From: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> commit 807174a93d24c456503692dc3f5af322ee0b640a upstream. 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@xxxxxxxxxxxxxxx Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory") Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Reported-by: Jianxiong Gao <jxgao@xxxxxxxxxx> Acked-by: David Hildenbrand <david@xxxxxxxxxx> Tested-by: Jianxiong Gao <jxgao@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Mike Rapoport (Microsoft) <rppt@xxxxxxxxxx> Cc: Tom Lendacky <thomas.lendacky@xxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> [6.5+] Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 42 ++++++++++++++++++++---------------------- 1 file changed, 20 insertions(+), 22 deletions(-) --- 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); @@ -3059,9 +3059,6 @@ static inline long __zone_watermark_unus 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; } @@ -3355,6 +3352,8 @@ retry: } } + 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 @@ -3380,10 +3379,8 @@ check_alloc_wmark: 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 /* @@ -3437,10 +3434,8 @@ try_this_zone: 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 */ @@ -6933,9 +6928,6 @@ static bool try_to_accept_memory_one(str 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); @@ -6961,23 +6953,29 @@ static bool try_to_accept_memory_one(str 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; } @@ -7020,7 +7018,7 @@ static void accept_page(struct page *pag { } -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; } Patches currently in stable-queue which might be from kirill.shutemov@xxxxxxxxxxxxxxx are queue-6.10/mm-fix-endless-reclaim-on-machines-with-unaccepted-memory.patch
