The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to stable@vger.kernel.org.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 807174a93d24c456503692dc3f5af322ee0b640a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to 'stable@vger.kernel.org' --in-reply-to '2024081913-outbid-skincare-1e41@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^..

Possible dependencies:

807174a93d24 ("mm: fix endless reclaim on machines with unaccepted memory") 57c0419c5f0e ("mm, pcp: decrease PCP high if free pages < high watermark") 51a755c56dc0 ("mm: tune PCP high automatically") 90b41691b988 ("mm: add framework for PCP high auto-tuning") c0a242394cb9 ("mm, page_alloc: scale the number of pages that are batch allocated") 52166607ecc9 ("mm: restrict the pcp batch scale factor to avoid too long latency") 362d37a106dd ("mm, pcp: reduce lock contention for draining high-order pages") 94a3bfe4073c ("cacheinfo: calculate size of per-CPU data cache slice") ca71fe1ad922 ("mm, pcp: avoid to drain PCP when process exit")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 807174a93d24c456503692dc3f5af322ee0b640a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com Date: Fri, 9 Aug 2024 14:48:47 +0300 Subject: [PATCH] mm: fix endless reclaim on machines with unaccepted memory

Unaccepted memory is considered unusable free memory, which is not counted as free on the zone watermark check. This causes get_page_from_freelist() to accept more memory to hit the high watermark, but it creates problems in the reclaim path.

The reclaim path encounters a failed zone watermark check and attempts to reclaim memory. This is usually successful, but if there is little or no reclaimable memory, it can result in endless reclaim with little to no progress. This can occur early in the boot process, just after start of the init process when the only reclaimable memory is the page cache of the init executable and its libraries.

Make unaccepted memory free from watermark check point of view. This way unaccepted memory will never be the trigger of memory reclaim. Accept more memory in the get_page_from_freelist() if needed.

Link: https://lkml.kernel.org/r/20240809114854.3745464-2-kirill.shutemov@linux.int... Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory") Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reported-by: Jianxiong Gao jxgao@google.com Acked-by: David Hildenbrand david@redhat.com Tested-by: Jianxiong Gao jxgao@google.com Cc: Borislav Petkov bp@alien8.de Cc: Johannes Weiner hannes@cmpxchg.org Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Matthew Wilcox willy@infradead.org Cc: Mel Gorman mgorman@suse.de Cc: Mike Rapoport (Microsoft) rppt@kernel.org Cc: Tom Lendacky thomas.lendacky@amd.com Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org [6.5+] Signed-off-by: Andrew Morton akpm@linux-foundation.org

diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 875d76e8684a..8747087acee3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -287,7 +287,7 @@ 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 try_to_accept_memory(struct zone *zone, 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);

@@ -3072,9 +3072,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z, if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif -#ifdef CONFIG_UNACCEPTED_MEMORY - unusable_free += zone_page_state(z, NR_UNACCEPTED); -#endif

return unusable_free; } @@ -3368,6 +3365,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, } }

+ cond_accept_memory(zone, order); + /* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free @@ -3393,10 +3392,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, gfp_mask)) { int ret;

- if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -3450,10 +3447,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,

return page; } else { - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ @@ -6950,9 +6945,6 @@ static bool try_to_accept_memory_one(struct zone *zone) struct page *page; bool last;

- if (list_empty(&zone->unaccepted_pages)) - return false; - spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, struct page, lru); @@ -6978,23 +6970,29 @@ static bool try_to_accept_memory_one(struct zone *zone) return true; }

-static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { long to_accept; - int ret = false; + bool ret = false; + + if (!has_unaccepted_memory()) + return false; + + if (list_empty(&zone->unaccepted_pages)) + return false;

/* How much to accept to get to high watermark? */ to_accept = high_wmark_pages(zone) - (zone_page_state(zone, NR_FREE_PAGES) - - __zone_watermark_unusable_free(zone, order, 0)); + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED));

- /* Accept at least one page */ - do { + while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break; ret = true; to_accept -= MAX_ORDER_NR_PAGES; - } while (to_accept > 0); + }

return ret; } @@ -7037,7 +7035,7 @@ static void accept_page(struct page *page, unsigned int order) { }

-static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { return false; }