kernel_optimize_test/mm/balloon_compaction.c
Minchan Kim 21ea9fb69e virtio_balloon: fix race between migration and ballooning
In balloon_page_dequeue, pages_lock should cover the loop
(ie, list_for_each_entry_safe). Otherwise, the cursor page could
be isolated by compaction and then list_del by isolation could
poison the page->lru.{prev,next} so the loop finally could
access wrong address like this. This patch fixes the bug.

general protection fault: 0000 [#1] SMP
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 2 PID: 82 Comm: vballoon Not tainted 4.4.0-rc5-mm1-access_bit+ #1906
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff8800a7ff0000 ti: ffff8800a7fec000 task.ti: ffff8800a7fec000
RIP: 0010:[<ffffffff8115e754>]  [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130
RSP: 0018:ffff8800a7fefdc0  EFLAGS: 00010246
RAX: ffff88013fff9a70 RBX: ffffea000056fe00 RCX: 0000000000002b7d
RDX: ffff88013fff9a70 RSI: ffffea000056fe00 RDI: ffff88013fff9a68
RBP: ffff8800a7fefde8 R08: ffffea000056fda0 R09: 0000000000000000
R10: ffff8800a7fefd90 R11: 0000000000000001 R12: dead0000000000e0
R13: ffffea000056fe20 R14: ffff880138809070 R15: ffff880138809060
FS:  0000000000000000(0000) GS:ffff88013fc40000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00007f229c10e000 CR3: 00000000b8b53000 CR4: 00000000000006a0
Stack:
 0000000000000100 ffff880138809088 ffff880138809000 ffff880138809060
 0000000000000046 ffff8800a7fefe28 ffffffff812c86d3 ffff880138809020
 ffff880138809000 fffffffffff91900 0000000000000100 ffff880138809060
Call Trace:
 [<ffffffff812c86d3>] leak_balloon+0x93/0x1a0
 [<ffffffff812c8bc7>] balloon+0x217/0x2a0
 [<ffffffff8143739e>] ? __schedule+0x31e/0x8b0
 [<ffffffff81078160>] ? abort_exclusive_wait+0xb0/0xb0
 [<ffffffff812c89b0>] ? update_balloon_stats+0xf0/0xf0
 [<ffffffff8105b6e9>] kthread+0xc9/0xe0
 [<ffffffff8105b620>] ? kthread_park+0x60/0x60
 [<ffffffff8143b4af>] ret_from_fork+0x3f/0x70
 [<ffffffff8105b620>] ? kthread_park+0x60/0x60
Code: 8d 60 e0 0f 84 af 00 00 00 48 8b 43 20 a8 01 75 3b 48 89 d8 f0 0f ba 28 00 72 10 48 8b 03 f6 c4 08 75 2f 48 89 df e8 8c 83 f9 ff <49> 8b 44 24 20 4d 8d 6c 24 20 48 83 e8 20 4d 39 f5 74 7a 4c 89
RIP  [<ffffffff8115e754>] balloon_page_dequeue+0x54/0x130
 RSP <ffff8800a7fefdc0>
---[ end trace 43cf28060d708d5f ]---
Kernel panic - not syncing: Fatal exception
Dumping ftrace buffer:
   (ftrace buffer empty)
Kernel Offset: disabled

Cc: <stable@vger.kernel.org>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
2016-01-12 20:47:06 +02:00

216 lines
6.6 KiB
C

/*
* mm/balloon_compaction.c
*
* Common interface for making balloon pages movable by compaction.
*
* Copyright (C) 2012, Red Hat, Inc. Rafael Aquini <aquini@redhat.com>
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/balloon_compaction.h>
/*
* balloon_page_enqueue - allocates a new page and inserts it into the balloon
* page list.
* @b_dev_info: balloon device decriptor where we will insert a new page to
*
* Driver must call it to properly allocate a new enlisted balloon page
* before definetively removing it from the guest system.
* This function returns the page address for the recently enqueued page or
* NULL in the case we fail to allocate a new page this turn.
*/
struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
{
unsigned long flags;
struct page *page = alloc_page(balloon_mapping_gfp_mask() |
__GFP_NOMEMALLOC | __GFP_NORETRY);
if (!page)
return NULL;
/*
* Block others from accessing the 'page' when we get around to
* establishing additional references. We should be the only one
* holding a reference to the 'page' at this point.
*/
BUG_ON(!trylock_page(page));
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
balloon_page_insert(b_dev_info, page);
__count_vm_event(BALLOON_INFLATE);
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
unlock_page(page);
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_enqueue);
/*
* balloon_page_dequeue - removes a page from balloon's page list and returns
* the its address to allow the driver release the page.
* @b_dev_info: balloon device decriptor where we will grab a page from.
*
* Driver must call it to properly de-allocate a previous enlisted balloon page
* before definetively releasing it back to the guest system.
* This function returns the page address for the recently dequeued page or
* NULL in the case we find balloon's page list temporarily empty due to
* compaction isolated pages.
*/
struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
{
struct page *page, *tmp;
unsigned long flags;
bool dequeued_page;
dequeued_page = false;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
/*
* Block others from accessing the 'page' while we get around
* establishing additional references and preparing the 'page'
* to be released by the balloon driver.
*/
if (trylock_page(page)) {
#ifdef CONFIG_BALLOON_COMPACTION
if (!PagePrivate(page)) {
/* raced with isolation */
unlock_page(page);
continue;
}
#endif
balloon_page_delete(page);
__count_vm_event(BALLOON_DEFLATE);
unlock_page(page);
dequeued_page = true;
break;
}
}
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
if (!dequeued_page) {
/*
* If we are unable to dequeue a balloon page because the page
* list is empty and there is no isolated pages, then something
* went out of track and some balloon pages are lost.
* BUG() here, otherwise the balloon driver may get stuck into
* an infinite loop while attempting to release all its pages.
*/
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
if (unlikely(list_empty(&b_dev_info->pages) &&
!b_dev_info->isolated_pages))
BUG();
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
page = NULL;
}
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_dequeue);
#ifdef CONFIG_BALLOON_COMPACTION
static inline void __isolate_balloon_page(struct page *page)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
ClearPagePrivate(page);
list_del(&page->lru);
b_dev_info->isolated_pages++;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
static inline void __putback_balloon_page(struct page *page)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
SetPagePrivate(page);
list_add(&page->lru, &b_dev_info->pages);
b_dev_info->isolated_pages--;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
/* __isolate_lru_page() counterpart for a ballooned page */
bool balloon_page_isolate(struct page *page)
{
/*
* Avoid burning cycles with pages that are yet under __free_pages(),
* or just got freed under us.
*
* In case we 'win' a race for a balloon page being freed under us and
* raise its refcount preventing __free_pages() from doing its job
* the put_page() at the end of this block will take care of
* release this page, thus avoiding a nasty leakage.
*/
if (likely(get_page_unless_zero(page))) {
/*
* As balloon pages are not isolated from LRU lists, concurrent
* compaction threads can race against page migration functions
* as well as race against the balloon driver releasing a page.
*
* In order to avoid having an already isolated balloon page
* being (wrongly) re-isolated while it is under migration,
* or to avoid attempting to isolate pages being released by
* the balloon driver, lets be sure we have the page lock
* before proceeding with the balloon page isolation steps.
*/
if (likely(trylock_page(page))) {
/*
* A ballooned page, by default, has PagePrivate set.
* Prevent concurrent compaction threads from isolating
* an already isolated balloon page by clearing it.
*/
if (balloon_page_movable(page)) {
__isolate_balloon_page(page);
unlock_page(page);
return true;
}
unlock_page(page);
}
put_page(page);
}
return false;
}
/* putback_lru_page() counterpart for a ballooned page */
void balloon_page_putback(struct page *page)
{
/*
* 'lock_page()' stabilizes the page and prevents races against
* concurrent isolation threads attempting to re-isolate it.
*/
lock_page(page);
if (__is_movable_balloon_page(page)) {
__putback_balloon_page(page);
/* drop the extra ref count taken for page isolation */
put_page(page);
} else {
WARN_ON(1);
dump_page(page, "not movable balloon page");
}
unlock_page(page);
}
/* move_to_new_page() counterpart for a ballooned page */
int balloon_page_migrate(struct page *newpage,
struct page *page, enum migrate_mode mode)
{
struct balloon_dev_info *balloon = balloon_page_device(page);
int rc = -EAGAIN;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
if (WARN_ON(!__is_movable_balloon_page(page))) {
dump_page(page, "not movable balloon page");
return rc;
}
if (balloon && balloon->migratepage)
rc = balloon->migratepage(balloon, newpage, page, mode);
return rc;
}
#endif /* CONFIG_BALLOON_COMPACTION */