From aad5f69bc161af489dbb5934868bd347282f0764 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 18 Oct 2019 20:19:20 -0700 Subject: fs/proc/page.c: don't access uninitialized memmaps in fs/proc/page.c There are three places where we access uninitialized memmaps, namely: - /proc/kpagecount - /proc/kpageflags - /proc/kpagecgroup We have initialized memmaps either when the section is online or when the page was initialized to the ZONE_DEVICE. Uninitialized memmaps contain garbage and in the worst case trigger kernel BUGs, especially with CONFIG_PAGE_POISONING. For example, not onlining a DIMM during boot and calling /proc/kpagecount with CONFIG_PAGE_POISONING: :/# cat /proc/kpagecount > tmp.test BUG: unable to handle page fault for address: fffffffffffffffe #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 114616067 P4D 114616067 PUD 114618067 PMD 0 Oops: 0000 [#1] SMP NOPTI CPU: 0 PID: 469 Comm: cat Not tainted 5.4.0-rc1-next-20191004+ #11 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.4 RIP: 0010:kpagecount_read+0xce/0x1e0 Code: e8 09 83 e0 3f 48 0f a3 02 73 2d 4c 89 e7 48 c1 e7 06 48 03 3d ab 51 01 01 74 1d 48 8b 57 08 480 RSP: 0018:ffffa14e409b7e78 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 0000000000020000 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 00007f76b5595000 RDI: fffff35645000000 RBP: 00007f76b5595000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000140000 R13: 0000000000020000 R14: 00007f76b5595000 R15: ffffa14e409b7f08 FS: 00007f76b577d580(0000) GS:ffff8f41bd400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 0000000078960000 CR4: 00000000000006f0 Call Trace: proc_reg_read+0x3c/0x60 vfs_read+0xc5/0x180 ksys_read+0x68/0xe0 do_syscall_64+0x5c/0xa0 entry_SYSCALL_64_after_hwframe+0x49/0xbe For now, let's drop support for ZONE_DEVICE from the three pseudo files in order to fix this. To distinguish offline memory (with garbage memmap) from ZONE_DEVICE memory with properly initialized memmaps, we would have to check get_dev_pagemap() and pfn_zone_device_reserved() right now. The usage of both (especially, special casing devmem) is frowned upon and needs to be reworked. The fundamental issue we have is: if (pfn_to_online_page(pfn)) { /* memmap initialized */ } else if (pfn_valid(pfn)) { /* * ??? * a) offline memory. memmap garbage. * b) devmem: memmap initialized to ZONE_DEVICE. * c) devmem: reserved for driver. memmap garbage. * (d) devmem: memmap currently initializing - garbage) */ } We'll leave the pfn_zone_device_reserved() check in stable_page_flags() in place as that function is also used from memory failure. We now no longer dump information about pages that are not in use anymore - offline. Link: http://lkml.kernel.org/r/20191009142435.3975-2-david@redhat.com Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") [visible after d0dc12e86b319] Signed-off-by: David Hildenbrand Reported-by: Qian Cai Acked-by: Michal Hocko Cc: Dan Williams Cc: Alexey Dobriyan Cc: Stephen Rothwell Cc: Toshiki Fukasawa Cc: Pankaj gupta Cc: Mike Rapoport Cc: Anthony Yznaga Cc: "Aneesh Kumar K.V" Cc: [4.13+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/page.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/page.c b/fs/proc/page.c index 544d1ee15aee..7c952ee732e6 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); + if (!ppage || PageSlab(ppage) || page_has_type(ppage)) pcount = 0; else @@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (put_user(stable_page_flags(ppage), out)) { ret = -EFAULT; @@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (ppage) ino = page_cgroup_ino(ppage); -- cgit v1.2.3-59-g8ed1b