diff options
| author | Kirill A. Shutemov <kirill.shutemov@linux.intel.com> | 2025-05-06 16:32:07 +0300 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2025-05-22 14:12:24 +0200 |
| commit | 98fdd2f612e949c652693f6df00442c81037776d (patch) | |
| tree | 594700cc751496fa3a66571e17bde929a32cae8a /mm | |
| parent | e24073cd8f169678555e8e2e2322fe6a2987e3c5 (diff) | |
| download | linux-98fdd2f612e949c652693f6df00442c81037776d.tar.gz linux-98fdd2f612e949c652693f6df00442c81037776d.tar.bz2 linux-98fdd2f612e949c652693f6df00442c81037776d.zip | |
mm/page_alloc: fix race condition in unaccepted memory handling
commit fefc075182275057ce607effaa3daa9e6e3bdc73 upstream.
The page allocator tracks the number of zones that have unaccepted memory
using static_branch_enc/dec() and uses that static branch in hot paths to
determine if it needs to deal with unaccepted memory.
Borislav and Thomas pointed out that the tracking is racy: operations on
static_branch are not serialized against adding/removing unaccepted pages
to/from the zone.
Sanity checks inside static_branch machinery detects it:
WARNING: CPU: 0 PID: 10 at kernel/jump_label.c:276 __static_key_slow_dec_cpuslocked+0x8e/0xa0
The comment around the WARN() explains the problem:
/*
* Warn about the '-1' case though; since that means a
* decrement is concurrent with a first (0->1) increment. IOW
* people are trying to disable something that wasn't yet fully
* enabled. This suggests an ordering problem on the user side.
*/
The effect of this static_branch optimization is only visible on
microbenchmark.
Instead of adding more complexity around it, remove it altogether.
Link: https://lkml.kernel.org/r/20250506133207.1009676-1-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory")
Link: https://lore.kernel.org/all/20250506092445.GBaBnVXXyvnazly6iF@fat_crate.local
Reported-by: Borislav Petkov <bp@alien8.de>
Tested-by: Borislav Petkov (AMD) <bp@alien8.de>
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org> [6.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/page_alloc.c | 27 |
1 files changed, 0 insertions, 27 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bc62bb2a3b13..74737c35082b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -303,7 +303,6 @@ EXPORT_SYMBOL(nr_online_nodes); static bool page_contains_unaccepted(struct page *page, unsigned int order); static void accept_page(struct page *page, unsigned int order); static bool cond_accept_memory(struct zone *zone, unsigned int order); -static inline bool has_unaccepted_memory(void); static bool __free_unaccepted(struct page *page); int page_group_by_mobility_disabled __read_mostly; @@ -6586,9 +6585,6 @@ bool has_managed_dma(void) #ifdef CONFIG_UNACCEPTED_MEMORY -/* Counts number of zones with unaccepted pages. */ -static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); - static bool lazy_accept = true; static int __init accept_memory_parse(char *p) @@ -6624,7 +6620,6 @@ static bool try_to_accept_memory_one(struct zone *zone) { unsigned long flags; struct page *page; - bool last; spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, @@ -6635,7 +6630,6 @@ static bool try_to_accept_memory_one(struct zone *zone) } list_del(&page->lru); - last = list_empty(&zone->unaccepted_pages); __mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); @@ -6645,9 +6639,6 @@ static bool try_to_accept_memory_one(struct zone *zone) __free_pages_ok(page, MAX_ORDER, FPI_TO_TAIL); - if (last) - static_branch_dec(&zones_with_unaccepted_pages); - return true; } @@ -6656,9 +6647,6 @@ static bool cond_accept_memory(struct zone *zone, unsigned int order) long to_accept, wmark; bool ret = false; - if (!has_unaccepted_memory()) - return false; - if (list_empty(&zone->unaccepted_pages)) return false; @@ -6688,30 +6676,20 @@ static bool cond_accept_memory(struct zone *zone, unsigned int order) return ret; } -static inline bool has_unaccepted_memory(void) -{ - return static_branch_unlikely(&zones_with_unaccepted_pages); -} - static bool __free_unaccepted(struct page *page) { struct zone *zone = page_zone(page); unsigned long flags; - bool first = false; if (!lazy_accept) return false; spin_lock_irqsave(&zone->lock, flags); - first = list_empty(&zone->unaccepted_pages); list_add_tail(&page->lru, &zone->unaccepted_pages); __mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); spin_unlock_irqrestore(&zone->lock, flags); - if (first) - static_branch_inc(&zones_with_unaccepted_pages); - return true; } @@ -6731,11 +6709,6 @@ static bool cond_accept_memory(struct zone *zone, unsigned int order) return false; } -static inline bool has_unaccepted_memory(void) -{ - return false; -} - static bool __free_unaccepted(struct page *page) { BUILD_BUG(); |
