OpenCloudOS-Kernel/drivers/xen/balloon.c

732 lines
18 KiB
C
Raw Normal View History

/******************************************************************************
* Xen balloon driver - enables returning/claiming memory to/from Xen.
*
* Copyright (c) 2003, B Dragovic
* Copyright (c) 2003-2004, M Williamson, K Fraser
* Copyright (c) 2005 Dan M. Smith, IBM Corporation
* Copyright (c) 2010 Daniel Kiper
*
* Memory hotplug support was written by Daniel Kiper. Work on
* it was sponsored by Google under Google Summer of Code 2010
* program. Jeremy Fitzhardinge from Citrix was the mentor for
* this project.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation; or, when distributed
* separately from the Linux kernel or incorporated into other
* software packages, subject to the following license:
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this source file (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy, modify,
* merge, publish, distribute, sublicense, and/or sell copies of the Software,
* and to permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/errno.h>
#include <linux/mm.h>
mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include <linux/memblock.h> @@ @@ - #include <linux/bootmem.h> + #include <linux/memblock.h> [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:09:49 +08:00
#include <linux/memblock.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/mutex.h>
#include <linux/list.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/percpu-defs.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <xen/xen.h>
#include <xen/interface/xen.h>
#include <xen/interface/memory.h>
#include <xen/balloon.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/mem-reservation.h>
static int xen_hotplug_unpopulated;
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
static struct ctl_table balloon_table[] = {
{
.procname = "hotplug_unpopulated",
.data = &xen_hotplug_unpopulated,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:50 +08:00
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{ }
};
static struct ctl_table balloon_root[] = {
{
.procname = "balloon",
.mode = 0555,
.child = balloon_table,
},
{ }
};
static struct ctl_table xen_root[] = {
{
.procname = "xen",
.mode = 0555,
.child = balloon_root,
},
{ }
};
#endif
/*
* Use one extent per PAGE_SIZE to avoid to break down the page into
* multiple frame.
*/
#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
/*
* balloon_process() state:
*
* BP_DONE: done or nothing to do,
* BP_WAIT: wait to be rescheduled,
* BP_EAGAIN: error, go to sleep,
* BP_ECANCELED: error, balloon operation canceled.
*/
enum bp_state {
BP_DONE,
BP_WAIT,
BP_EAGAIN,
BP_ECANCELED
};
static DEFINE_MUTEX(balloon_mutex);
struct balloon_stats balloon_stats;
EXPORT_SYMBOL_GPL(balloon_stats);
/* We increase/decrease in batches which fit in a page */
static xen_pfn_t frame_list[PAGE_SIZE / sizeof(xen_pfn_t)];
/* List of ballooned pages, threaded through the mem_map array. */
static LIST_HEAD(ballooned_pages);
static DECLARE_WAIT_QUEUE_HEAD(balloon_wq);
/* Main work function, always executed in process context. */
static void balloon_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
/* When ballooning out (allocating memory to return to Xen) we don't really
want the kernel to try too hard since that can trigger the oom killer. */
#define GFP_BALLOON \
(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
/* balloon_append: add the given page to the balloon. */
static void balloon_append(struct page *page)
{
__SetPageOffline(page);
/* Lowmem is re-populated first, so highmem pages go at list tail. */
if (PageHighMem(page)) {
list_add_tail(&page->lru, &ballooned_pages);
balloon_stats.balloon_high++;
} else {
list_add(&page->lru, &ballooned_pages);
balloon_stats.balloon_low++;
}
wake_up(&balloon_wq);
}
/* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
static struct page *balloon_retrieve(bool require_lowmem)
{
struct page *page;
if (list_empty(&ballooned_pages))
return NULL;
page = list_entry(ballooned_pages.next, struct page, lru);
if (require_lowmem && PageHighMem(page))
return NULL;
list_del(&page->lru);
mm: correctly update zone->managed_pages Enhance adjust_managed_page_count() to adjust totalhigh_pages for highmem pages. And change code which directly adjusts totalram_pages to use adjust_managed_page_count() because it adjusts totalram_pages, totalhigh_pages and zone->managed_pages altogether in a safe way. Remove inc_totalhigh_pages() and dec_totalhigh_pages() from xen/balloon driver bacause adjust_managed_page_count() has already adjusted totalhigh_pages. This patch also fixes two bugs: 1) enhances virtio_balloon driver to adjust totalhigh_pages when reserve/unreserve pages. 2) enhance memory_hotplug.c to adjust totalhigh_pages when hot-removing memory. We still need to deal with modifications of totalram_pages in file arch/powerpc/platforms/pseries/cmm.c, but need help from PPC experts. [akpm@linux-foundation.org: remove ifdef, per Wanpeng Li, virtio_balloon.c cleanup, per Sergei] [akpm@linux-foundation.org: export adjust_managed_page_count() to modules, for drivers/virtio/virtio_balloon.c] Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:21 +08:00
if (PageHighMem(page))
balloon_stats.balloon_high--;
mm: correctly update zone->managed_pages Enhance adjust_managed_page_count() to adjust totalhigh_pages for highmem pages. And change code which directly adjusts totalram_pages to use adjust_managed_page_count() because it adjusts totalram_pages, totalhigh_pages and zone->managed_pages altogether in a safe way. Remove inc_totalhigh_pages() and dec_totalhigh_pages() from xen/balloon driver bacause adjust_managed_page_count() has already adjusted totalhigh_pages. This patch also fixes two bugs: 1) enhances virtio_balloon driver to adjust totalhigh_pages when reserve/unreserve pages. 2) enhance memory_hotplug.c to adjust totalhigh_pages when hot-removing memory. We still need to deal with modifications of totalram_pages in file arch/powerpc/platforms/pseries/cmm.c, but need help from PPC experts. [akpm@linux-foundation.org: remove ifdef, per Wanpeng Li, virtio_balloon.c cleanup, per Sergei] [akpm@linux-foundation.org: export adjust_managed_page_count() to modules, for drivers/virtio/virtio_balloon.c] Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:21 +08:00
else
balloon_stats.balloon_low--;
__ClearPageOffline(page);
return page;
}
static struct page *balloon_next_page(struct page *page)
{
struct list_head *next = page->lru.next;
if (next == &ballooned_pages)
return NULL;
return list_entry(next, struct page, lru);
}
static enum bp_state update_schedule(enum bp_state state)
{
if (state == BP_WAIT)
return BP_WAIT;
if (state == BP_ECANCELED)
return BP_ECANCELED;
if (state == BP_DONE) {
balloon_stats.schedule_delay = 1;
balloon_stats.retry_count = 1;
return BP_DONE;
}
++balloon_stats.retry_count;
if (balloon_stats.max_retry_count != RETRY_UNLIMITED &&
balloon_stats.retry_count > balloon_stats.max_retry_count) {
balloon_stats.schedule_delay = 1;
balloon_stats.retry_count = 1;
return BP_ECANCELED;
}
balloon_stats.schedule_delay <<= 1;
if (balloon_stats.schedule_delay > balloon_stats.max_schedule_delay)
balloon_stats.schedule_delay = balloon_stats.max_schedule_delay;
return BP_EAGAIN;
}
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
static void release_memory_resource(struct resource *resource)
{
if (!resource)
return;
/*
* No need to reset region to identity mapped since we now
* know that no I/O can be in this region
*/
release_resource(resource);
kfree(resource);
}
static struct resource *additional_memory_resource(phys_addr_t size)
{
struct resource *res;
int ret;
res = kzalloc(sizeof(*res), GFP_KERNEL);
if (!res)
return NULL;
res->name = "System RAM";
res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
ret = allocate_resource(&iomem_resource, res,
size, 0, -1,
PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
if (ret < 0) {
pr_err("Cannot allocate new System RAM resource\n");
kfree(res);
return NULL;
}
return res;
}
static enum bp_state reserve_additional_memory(void)
{
long credit;
struct resource *resource;
int nid, rc;
unsigned long balloon_hotplug;
credit = balloon_stats.target_pages + balloon_stats.target_unpopulated
- balloon_stats.total_pages;
/*
* Already hotplugged enough pages? Wait for them to be
* onlined.
*/
if (credit <= 0)
return BP_WAIT;
balloon_hotplug = round_up(credit, PAGES_PER_SECTION);
resource = additional_memory_resource(balloon_hotplug * PAGE_SIZE);
if (!resource)
goto err;
nid = memory_add_physaddr_to_nid(resource->start);
#ifdef CONFIG_XEN_HAVE_PVMMU
/*
* We don't support PV MMU when Linux and Xen is using
* different page granularity.
*/
BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
/*
* add_memory() will build page tables for the new memory so
* the p2m must contain invalid entries so the correct
* non-present PTEs will be written.
*
* If a failure occurs, the original (identity) p2m entries
* are not restored since this region is now known not to
* conflict with any devices.
*/
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
unsigned long pfn, i;
pfn = PFN_DOWN(resource->start);
for (i = 0; i < balloon_hotplug; i++) {
if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
pr_warn("set_phys_to_machine() failed, no memory added\n");
goto err;
}
}
}
#endif
/*
* add_memory_resource() will call online_pages() which in its turn
* will call xen_online_page() callback causing deadlock if we don't
* release balloon_mutex here. Unlocking here is safe because the
* callers drop the mutex before trying again.
*/
mutex_unlock(&balloon_mutex);
mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Len Brown <lenb@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com> Cc: John Allen <jallen@linux.vnet.ibm.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mathieu Malaterre <malat@debian.org> Cc: Pavel Tatashin <pavel.tatashin@microsoft.com> Cc: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Neuling <mikey@neuling.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:10:24 +08:00
/* add_memory_resource() requires the device_hotplug lock */
lock_device_hotplug();
rc = add_memory_resource(nid, resource);
mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Len Brown <lenb@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com> Cc: John Allen <jallen@linux.vnet.ibm.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mathieu Malaterre <malat@debian.org> Cc: Pavel Tatashin <pavel.tatashin@microsoft.com> Cc: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Neuling <mikey@neuling.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:10:24 +08:00
unlock_device_hotplug();
mutex_lock(&balloon_mutex);
if (rc) {
pr_warn("Cannot add additional memory (%i)\n", rc);
goto err;
}
balloon_stats.total_pages += balloon_hotplug;
return BP_WAIT;
err:
release_memory_resource(resource);
return BP_ECANCELED;
}
mm/page_alloc.c: memory hotplug: free pages as higher order When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks@codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org [akpm@linux-foundation.org: remove unused local, per Arun] [akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks@codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org [arunks@codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mathieu Malaterre <malat@debian.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Srivatsa Vaddagiri <vatsa@codeaurora.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:14 +08:00
static void xen_online_page(struct page *page, unsigned int order)
{
mm/page_alloc.c: memory hotplug: free pages as higher order When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks@codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org [akpm@linux-foundation.org: remove unused local, per Arun] [akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks@codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org [arunks@codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mathieu Malaterre <malat@debian.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Srivatsa Vaddagiri <vatsa@codeaurora.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:14 +08:00
unsigned long i, size = (1 << order);
unsigned long start_pfn = page_to_pfn(page);
struct page *p;
mm/page_alloc.c: memory hotplug: free pages as higher order When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks@codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org [akpm@linux-foundation.org: remove unused local, per Arun] [akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks@codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org [arunks@codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mathieu Malaterre <malat@debian.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Srivatsa Vaddagiri <vatsa@codeaurora.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:14 +08:00
pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn);
mutex_lock(&balloon_mutex);
mm/page_alloc.c: memory hotplug: free pages as higher order When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks@codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org [akpm@linux-foundation.org: remove unused local, per Arun] [akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks@codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org [arunks@codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mathieu Malaterre <malat@debian.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Srivatsa Vaddagiri <vatsa@codeaurora.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:14 +08:00
for (i = 0; i < size; i++) {
p = pfn_to_page(start_pfn + i);
balloon_append(p);
mm/page_alloc.c: memory hotplug: free pages as higher order When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks@codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org [akpm@linux-foundation.org: remove unused local, per Arun] [akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks@codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org [arunks@codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mathieu Malaterre <malat@debian.org> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Srivatsa Vaddagiri <vatsa@codeaurora.org> Cc: Vinayak Menon <vinmenon@codeaurora.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:42:14 +08:00
}
mutex_unlock(&balloon_mutex);
}
static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v)
{
if (val == MEM_ONLINE)
schedule_delayed_work(&balloon_worker, 0);
return NOTIFY_OK;
}
static struct notifier_block xen_memory_nb = {
.notifier_call = xen_memory_notifier,
.priority = 0
};
#else
static enum bp_state reserve_additional_memory(void)
{
balloon_stats.target_pages = balloon_stats.current_pages +
balloon_stats.target_unpopulated;
return BP_ECANCELED;
}
#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
static long current_credit(void)
{
return balloon_stats.target_pages - balloon_stats.current_pages;
}
static bool balloon_is_inflated(void)
{
return balloon_stats.balloon_low || balloon_stats.balloon_high;
}
static enum bp_state increase_reservation(unsigned long nr_pages)
{
int rc;
unsigned long i;
struct page *page;
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
page = list_first_entry_or_null(&ballooned_pages, struct page, lru);
for (i = 0; i < nr_pages; i++) {
if (!page) {
nr_pages = i;
break;
}
frame_list[i] = page_to_xen_pfn(page);
page = balloon_next_page(page);
}
rc = xenmem_reservation_increase(nr_pages, frame_list);
if (rc <= 0)
return BP_EAGAIN;
for (i = 0; i < rc; i++) {
page = balloon_retrieve(false);
BUG_ON(page == NULL);
xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
/* Relinquish the page back to the allocator. */
free_reserved_page(page);
}
balloon_stats.current_pages += rc;
return BP_DONE;
}
static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
{
enum bp_state state = BP_DONE;
unsigned long i;
struct page *page, *tmp;
int ret;
LIST_HEAD(pages);
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
for (i = 0; i < nr_pages; i++) {
page = alloc_page(gfp);
if (page == NULL) {
nr_pages = i;
state = BP_EAGAIN;
break;
}
adjust_managed_page_count(page, -1);
xenmem_reservation_scrub_page(page);
list_add(&page->lru, &pages);
}
/*
* Ensure that ballooned highmem pages don't have kmaps.
*
* Do this before changing the p2m as kmap_flush_unused()
* reads PTEs to obtain pages (and hence needs the original
* p2m entry).
*/
kmap_flush_unused();
/*
* Setup the frame, update direct mapping, invalidate P2M,
* and add to balloon.
*/
i = 0;
list_for_each_entry_safe(page, tmp, &pages, lru) {
frame_list[i++] = xen_page_to_gfn(page);
xenmem_reservation_va_mapping_reset(1, &page);
list_del(&page->lru);
balloon_append(page);
}
flush_tlb_all();
ret = xenmem_reservation_decrease(nr_pages, frame_list);
BUG_ON(ret != nr_pages);
balloon_stats.current_pages -= nr_pages;
return state;
}
/*
* As this is a work item it is guaranteed to run as a single instance only.
* We may of course race updates of the target counts (which are protected
* by the balloon lock), or with changes to the Xen hard limit, but we will
* recover from these in time.
*/
static void balloon_process(struct work_struct *work)
{
enum bp_state state = BP_DONE;
long credit;
do {
mutex_lock(&balloon_mutex);
credit = current_credit();
if (credit > 0) {
if (balloon_is_inflated())
state = increase_reservation(credit);
else
state = reserve_additional_memory();
}
if (credit < 0) {
long n_pages;
n_pages = min(-credit, si_mem_available());
state = decrease_reservation(n_pages, GFP_BALLOON);
if (state == BP_DONE && n_pages != -credit &&
n_pages < totalreserve_pages)
state = BP_EAGAIN;
}
state = update_schedule(state);
mutex_unlock(&balloon_mutex);
cond_resched();
} while (credit && state == BP_DONE);
/* Schedule more work if there is some still to be done. */
if (state == BP_EAGAIN)
schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
}
/* Resets the Xen limit, sets new target, and kicks off processing. */
void balloon_set_new_target(unsigned long target)
{
/* No need for lock. Not read-modify-write updates. */
balloon_stats.target_pages = target;
schedule_delayed_work(&balloon_worker, 0);
}
EXPORT_SYMBOL_GPL(balloon_set_new_target);
static int add_ballooned_pages(int nr_pages)
{
enum bp_state st;
if (xen_hotplug_unpopulated) {
st = reserve_additional_memory();
if (st != BP_ECANCELED) {
int rc;
mutex_unlock(&balloon_mutex);
rc = wait_event_interruptible(balloon_wq,
!list_empty(&ballooned_pages));
mutex_lock(&balloon_mutex);
return rc ? -ENOMEM : 0;
}
}
if (si_mem_available() < nr_pages)
return -ENOMEM;
st = decrease_reservation(nr_pages, GFP_USER);
if (st != BP_DONE)
return -ENOMEM;
return 0;
}
/**
* alloc_xenballooned_pages - get pages that have been ballooned out
* @nr_pages: Number of pages to get
* @pages: pages returned
* @return 0 on success, error otherwise
*/
int alloc_xenballooned_pages(int nr_pages, struct page **pages)
{
int pgno = 0;
struct page *page;
int ret;
mutex_lock(&balloon_mutex);
balloon_stats.target_unpopulated += nr_pages;
while (pgno < nr_pages) {
page = balloon_retrieve(true);
if (page) {
pages[pgno++] = page;
#ifdef CONFIG_XEN_HAVE_PVMMU
/*
* We don't support PV MMU when Linux and Xen is using
* different page granularity.
*/
BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
ret = xen_alloc_p2m_entry(page_to_pfn(page));
if (ret < 0)
goto out_undo;
}
#endif
} else {
ret = add_ballooned_pages(nr_pages - pgno);
if (ret < 0)
goto out_undo;
}
}
mutex_unlock(&balloon_mutex);
return 0;
out_undo:
mutex_unlock(&balloon_mutex);
free_xenballooned_pages(pgno, pages);
/*
* NB: free_xenballooned_pages will only subtract pgno pages, but since
* target_unpopulated is incremented with nr_pages at the start we need
* to remove the remaining ones also, or accounting will be screwed.
*/
balloon_stats.target_unpopulated -= nr_pages - pgno;
return ret;
}
EXPORT_SYMBOL(alloc_xenballooned_pages);
/**
* free_xenballooned_pages - return pages retrieved with get_ballooned_pages
* @nr_pages: Number of pages
* @pages: pages to return
*/
void free_xenballooned_pages(int nr_pages, struct page **pages)
{
int i;
mutex_lock(&balloon_mutex);
for (i = 0; i < nr_pages; i++) {
if (pages[i])
balloon_append(pages[i]);
}
balloon_stats.target_unpopulated -= nr_pages;
/* The balloon may be too large now. Shrink it if needed. */
if (current_credit())
schedule_delayed_work(&balloon_worker, 0);
mutex_unlock(&balloon_mutex);
}
EXPORT_SYMBOL(free_xenballooned_pages);
#ifdef CONFIG_XEN_PV
static void __init balloon_add_region(unsigned long start_pfn,
unsigned long pages)
{
unsigned long pfn, extra_pfn_end;
/*
* If the amount of usable memory has been limited (e.g., with
* the 'mem' command line parameter), don't add pages beyond
* this limit.
*/
extra_pfn_end = min(max_pfn, start_pfn + pages);
for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
/* totalram_pages and totalhigh_pages do not
include the boot-time balloon extension, so
don't subtract from it. */
balloon_append(pfn_to_page(pfn));
}
balloon_stats.total_pages += extra_pfn_end - start_pfn;
}
#endif
static int __init balloon_init(void)
{
if (!xen_domain())
return -ENODEV;
pr_info("Initialising balloon driver\n");
#ifdef CONFIG_XEN_PV
balloon_stats.current_pages = xen_pv_domain()
? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
: get_num_physpages();
#else
balloon_stats.current_pages = get_num_physpages();
#endif
balloon_stats.target_pages = balloon_stats.current_pages;
balloon_stats.balloon_low = 0;
balloon_stats.balloon_high = 0;
balloon_stats.total_pages = balloon_stats.current_pages;
balloon_stats.schedule_delay = 1;
balloon_stats.max_schedule_delay = 32;
balloon_stats.retry_count = 1;
balloon_stats.max_retry_count = 4;
#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
set_online_page_callback(&xen_online_page);
register_memory_notifier(&xen_memory_nb);
register_sysctl_table(xen_root);
#endif
#ifdef CONFIG_XEN_PV
{
int i;
/*
* Initialize the balloon with pages from the extra memory
* regions (see arch/x86/xen/setup.c).
*/
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
if (xen_extra_mem[i].n_pfns)
balloon_add_region(xen_extra_mem[i].start_pfn,
xen_extra_mem[i].n_pfns);
}
#endif
/* Init the xen-balloon driver. */
xen_balloon_init();
return 0;
}
subsys_initcall(balloon_init);