From b3bebe44306e23827397d0d774d206e3fa374041 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 17 Jul 2024 14:28:44 -0700 Subject: alloc_tag: outline and export free_reserved_page() Outline and export free_reserved_page() because modules use it and it in turn uses page_ext_{get|put} which should not be exported. The same result could be obtained by outlining {get|put}_page_tag_ref() but that would have higher performance impact as these functions are used in more performance critical paths. Link: https://lkml.kernel.org/r/20240717212844.2749975-1-surenb@google.com Fixes: dcfe378c81f7 ("lib: introduce support for page allocation tagging") Signed-off-by: Suren Baghdasaryan Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202407080044.DWMC9N9I-lkp@intel.com/ Suggested-by: Christoph Hellwig Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Cc: Kees Cook Cc: Kent Overstreet Cc: Pasha Tatashin Cc: Sourav Panda Cc: [6.10] Signed-off-by: Andrew Morton --- mm/page_alloc.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8337926b89d4..7ac8d61148fe 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5815,6 +5815,23 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char return pages; } +void free_reserved_page(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } + ClearPageReserved(page); + init_page_count(page); + __free_page(page); + adjust_managed_page_count(page, 1); +} +EXPORT_SYMBOL(free_reserved_page); + static int page_alloc_cpu_dead(unsigned int cpu) { struct zone *zone; -- cgit v1.2.3 From 66eca1021a42856d6af2a9802c99e160278aed91 Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Tue, 23 Jul 2024 14:44:28 +0800 Subject: mm/page_alloc: fix pcp->count race between drain_pages_zone() vs __rmqueue_pcplist() It's expected that no page should be left in pcp_list after calling zone_pcp_disable() in offline_pages(). Previously, it's observed that offline_pages() gets stuck [1] due to some pages remaining in pcp_list. Cause: There is a race condition between drain_pages_zone() and __rmqueue_pcplist() involving the pcp->count variable. See below scenario: CPU0 CPU1 ---------------- --------------- spin_lock(&pcp->lock); __rmqueue_pcplist() { zone_pcp_disable() { /* list is empty */ if (list_empty(list)) { /* add pages to pcp_list */ alloced = rmqueue_bulk() mutex_lock(&pcp_batch_high_lock) ... __drain_all_pages() { drain_pages_zone() { /* read pcp->count, it's 0 here */ count = READ_ONCE(pcp->count) /* 0 means nothing to drain */ /* update pcp->count */ pcp->count += alloced << order; ... ... spin_unlock(&pcp->lock); In this case, after calling zone_pcp_disable() though, there are still some pages in pcp_list. And these pages in pcp_list are neither movable nor isolated, offline_pages() gets stuck as a result. Solution: Expand the scope of the pcp->lock to also protect pcp->count in drain_pages_zone(), to ensure no pages are left in the pcp list after zone_pcp_disable() [1] https://lore.kernel.org/linux-mm/6a07125f-e720-404c-b2f9-e55f3f166e85@fujitsu.com/ Link: https://lkml.kernel.org/r/20240723064428.1179519-1-lizhijian@fujitsu.com Fixes: 4b23a68f9536 ("mm/page_alloc: protect PCP lists with a spinlock") Signed-off-by: Li Zhijian Reported-by: Yao Xingtao Reviewed-by: Vlastimil Babka Cc: David Hildenbrand Cc: Signed-off-by: Andrew Morton --- mm/page_alloc.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7ac8d61148fe..28f80daf5c04 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2343,16 +2343,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - int count = READ_ONCE(pcp->count); - - while (count) { - int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); - count -= to_drain; + int count; + do { spin_lock(&pcp->lock); - free_pcppages_bulk(zone, to_drain, pcp, 0); + count = pcp->count; + if (count) { + int to_drain = min(count, + pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); + + free_pcppages_bulk(zone, to_drain, pcp, 0); + count -= to_drain; + } spin_unlock(&pcp->lock); - } + } while (count); } /* -- cgit v1.2.3