From 71f2a2c4ff62c9bb1daa0e47b588220178a5ad12 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Mon, 14 Jul 2025 09:16:53 -0400 Subject: [PATCH] proc: kpagecount: use snapshot_page() Currently, the call to folio_precise_page_mapcount() from kpage_read() can race with a folio split. When the race happens we trigger a VM_BUG_ON_FOLIO() in folio_entire_mapcount() (see splat below). This commit fixes this race by using snapshot_page() so that we retrieve the folio mapcount using a folio snapshot. [ 2356.558576] page: refcount:1 mapcount:1 mapping:0000000000000000 index:0xffff85200 pfn:0x6f7c00 [ 2356.558748] memcg:ffff000651775780 [ 2356.558763] anon flags: 0xafffff60020838(uptodate|dirty|lru|owner_2|swapbacked|node=1|zone=2|lastcpupid=0xfffff) [ 2356.558796] raw: 00afffff60020838 fffffdffdb5d0048 fffffdffdadf7fc8 ffff00064c1629c1 [ 2356.558817] raw: 0000000ffff85200 0000000000000000 0000000100000000 ffff000651775780 [ 2356.558839] page dumped because: VM_BUG_ON_FOLIO(!folio_test_large(folio)) [ 2356.558882] ------------[ cut here ]------------ [ 2356.558897] kernel BUG at ./include/linux/mm.h:1103! [ 2356.558982] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP [ 2356.564729] CPU: 8 UID: 0 PID: 1864 Comm: folio-split-rac Tainted: G S W 6.15.0+ #3 PREEMPT(voluntary) [ 2356.566196] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 2356.566814] Hardware name: Red Hat KVM, BIOS edk2-20241117-3.el9 11/17/2024 [ 2356.567684] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 2356.568563] pc : kpage_read.constprop.0+0x26c/0x290 [ 2356.569605] lr : kpage_read.constprop.0+0x26c/0x290 [ 2356.569992] sp : ffff80008fb739b0 [ 2356.570263] x29: ffff80008fb739b0 x28: ffff00064aa69580 x27: 00000000ff000000 [ 2356.570842] x26: 0000fffffffffff8 x25: ffff00064aa69580 x24: ffff80008fb73ae0 [ 2356.571411] x23: 0000000000000001 x22: 0000ffff86c6e8b8 x21: 0000000000000008 [ 2356.571978] x20: 00000000006f7c00 x19: 0000ffff86c6e8b8 x18: 0000000000000000 [ 2356.572581] x17: 3630303066666666 x16: 0000000000000003 x15: 0000000000001000 [ 2356.573217] x14: 00000000ffffffff x13: 0000000000000004 x12: 00aaaaaa00aaaaaa [ 2356.577674] x11: 0000000000000000 x10: 00aaaaaa00aaaaaa x9 : ffffbf3afca6c300 [ 2356.578332] x8 : 0000000000000002 x7 : 0000000000000001 x6 : 0000000000000001 [ 2356.578984] x5 : ffff000c79812408 x4 : 0000000000000000 x3 : 0000000000000000 [ 2356.579635] x2 : 0000000000000000 x1 : ffff00064aa69580 x0 : 000000000000003e [ 2356.580286] Call trace: [ 2356.580524] kpage_read.constprop.0+0x26c/0x290 (P) [ 2356.580982] kpagecount_read+0x28/0x40 [ 2356.581336] proc_reg_read+0x38/0x100 [ 2356.581681] vfs_read+0xcc/0x320 [ 2356.581992] ksys_read+0x74/0x118 [ 2356.582306] __arm64_sys_read+0x24/0x38 [ 2356.582668] invoke_syscall+0x70/0x100 [ 2356.583022] el0_svc_common.constprop.0+0x48/0xf8 [ 2356.583456] do_el0_svc+0x28/0x40 [ 2356.583930] el0_svc+0x38/0x118 [ 2356.584328] el0t_64_sync_handler+0x144/0x168 [ 2356.584883] el0t_64_sync+0x19c/0x1a0 [ 2356.585350] Code: aa0103e0 9003a541 91082021 97f813fc (d4210000) [ 2356.586130] ---[ end trace 0000000000000000 ]--- [ 2356.587377] note: folio-split-rac[1864] exited with irqs disabled [ 2356.588050] note: folio-split-rac[1864] exited with preempt_count 1 Link: https://lkml.kernel.org/r/1c05cc725b90962d56323ff2e28e9cc3ae397b68.1752499009.git.luizcap@redhat.com Signed-off-by: Luiz Capitulino Reported-by: syzbot+3d7dc5eaba6b932f8535@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/67812fbd.050a0220.d0267.0030.GAE@google.com/Reviewed-by: Shivank Garg Tested-by: Harry Yoo Acked-by: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Oscar Salvador Cc: SeongJae Park Signed-off-by: Andrew Morton --- fs/proc/page.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/fs/proc/page.c b/fs/proc/page.c index 0cdc78c0d23fa..21e69935c28b9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -43,6 +43,22 @@ static inline unsigned long get_max_dump_pfn(void) #endif } +static u64 get_kpage_count(const struct page *page) +{ + struct page_snapshot ps; + u64 ret; + + snapshot_page(&ps, page); + + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) + ret = folio_precise_page_mapcount(&ps.folio_snapshot, + &ps.page_snapshot); + else + ret = folio_average_page_mapcount(&ps.folio_snapshot); + + return ret; +} + static ssize_t kpage_read(struct file *file, char __user *buf, size_t count, loff_t *ppos, enum kpage_operation op) @@ -75,10 +91,7 @@ static ssize_t kpage_read(struct file *file, char __user *buf, info = stable_page_flags(page); break; case KPAGE_COUNT: - if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) - info = folio_precise_page_mapcount(page_folio(page), page); - else - info = folio_average_page_mapcount(page_folio(page)); + info = get_kpage_count(page); break; case KPAGE_CGROUP: info = page_cgroup_ino(page); -- 2.47.2