From a05dd8ae5cbb1cb45f349922cfea4f548a5e5d6f Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 10 Jun 2025 01:17:51 +0800 Subject: [PATCH] mm/shmem, swap: fix softlockup with mTHP swapin MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Following softlockup can be easily reproduced on my test machine with: echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled swapon /dev/zram0 # zram0 is a 48G swap device mkdir -p /sys/fs/cgroup/memory/test echo 1G > /sys/fs/cgroup/test/memory.max echo $BASHPID > /sys/fs/cgroup/test/cgroup.procs while true; do dd if=/dev/zero of=/tmp/test.img bs=1M count=5120 cat /tmp/test.img > /dev/null rm /tmp/test.img done Then after a while: watchdog: BUG: soft lockup - CPU#0 stuck for 763s! [cat:5787] Modules linked in: zram virtiofs CPU: 0 UID: 0 PID: 5787 Comm: cat Kdump: loaded Tainted: G L 6.15.0.orig-gf3021d9246bc-dirty #118 PREEMPT(voluntary)· Tainted: [L]=SOFTLOCKUP Hardware name: Red Hat KVM/RHEL-AV, BIOS 0.0.0 02/06/2015 RIP: 0010:mpol_shared_policy_lookup+0xd/0x70 Code: e9 b8 b4 ff ff 31 c0 c3 cc cc cc cc 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 41 54 55 53 <48> 8b 1f 48 85 db 74 41 4c 8d 67 08 48 89 fb 48 89 f5 4c 89 e7 e8 RSP: 0018:ffffc90002b1fc28 EFLAGS: 00000202 RAX: 00000000001c20ca RBX: 0000000000724e1e RCX: 0000000000000001 RDX: ffff888118e214c8 RSI: 0000000000057d42 RDI: ffff888118e21518 RBP: 000000000002bec8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000bf4 R11: 0000000000000000 R12: 0000000000000001 R13: 00000000001c20ca R14: 00000000001c20ca R15: 0000000000000000 FS: 00007f03f995c740(0000) GS:ffff88a07ad9a000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f03f98f1000 CR3: 0000000144626004 CR4: 0000000000770eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: shmem_alloc_folio+0x31/0xc0 shmem_swapin_folio+0x309/0xcf0 ? filemap_get_entry+0x117/0x1e0 ? xas_load+0xd/0xb0 ? filemap_get_entry+0x101/0x1e0 shmem_get_folio_gfp+0x2ed/0x5b0 shmem_file_read_iter+0x7f/0x2e0 vfs_read+0x252/0x330 ksys_read+0x68/0xf0 do_syscall_64+0x4c/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f03f9a46991 Code: 00 48 8b 15 81 14 10 00 f7 d8 64 89 02 b8 ff ff ff ff eb bd e8 20 ad 01 00 f3 0f 1e fa 80 3d 35 97 10 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 4f c3 66 0f 1f 44 00 00 55 48 89 e5 48 83 ec RSP: 002b:00007fff3c52bd28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000040000 RCX: 00007f03f9a46991 RDX: 0000000000040000 RSI: 00007f03f98ba000 RDI: 0000000000000003 RBP: 00007fff3c52bd50 R08: 0000000000000000 R09: 00007f03f9b9a380 R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000040000 R13: 00007f03f98ba000 R14: 0000000000000003 R15: 0000000000000000 The reason is simple, readahead brought some order 0 folio in swap cache, and the swapin mTHP folio being allocated is in conflict with it, so swapcache_prepare fails and causes shmem_swap_alloc_folio to return -EEXIST, and shmem simply retries again and again causing this loop. Fix it by applying a similar fix for anon mTHP swapin. The performance change is very slight, time of swapin 10g zero folios with shmem (test for 12 times): Before: 2.47s After: 2.48s [kasong@tencent.com: add comment] Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20250609171751.36305-1-ryncsn@gmail.com Fixes: 1dd44c0af4fa ("mm: shmem: skip swapcache for swapin of synchronous swap device") Signed-off-by: Kairui Song Reviewed-by: Barry Song Acked-by: Nhat Pham Reviewed-by: Baolin Wang Cc: Baoquan He Cc: Chris Li Cc: Hugh Dickins Cc: Kemeng Shi Cc: Usama Arif Cc: Signed-off-by: Andrew Morton --- mm/memory.c | 20 -------------------- mm/shmem.c | 6 +++++- mm/swap.h | 23 +++++++++++++++++++++++ 3 files changed, 28 insertions(+), 21 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 8eba595056fe..b0cda5aab398 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) -{ - struct swap_info_struct *si = swp_swap_info(entry); - pgoff_t offset = swp_offset(entry); - int i; - - /* - * While allocating a large folio and doing swap_read_folio, which is - * the case the being faulted pte doesn't have swapcache. We need to - * ensure all PTEs have no cache as well, otherwise, we might go to - * swap devices while the content is in swapcache. - */ - for (i = 0; i < max_nr; i++) { - if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) - return i; - } - - return i; -} - /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. diff --git a/mm/shmem.c b/mm/shmem.c index 0c5fb4ffa03a..3a5a65b1f41a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, folio = swap_cache_get_folio(swap, NULL, 0); order = xa_get_order(&mapping->i_pages, index); if (!folio) { + int nr_pages = 1 << order; bool fallback_order0 = false; /* Or update major stats only when swapin succeeds?? */ @@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, * If uffd is active for the vma, we need per-page fault * fidelity to maintain the uffd semantics, then fallback * to swapin order-0 folio, as well as for zswap case. + * Any existing sub folio in the swap cache also blocks + * mTHP swapin. */ if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) || - !zswap_never_enabled())) + !zswap_never_enabled() || + non_swapcache_batch(swap, nr_pages) != nr_pages)) fallback_order0 = true; /* Skip swapcache for synchronous device. */ diff --git a/mm/swap.h b/mm/swap.h index 2269eb9df0af..9096082a915e 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, return find_next_bit(sis->zeromap, end, start) - start; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + struct swap_info_struct *si = swp_swap_info(entry); + pgoff_t offset = swp_offset(entry); + int i; + + /* + * While allocating a large folio and doing mTHP swapin, we need to + * ensure all entries are not cached, otherwise, the mTHP folio will + * be in conflict with the folio in swap cache. + */ + for (i = 0; i < max_nr; i++) { + if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) + return i; + } + + return i; +} + #else /* CONFIG_SWAP */ struct swap_iocb; static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug) @@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, return 0; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + return 0; +} #endif /* CONFIG_SWAP */ /** -- 2.25.1