From 1c8aab376bd636a61b52edec85cc6b8a03e74351 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 19 Jun 2024 11:35:28 +0200 Subject: [PATCH] 6.9-stable patches added patches: mm-huge_memory-don-t-unpoison-huge_zero_folio.patch --- ...emory-don-t-unpoison-huge_zero_folio.patch | 90 +++++++++++++++++++ queue-6.9/series | 1 + 2 files changed, 91 insertions(+) create mode 100644 queue-6.9/mm-huge_memory-don-t-unpoison-huge_zero_folio.patch diff --git a/queue-6.9/mm-huge_memory-don-t-unpoison-huge_zero_folio.patch b/queue-6.9/mm-huge_memory-don-t-unpoison-huge_zero_folio.patch new file mode 100644 index 00000000000..f5337161182 --- /dev/null +++ b/queue-6.9/mm-huge_memory-don-t-unpoison-huge_zero_folio.patch @@ -0,0 +1,90 @@ +From fe6f86f4b40855a130a19aa589f9ba7f650423f4 Mon Sep 17 00:00:00 2001 +From: Miaohe Lin +Date: Thu, 16 May 2024 20:26:08 +0800 +Subject: mm/huge_memory: don't unpoison huge_zero_folio + +From: Miaohe Lin + +commit fe6f86f4b40855a130a19aa589f9ba7f650423f4 upstream. + +When I did memory failure tests recently, below panic occurs: + + kernel BUG at include/linux/mm.h:1135! + invalid opcode: 0000 [#1] PREEMPT SMP NOPTI + CPU: 9 PID: 137 Comm: kswapd1 Not tainted 6.9.0-rc4-00491-gd5ce28f156fe-dirty #14 + RIP: 0010:shrink_huge_zero_page_scan+0x168/0x1a0 + RSP: 0018:ffff9933c6c57bd0 EFLAGS: 00000246 + RAX: 000000000000003e RBX: 0000000000000000 RCX: ffff88f61fc5c9c8 + RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff88f61fc5c9c0 + RBP: ffffcd7c446b0000 R08: ffffffff9a9405f0 R09: 0000000000005492 + R10: 00000000000030ea R11: ffffffff9a9405f0 R12: 0000000000000000 + R13: 0000000000000000 R14: 0000000000000000 R15: ffff88e703c4ac00 + FS: 0000000000000000(0000) GS:ffff88f61fc40000(0000) knlGS:0000000000000000 + CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + CR2: 000055f4da6e9878 CR3: 0000000c71048000 CR4: 00000000000006f0 + Call Trace: + + do_shrink_slab+0x14f/0x6a0 + shrink_slab+0xca/0x8c0 + shrink_node+0x2d0/0x7d0 + balance_pgdat+0x33a/0x720 + kswapd+0x1f3/0x410 + kthread+0xd5/0x100 + ret_from_fork+0x2f/0x50 + ret_from_fork_asm+0x1a/0x30 + + Modules linked in: mce_inject hwpoison_inject + ---[ end trace 0000000000000000 ]--- + RIP: 0010:shrink_huge_zero_page_scan+0x168/0x1a0 + RSP: 0018:ffff9933c6c57bd0 EFLAGS: 00000246 + RAX: 000000000000003e RBX: 0000000000000000 RCX: ffff88f61fc5c9c8 + RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff88f61fc5c9c0 + RBP: ffffcd7c446b0000 R08: ffffffff9a9405f0 R09: 0000000000005492 + R10: 00000000000030ea R11: ffffffff9a9405f0 R12: 0000000000000000 + R13: 0000000000000000 R14: 0000000000000000 R15: ffff88e703c4ac00 + FS: 0000000000000000(0000) GS:ffff88f61fc40000(0000) knlGS:0000000000000000 + CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + CR2: 000055f4da6e9878 CR3: 0000000c71048000 CR4: 00000000000006f0 + +The root cause is that HWPoison flag will be set for huge_zero_folio +without increasing the folio refcnt. But then unpoison_memory() will +decrease the folio refcnt unexpectedly as it appears like a successfully +hwpoisoned folio leading to VM_BUG_ON_PAGE(page_ref_count(page) == 0) when +releasing huge_zero_folio. + +Skip unpoisoning huge_zero_folio in unpoison_memory() to fix this issue. +We're not prepared to unpoison huge_zero_folio yet. + +Link: https://lkml.kernel.org/r/20240516122608.22610-1-linmiaohe@huawei.com +Fixes: 478d134e9506 ("mm/huge_memory: do not overkill when splitting huge_zero_page") +Signed-off-by: Miaohe Lin +Acked-by: David Hildenbrand +Reviewed-by: Yang Shi +Reviewed-by: Oscar Salvador +Reviewed-by: Anshuman Khandual +Cc: Naoya Horiguchi +Cc: Xu Yu +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Miaohe Lin +Signed-off-by: Greg Kroah-Hartman +--- + mm/memory-failure.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/mm/memory-failure.c ++++ b/mm/memory-failure.c +@@ -2550,6 +2550,13 @@ int unpoison_memory(unsigned long pfn) + goto unlock_mutex; + } + ++ if (is_huge_zero_page(&folio->page)) { ++ unpoison_pr_info("Unpoison: huge zero page is not supported %#lx\n", ++ pfn, &unpoison_rs); ++ ret = -EOPNOTSUPP; ++ goto unlock_mutex; ++ } ++ + if (!PageHWPoison(p)) { + unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", + pfn, &unpoison_rs); diff --git a/queue-6.9/series b/queue-6.9/series index e6cb57da20e..f6b672e3f52 100644 --- a/queue-6.9/series +++ b/queue-6.9/series @@ -274,3 +274,4 @@ pmdomain-ti-sci-fix-duplicate-pd-referrals.patch btrfs-zoned-fix-use-after-free-due-to-race-with-dev-replace.patch wifi-iwlwifi-mvm-support-iwl_dev_tx_power_cmd_v8.patch wifi-iwlwifi-mvm-fix-a-crash-on-7265.patch +mm-huge_memory-don-t-unpoison-huge_zero_folio.patch -- 2.47.3