From 139b6a6fb1539e04b01663d61baff3088c63dbb5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 6 May 2014 12:50:05 -0700 Subject: mm: filemap: update find_get_pages_tag() to deal with shadow entries Dave Jones reports the following crash when find_get_pages_tag() runs into an exceptional entry: kernel BUG at mm/filemap.c:1347! RIP: find_get_pages_tag+0x1cb/0x220 Call Trace: find_get_pages_tag+0x36/0x220 pagevec_lookup_tag+0x21/0x30 filemap_fdatawait_range+0xbe/0x1e0 filemap_fdatawait+0x27/0x30 sync_inodes_sb+0x204/0x2a0 sync_inodes_one_sb+0x19/0x20 iterate_supers+0xb2/0x110 sys_sync+0x44/0xb0 ia32_do_call+0x13/0x13 1343 /* 1344 * This function is never used on a shmem/tmpfs 1345 * mapping, so a swap entry won't be found here. 1346 */ 1347 BUG(); After commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") this comment and BUG() are out of date because exceptional entries can now appear in all mappings - as shadows of recently evicted pages. However, as Hugh Dickins notes, "it is truly surprising for a PAGECACHE_TAG_WRITEBACK (and probably any other PAGECACHE_TAG_*) to appear on an exceptional entry. I expect it comes down to an occasional race in RCU lookup of the radix_tree: lacking absolute synchronization, we might sometimes catch an exceptional entry, with the tag which really belongs with the unexceptional entry which was there an instant before." And indeed, not only is the tree walk lockless, the tags are also read in chunks, one radix tree node at a time. There is plenty of time for page reclaim to swoop in and replace a page that was already looked up as tagged with a shadow entry. Remove the BUG() and update the comment. While reviewing all other lookup sites for whether they properly deal with shadow entries of evicted pages, update all the comments and fix memcg file charge moving to not miss shmem/tmpfs swapcache pages. Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees") Signed-off-by: Johannes Weiner Reported-by: Dave Jones Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 29501f040568..c47dffdcb246 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6686,16 +6686,20 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, pgoff = pte_to_pgoff(ptent); /* page is moved even if it's not RSS of this task(page-faulted). */ - page = find_get_page(mapping, pgoff); - #ifdef CONFIG_SWAP /* shmem/tmpfs may report page out on swap: account for that too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - if (do_swap_account) - *entry = swap; - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + if (do_swap_account) + *entry = swp; + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif return page; } -- cgit v1.2.3 From 6f6acb00514c10be35529402f36ad7a288f08c2e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 22 May 2014 11:54:19 -0700 Subject: memcg: fix swapcache charge from kernel thread context Commit 284f39afeaa4 ("mm: memcg: push !mm handling out to page cache charge function") explicitly checks for page cache charges without any mm context (from kernel thread context[1]). This seemed to be the only possible case where memory could be charged without mm context so commit 03583f1a631c ("memcg: remove unnecessary !mm check from try_get_mem_cgroup_from_mm()") removed the mm check from get_mem_cgroup_from_mm(). This however caused another NULL ptr dereference during early boot when loopback kernel thread splices to tmpfs as reported by Stephan Kulow: BUG: unable to handle kernel NULL pointer dereference at 0000000000000360 IP: get_mem_cgroup_from_mm.isra.42+0x2b/0x60 Oops: 0000 [#1] SMP Modules linked in: btrfs dm_multipath dm_mod scsi_dh multipath raid10 raid456 async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 md_mod parport_pc parport nls_utf8 isofs usb_storage iscsi_ibft iscsi_boot_sysfs arc4 ecb fan thermal nfs lockd fscache nls_iso8859_1 nls_cp437 sg st hid_generic usbhid af_packet sunrpc sr_mod cdrom ata_generic uhci_hcd virtio_net virtio_blk ehci_hcd usbcore ata_piix floppy processor button usb_common virtio_pci virtio_ring virtio edd squashfs loop ppa] CPU: 0 PID: 97 Comm: loop1 Not tainted 3.15.0-rc5-5-default #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Call Trace: __mem_cgroup_try_charge_swapin+0x40/0xe0 mem_cgroup_charge_file+0x8b/0xd0 shmem_getpage_gfp+0x66b/0x7b0 shmem_file_splice_read+0x18f/0x430 splice_direct_to_actor+0xa2/0x1c0 do_lo_receive+0x5a/0x60 [loop] loop_thread+0x298/0x720 [loop] kthread+0xc6/0xe0 ret_from_fork+0x7c/0xb0 Also Branimir Maksimovic reported the following oops which is tiggered for the swapcache charge path from the accounting code for kernel threads: CPU: 1 PID: 160 Comm: kworker/u8:5 Tainted: P OE 3.15.0-rc5-core2-custom #159 Hardware name: System manufacturer System Product Name/MAXIMUSV GENE, BIOS 1903 08/19/2013 task: ffff880404e349b0 ti: ffff88040486a000 task.ti: ffff88040486a000 RIP: get_mem_cgroup_from_mm.isra.42+0x2b/0x60 Call Trace: __mem_cgroup_try_charge_swapin+0x45/0xf0 mem_cgroup_charge_file+0x9c/0xe0 shmem_getpage_gfp+0x62c/0x770 shmem_write_begin+0x38/0x40 generic_perform_write+0xc5/0x1c0 __generic_file_aio_write+0x1d1/0x3f0 generic_file_aio_write+0x4f/0xc0 do_sync_write+0x5a/0x90 do_acct_process+0x4b1/0x550 acct_process+0x6d/0xa0 do_exit+0x827/0xa70 kthread+0xc3/0xf0 This patch fixes the issue by reintroducing mm check into get_mem_cgroup_from_mm. We could do the same trick in __mem_cgroup_try_charge_swapin as we do for the regular page cache path but it is not worth troubles. The check is not that expensive and it is better to have get_mem_cgroup_from_mm more robust. [1] - http://marc.info/?l=linux-mm&m=139463617808941&w=2 Fixes: 03583f1a631c ("memcg: remove unnecessary !mm check from try_get_mem_cgroup_from_mm()") Reported-and-tested-by: Stephan Kulow Reported-by: Branimir Maksimovic Signed-off-by: Michal Hocko Acked-by: Johannes Weiner Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c47dffdcb246..5177c6d4a2dd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1077,9 +1077,18 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) rcu_read_lock(); do { - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) + /* + * Page cache insertions can happen withou an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + */ + if (unlikely(!mm)) memcg = root_mem_cgroup; + else { + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + memcg = root_mem_cgroup; + } } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; @@ -3958,17 +3967,9 @@ int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, return 0; } - /* - * Page cache insertions can happen without an actual mm - * context, e.g. during disk probing on boot. - */ - if (unlikely(!mm)) - memcg = root_mem_cgroup; - else { - memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); - if (!memcg) - return -ENOMEM; - } + memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true); + if (!memcg) + return -ENOMEM; __mem_cgroup_commit_charge(memcg, page, 1, type, false); return 0; } -- cgit v1.2.3