2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 13:13:57 +08:00
linux-next/mm/balloon_compaction.c
Michael S. Tsirkin c7cdff0e86 virtio_balloon: fix deadlock on OOM
fill_balloon doing memory allocations under balloon_lock
can cause a deadlock when leak_balloon is called from
virtballoon_oom_notify and tries to take same lock.

To fix, split page allocation and enqueue and do allocations outside the lock.

Here's a detailed analysis of the deadlock by Tetsuo Handa:

In leak_balloon(), mutex_lock(&vb->balloon_lock) is called in order to
serialize against fill_balloon(). But in fill_balloon(),
alloc_page(GFP_HIGHUSER[_MOVABLE] | __GFP_NOMEMALLOC | __GFP_NORETRY) is
called with vb->balloon_lock mutex held. Since GFP_HIGHUSER[_MOVABLE]
implies __GFP_DIRECT_RECLAIM | __GFP_IO | __GFP_FS, despite __GFP_NORETRY
is specified, this allocation attempt might indirectly depend on somebody
else's __GFP_DIRECT_RECLAIM memory allocation. And such indirect
__GFP_DIRECT_RECLAIM memory allocation might call leak_balloon() via
virtballoon_oom_notify() via blocking_notifier_call_chain() callback via
out_of_memory() when it reached __alloc_pages_may_oom() and held oom_lock
mutex. Since vb->balloon_lock mutex is already held by fill_balloon(), it
will cause OOM lockup.

  Thread1                                       Thread2
    fill_balloon()
      takes a balloon_lock
      balloon_page_enqueue()
        alloc_page(GFP_HIGHUSER_MOVABLE)
          direct reclaim (__GFP_FS context)       takes a fs lock
            waits for that fs lock                  alloc_page(GFP_NOFS)
                                                      __alloc_pages_may_oom()
                                                        takes the oom_lock
                                                        out_of_memory()
                                                          blocking_notifier_call_chain()
                                                            leak_balloon()
                                                              tries to take that balloon_lock and deadlocks

Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2017-11-14 23:57:38 +02:00

178 lines
5.5 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_alloc - allocates a new page for insertion into the balloon
* page list.
*
* Driver must call it to properly allocate a new enlisted balloon page.
* Driver must call balloon_page_enqueue before definitively removing it from
* the guest system. This function returns the page address for the recently
* allocated page or NULL in the case we fail to allocate a new page this turn.
*/
struct page *balloon_page_alloc(void)
{
struct page *page = alloc_page(balloon_mapping_gfp_mask() |
__GFP_NOMEMALLOC | __GFP_NORETRY);
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_alloc);
/*
* balloon_page_enqueue - allocates a new page and inserts it into the balloon
* page list.
* @b_dev_info: balloon device descriptor where we will insert a new page to
* @page: new page to enqueue - allocated using balloon_page_alloc.
*
* Driver must call it to properly enqueue a new allocated balloon page
* before definitively 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.
*/
void balloon_page_enqueue(struct balloon_dev_info *b_dev_info,
struct page *page)
{
unsigned long flags;
/*
* 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);
}
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 (PageIsolated(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
bool balloon_page_isolate(struct page *page, isolate_mode_t mode)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
list_del(&page->lru);
b_dev_info->isolated_pages++;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
return true;
}
void balloon_page_putback(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);
list_add(&page->lru, &b_dev_info->pages);
b_dev_info->isolated_pages--;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
/* move_to_new_page() counterpart for a ballooned page */
int balloon_page_migrate(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
struct balloon_dev_info *balloon = balloon_page_device(page);
/*
* We can not easily support the no copy case here so ignore it as it
* is unlikely to be use with ballon pages. See include/linux/hmm.h for
* user of the MIGRATE_SYNC_NO_COPY mode.
*/
if (mode == MIGRATE_SYNC_NO_COPY)
return -EINVAL;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
return balloon->migratepage(balloon, newpage, page, mode);
}
const struct address_space_operations balloon_aops = {
.migratepage = balloon_page_migrate,
.isolate_page = balloon_page_isolate,
.putback_page = balloon_page_putback,
};
EXPORT_SYMBOL_GPL(balloon_aops);
#endif /* CONFIG_BALLOON_COMPACTION */