From 13ddaf26be324a7f951891ecd9ccd04466d27458 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Wed, 7 Feb 2024 02:25:59 +0800 Subject: [PATCH] mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry swap_read_folio() <- read to page A swap_read_folio() <- read to page B ... set_pte_at() swap_free() <- entry is free pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong@tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device") Reported-by: "Huang, Ying" Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel.com/ Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1] Signed-off-by: Kairui Song Reviewed-by: "Huang, Ying" Acked-by: Yu Zhao Acked-by: David Hildenbrand Acked-by: Chris Li Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Minchan Kim Cc: Yosry Ahmed Cc: Yu Zhao Cc: Barry Song <21cnbao@gmail.com> Cc: SeongJae Park Cc: Signed-off-by: Andrew Morton --- include/linux/swap.h | 5 +++++ mm/memory.c | 20 ++++++++++++++++++++ mm/swap.h | 5 +++++ mm/swapfile.c | 13 +++++++++++++ 4 files changed, 43 insertions(+) diff --git a/include/linux/swap.h b/include/linux/swap.h index 4db00ddad261..8d28f6091a32 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } +static inline int swapcache_prepare(swp_entry_t swp) +{ + return 0; +} + static inline void swap_free(swp_entry_t swp) { } diff --git a/mm/memory.c b/mm/memory.c index 15f8b10ea17c..0bfc8b007c01 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; @@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread may + * finish swapin first, free the entry, and swapout + * reusing the same entry. It's undetectable as + * pte_same() returns true due to entry reuse. + */ + if (swapcache_prepare(entry)) { + /* Relax a bit to prevent rapid repeated page faults */ + schedule_timeout_uninterruptible(1); + goto out; + } + need_clear_cache = true; + /* skip swapcache */ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false); @@ -4117,6 +4132,9 @@ unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; @@ -4131,6 +4149,8 @@ out_release: folio_unlock(swapcache); folio_put(swapcache); } + if (need_clear_cache) + swapcache_clear(si, entry); if (si) put_swap_device(si); return ret; diff --git a/mm/swap.h b/mm/swap.h index 758c46ca671e..fc2f6ade7f80 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio, void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); struct folio *filemap_get_incore_folio(struct address_space *mapping, @@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc) return 0; } +static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ +} + static inline struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 556ff7347d5f..746aa9da5302 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry) return __swap_duplicate(entry, SWAP_HAS_CACHE); } +void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + unsigned char usage; + + ci = lock_cluster_or_swap_info(si, offset); + usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); + unlock_cluster_or_swap_info(si, ci); + if (!usage) + free_swap_slot(entry); +} + struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry));