From 4067196a52278156d18d8d6fa7f43970611b1b49 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sat, 29 Mar 2025 19:10:29 +0200 Subject: mm/page_alloc: fix deadlock on cpu_hotplug_lock in __accept_page() When the last page in the zone is accepted, __accept_page() calls static_branch_dec(). This function takes cpu_hotplug_lock, which can lead to a deadlock if the allocation occurs during CPU bringup path as _cpu_up() also takes the lock. To prevent this deadlock, defer static_branch_dec() to a workqueue. Call static_branch_dec() only when the workqueue is not yet initialized. Workqueues are initialized before CPU bring up, so this will not conflict with the first scenario. Link: https://lkml.kernel.org/r/20250329171030.3942298-1-kirill.shutemov@linux.intel.com Fixes: 55ad43e8ba0f ("mm: add a helper to accept page") Signed-off-by: Kirill A. Shutemov Reported-by: Srikanth Aithal Tested-by: Srikanth Aithal Cc: Dave Hansen Cc: Ashish Kalra Cc: David Hildenbrand Cc: "Edgecombe, Rick P" Cc: Mel Gorman Cc: "Mike Rapoport (IBM)" Cc: Thomas Lendacky Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/mmzone.h') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 25e80b2ca7f4..4c95fcc9e9df 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -967,6 +967,9 @@ struct zone { #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; + + /* To be called once the last page in the zone is accepted */ + struct work_struct unaccepted_cleanup; #endif /* zone flags, see below */ -- cgit v1.2.3 From 38448181459e24257b40d5258afdbaa3565e8cfc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 16 Apr 2025 09:45:39 -0400 Subject: mm: vmscan: restore high-cpu watermark safety in kswapd Vlastimil points out that commit a211c6550efc ("mm: page_alloc: defrag_mode kswapd/kcompactd watermarks") switched kswapd from zone_watermark_ok_safe() to the standard, percpu-cached version of reading free pages, thus dropping the watermark safety precautions for systems with high CPU counts (e.g. >212 cpus on 64G). Restore them. Since zone_watermark_ok_safe() is no longer the right interface, and this was the last caller of the function anyway, open-code the zone_page_state_snapshot() conditional and delete the function. Link: https://lkml.kernel.org/r/20250416135142.778933-2-hannes@cmpxchg.org Fixes: a211c6550efc ("mm: page_alloc: defrag_mode kswapd/kcompactd watermarks") Signed-off-by: Johannes Weiner Reported-by: Vlastimil Babka Reviewed-by: Vlastimil Babka Cc: Brendan Jackman Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 -- mm/page_alloc.c | 12 ------------ mm/vmscan.c | 21 +++++++++++++++++++-- 3 files changed, 19 insertions(+), 16 deletions(-) (limited to 'include/linux/mmzone.h') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4c95fcc9e9df..6ccec1bf2896 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1502,8 +1502,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); -bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e506e365d6f1..5669baf2a6fe 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3470,18 +3470,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, return false; } -bool zone_watermark_ok_safe(struct zone *z, unsigned int order, - unsigned long mark, int highest_zoneidx) -{ - long free_pages = zone_page_state(z, NR_FREE_PAGES); - - if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark) - free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES); - - return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0, - free_pages); -} - #ifdef CONFIG_NUMA int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; diff --git a/mm/vmscan.c b/mm/vmscan.c index b620d74b0f66..cc422ad830d6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6736,6 +6736,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) * meet watermarks. */ for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) { + enum zone_stat_item item; unsigned long free_pages; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) @@ -6748,9 +6749,25 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) * blocks to avoid polluting allocator fallbacks. */ if (defrag_mode) - free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS); + item = NR_FREE_PAGES_BLOCKS; else - free_pages = zone_page_state(zone, NR_FREE_PAGES); + item = NR_FREE_PAGES; + + /* + * When there is a high number of CPUs in the system, + * the cumulative error from the vmstat per-cpu cache + * can blur the line between the watermarks. In that + * case, be safe and get an accurate snapshot. + * + * TODO: NR_FREE_PAGES_BLOCKS moves in steps of + * pageblock_nr_pages, while the vmstat pcp threshold + * is limited to 125. On many configurations that + * counter won't actually be per-cpu cached. But keep + * things simple for now; revisit when somebody cares. + */ + free_pages = zone_page_state(zone, item); + if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark) + free_pages = zone_page_state_snapshot(zone, item); if (__zone_watermark_ok(zone, order, mark, highest_zoneidx, 0, free_pages)) -- cgit v1.2.3