B - 64b - 32768 entries (40B per entry) fit into 2097152 cache This is ~37% wasted space per memory section and it sumps up for the whole memory. On a x86_64 machine it is something like 6MB per 1GB of RAM. We can reduce the internal fragmentation by using alloc_pages_exact which allocates PAGE_SIZE aligned blocks so we will get down to <4kB wasted memory per section which is much better. We still need a fallback to vmalloc because we have no guarantees that we will have a continuous memory of that size (order-10) later on during the hotplug events. [hannes@cmpxchg.org: do not define unused free_page_cgroup() without memory hotplug] Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:42:40 +08:00
free_page_cgroup(base);
ms->page_cgroup = NULL;
}
int __meminit online_page_cgroup(unsigned long start_pfn,
unsigned long nr_pages,
int nid)
{
unsigned long start, end, pfn;
int fail = 0;
start = SECTION_ALIGN_DOWN(start_pfn);
end = SECTION_ALIGN_UP(start_pfn + nr_pages);
if (nid == -1) {
/*
* In this case, "nid" already exists and contains valid memory.
* "start_pfn" passed to us is a pfn which is an arg for
* online__pages(), and start_pfn should exist.
*/
nid = pfn_to_nid(start_pfn);
VM_BUG_ON(!node_state(nid, N_ONLINE));
}
for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
if (!pfn_present(pfn))
continue;
fail = init_section_page_cgroup(pfn, nid);
}
if (!fail)
return 0;
/* rollback */
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
__free_page_cgroup(pfn);
return -ENOMEM;
}
int __meminit offline_page_cgroup(unsigned long start_pfn,
unsigned long nr_pages, int nid)
{
unsigned long start, end, pfn;
start = SECTION_ALIGN_DOWN(start_pfn);
end = SECTION_ALIGN_UP(start_pfn + nr_pages);
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
__free_page_cgroup(pfn);
return 0;
}
static int __meminit page_cgroup_callback(struct notifier_block *self,
unsigned long action, void *arg)
{
struct memory_notify *mn = arg;
int ret = 0;
switch (action) {
case MEM_GOING_ONLINE:
ret = online_page_cgroup(mn->start_pfn,
mn->nr_pages, mn->status_change_nid);
break;
case MEM_OFFLINE:
offline_page_cgroup(mn->start_pfn,
mn->nr_pages, mn->status_change_nid);
break;
memcg: memory hotplug fix for notifier callback Fixes for memcg/memory hotplug. While memory hotplug allocate/free memmap, page_cgroup doesn't free page_cgroup at OFFLINE when page_cgroup is allocated via bootomem. (Because freeing bootmem requires special care.) Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated by memory hotplug, page_cgroup->page == page is no longer true. But current MEM_ONLINE handler doesn't check it and update page_cgroup->page if it's not necessary to allocate page_cgroup. (This was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.) And I noticed that MEM_ONLINE can be called against "part of section". So, freeing page_cgroup at CANCEL_ONLINE will cause trouble. (freeing used page_cgroup) Don't rollback at CANCEL. One more, current memory hotplug notifier is stopped by slub because it sets NOTIFY_STOP_MASK to return vaule. So, page_cgroup's callback never be called. (low priority than slub now.) I think this slub's behavior is not intentional(BUG). and fixes it. Another way to be considered about page_cgroup allocation: - free page_cgroup at OFFLINE even if it's from bootmem and remove specieal handler. But it requires more changes. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041 Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-02 05:13:48 +08:00
case MEM_CANCEL_ONLINE:
case MEM_GOING_OFFLINE:
break;
case MEM_ONLINE:
case MEM_CANCEL_OFFLINE:
break;
}
memcg: memory hotplug fix for notifier callback Fixes for memcg/memory hotplug. While memory hotplug allocate/free memmap, page_cgroup doesn't free page_cgroup at OFFLINE when page_cgroup is allocated via bootomem. (Because freeing bootmem requires special care.) Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated by memory hotplug, page_cgroup->page == page is no longer true. But current MEM_ONLINE handler doesn't check it and update page_cgroup->page if it's not necessary to allocate page_cgroup. (This was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.) And I noticed that MEM_ONLINE can be called against "part of section". So, freeing page_cgroup at CANCEL_ONLINE will cause trouble. (freeing used page_cgroup) Don't rollback at CANCEL. One more, current memory hotplug notifier is stopped by slub because it sets NOTIFY_STOP_MASK to return vaule. So, page_cgroup's callback never be called. (low priority than slub now.) I think this slub's behavior is not intentional(BUG). and fixes it. Another way to be considered about page_cgroup allocation: - free page_cgroup at OFFLINE even if it's from bootmem and remove specieal handler. But it requires more changes. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041 Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-02 05:13:48 +08:00
return notifier_from_errno(ret);
}
#endif
void __init page_cgroup_init(void)
{
unsigned long pfn;
int nid;
if (mem_cgroup_disabled())
return;
for_each_node_state(nid, N_HIGH_MEMORY) {
unsigned long start_pfn, end_pfn;
start_pfn = node_start_pfn(nid);
end_pfn = node_end_pfn(nid);
/*
* start_pfn and end_pfn may not be aligned to SECTION and the
* page->flags of out of node pages are not initialized. So we
* scan [start_pfn, the biggest section's pfn < end_pfn) here.
*/
for (pfn = start_pfn;
pfn < end_pfn;
pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
if (!pfn_valid(pfn))
continue;
/*
* Nodes's pfns can be overlapping.
* We know some arch can have a nodes layout such as
* -------------pfn-------------->
* N0 | N1 | N2 | N0 | N1 | N2|....
*/
if (pfn_to_nid(pfn) != nid)
continue;
if (init_section_page_cgroup(pfn, nid))
goto oom;
}
}
hotplug_memory_notifier(page_cgroup_callback, 0);
printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
"don't want memory cgroups\n");
return;
oom:
printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
panic("Out of memory");
}
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
{
return;
}
#endif
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
static DEFINE_MUTEX(swap_cgroup_mutex);
struct swap_cgroup_ctrl {
struct page **map;
unsigned long length;
spinlock_t lock;
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
};
static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
struct swap_cgroup {
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
unsigned short id;
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
};
#define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup))
#define SC_POS_MASK (SC_PER_PAGE - 1)
/*
* SwapCgroup implements "lookup" and "exchange" operations.
* In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
* against SwapCache. At swap_free(), this is accessed directly from swap.
*
* This means,
* - we have no race in "exchange" when we're accessed via SwapCache because
* SwapCache(and its swp_entry) is under lock.
* - When called via swap_free(), there is no user of this entry and no race.
* Then, we don't need lock around "exchange".
*
* TODO: we can push these buffers out to HIGHMEM.
*/
/*
* allocate buffer for swap_cgroup.
*/
static int swap_cgroup_prepare(int type)
{
struct page *page;
struct swap_cgroup_ctrl *ctrl;
unsigned long idx, max;
ctrl = &swap_cgroup_ctrl[type];
for (idx = 0; idx < ctrl->length; idx++) {
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page)
goto not_enough_page;
ctrl->map[idx] = page;
}
return 0;
not_enough_page:
max = idx;
for (idx = 0; idx < max; idx++)
__free_page(ctrl->map[idx]);
return -ENOMEM;
}
/**
* swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
* @end: swap entry to be cmpxchged
* @old: old id
* @new: new id
*
* Returns old id at success, 0 at failure.
* (There is no mem_cgroup using 0 as its id)
*/
unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
unsigned short old, unsigned short new)
{
int type = swp_type(ent);
unsigned long offset = swp_offset(ent);
unsigned long idx = offset / SC_PER_PAGE;
unsigned long pos = offset & SC_POS_MASK;
struct swap_cgroup_ctrl *ctrl;
struct page *mappage;
struct swap_cgroup *sc;
unsigned long flags;
unsigned short retval;
ctrl = &swap_cgroup_ctrl[type];
mappage = ctrl->map[idx];
sc = page_address(mappage);
sc += pos;
spin_lock_irqsave(&ctrl->lock, flags);
retval = sc->id;
if (retval == old)
sc->id = new;
else
retval = 0;
spin_unlock_irqrestore(&ctrl->lock, flags);
return retval;
}
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
/**
* swap_cgroup_record - record mem_cgroup for this swp_entry.
* @ent: swap entry to be recorded into
* @mem: mem_cgroup to be recorded
*
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
* Returns old value at success, 0 at failure.
* (Of course, old value can be 0.)
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
*/
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
{
int type = swp_type(ent);
unsigned long offset = swp_offset(ent);
unsigned long idx = offset / SC_PER_PAGE;
unsigned long pos = offset & SC_POS_MASK;
struct swap_cgroup_ctrl *ctrl;
struct page *mappage;
struct swap_cgroup *sc;
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
unsigned short old;
unsigned long flags;
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
ctrl = &swap_cgroup_ctrl[type];
mappage = ctrl->map[idx];
sc = page_address(mappage);
sc += pos;
spin_lock_irqsave(&ctrl->lock, flags);
old = sc->id;
sc->id = id;
spin_unlock_irqrestore(&ctrl->lock, flags);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
return old;
}
/**
* lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
* @ent: swap entry to be looked up.
*
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
* Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
*/
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
unsigned short lookup_swap_cgroup(swp_entry_t ent)
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
{
int type = swp_type(ent);
unsigned long offset = swp_offset(ent);
unsigned long idx = offset / SC_PER_PAGE;
unsigned long pos = offset & SC_POS_MASK;
struct swap_cgroup_ctrl *ctrl;
struct page *mappage;
struct swap_cgroup *sc;
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
unsigned short ret;
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
ctrl = &swap_cgroup_ctrl[type];
mappage = ctrl->map[idx];
sc = page_address(mappage);
sc += pos;
cgroups: use css id in swap cgroup for saving memory v5 Try to use CSS ID for records in swap_cgroup. By this, on 64bit machine, size of swap_cgroup goes down to 2 bytes from 8bytes. This means, when 2GB of swap is equipped, (assume the page size is 4096bytes) From size of swap_cgroup = 2G/4k * 8 = 4Mbytes. To size of swap_cgroup = 2G/4k * 2 = 1Mbytes. Reduction is large. Of course, there are trade-offs. This CSS ID will add overhead to swap-in/swap-out/swap-free. But in general, - swap is a resource which the user tend to avoid use. - If swap is never used, swap_cgroup area is not used. - Reading traditional manuals, size of swap should be proportional to size of memory. Memory size of machine is increasing now. I think reducing size of swap_cgroup makes sense. Note: - ID->CSS lookup routine has no locks, it's under RCU-Read-Side. - memcg can be obsolete at rmdir() but not freed while refcnt from swap_cgroup is available. Changelog v4->v5: - reworked on to memcg-charge-swapcache-to-proper-memcg.patch Changlog ->v4: - fixed not configured case. - deleted unnecessary comments. - fixed NULL pointer bug. - fixed message in dmesg. [nishimura@mxp.nes.nec.co.jp: css_tryget can be called twice in !PageCgroupUsed case] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:45 +08:00
ret = sc->id;
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
return ret;
}
int swap_cgroup_swapon(int type, unsigned long max_pages)
{
void *array;
unsigned long array_size;
unsigned long length;
struct swap_cgroup_ctrl *ctrl;
if (!do_swap_account)
return 0;
length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
array_size = length * sizeof(void *);
array = vzalloc(array_size);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
if (!array)
goto nomem;
ctrl = &swap_cgroup_ctrl[type];
mutex_lock(&swap_cgroup_mutex);
ctrl->length = length;
ctrl->map = array;
spin_lock_init(&ctrl->lock);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
if (swap_cgroup_prepare(type)) {
/* memory shortage */
ctrl->map = NULL;
ctrl->length = 0;
mutex_unlock(&swap_cgroup_mutex);
vfree(array);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
goto nomem;
}
mutex_unlock(&swap_cgroup_mutex);
return 0;
nomem:
printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
printk(KERN_INFO
"swap_cgroup can be disabled by swapaccount=0 boot option\n");
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
return -ENOMEM;
}
void swap_cgroup_swapoff(int type)
{
struct page **map;
unsigned long i, length;
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
struct swap_cgroup_ctrl *ctrl;
if (!do_swap_account)
return;
mutex_lock(&swap_cgroup_mutex);
ctrl = &swap_cgroup_ctrl[type];
map = ctrl->map;
length = ctrl->length;
ctrl->map = NULL;
ctrl->length = 0;
mutex_unlock(&swap_cgroup_mutex);
if (map) {
for (i = 0; i < length; i++) {
struct page *page = map[i];
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
if (page)
__free_page(page);
}
vfree(map);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:07:58 +08:00
}
}
#endif