From 94b07b6f9e2e996afff7395de6b35f34f4cb10bf Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Thu, 21 Nov 2019 17:53:52 -0800 Subject: Revert "fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()" This reverts commit 56e94ea132bb5c2c1d0b60a6aeb34dcb7d71a53d. Commit 56e94ea132bb ("fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()") introduces a regression that fail to create directory with mount option user_xattr and acl. Actually the reported NULL pointer dereference case can be correctly handled by loc->xl_ops->xlo_add_entry(), so revert it. Link: http://lkml.kernel.org/r/1573624916-83825-1-git-send-email-joseph.qi@linux.alibaba.com Fixes: 56e94ea132bb ("fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()") Signed-off-by: Joseph Qi Reported-by: Thomas Voegtle Acked-by: Changwei Ge Cc: Jia-Ju Bai Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/xattr.c | 56 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 33 insertions(+), 23 deletions(-) diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index d8507972ee13..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1490,6 +1490,18 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc, return loc->xl_ops->xlo_check_space(loc, xi); } +static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash) +{ + loc->xl_ops->xlo_add_entry(loc, name_hash); + loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash); + /* + * We can't leave the new entry's xe_name_offset at zero or + * add_namevalue() will go nuts. We set it to the size of our + * storage so that it can never be less than any other entry. + */ + loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size); +} + static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc, struct ocfs2_xattr_info *xi) { @@ -2121,31 +2133,29 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc, if (rc) goto out; - if (!loc->xl_entry) { - rc = -EINVAL; - goto out; - } - - if (ocfs2_xa_can_reuse_entry(loc, xi)) { - orig_value_size = loc->xl_entry->xe_value_size; - rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); - if (rc) - goto out; - goto alloc_value; - } + if (loc->xl_entry) { + if (ocfs2_xa_can_reuse_entry(loc, xi)) { + orig_value_size = loc->xl_entry->xe_value_size; + rc = ocfs2_xa_reuse_entry(loc, xi, ctxt); + if (rc) + goto out; + goto alloc_value; + } - if (!ocfs2_xattr_is_local(loc->xl_entry)) { - orig_clusters = ocfs2_xa_value_clusters(loc); - rc = ocfs2_xa_value_truncate(loc, 0, ctxt); - if (rc) { - mlog_errno(rc); - ocfs2_xa_cleanup_value_truncate(loc, - "overwriting", - orig_clusters); - goto out; + if (!ocfs2_xattr_is_local(loc->xl_entry)) { + orig_clusters = ocfs2_xa_value_clusters(loc); + rc = ocfs2_xa_value_truncate(loc, 0, ctxt); + if (rc) { + mlog_errno(rc); + ocfs2_xa_cleanup_value_truncate(loc, + "overwriting", + orig_clusters); + goto out; + } } - } - ocfs2_xa_wipe_namevalue(loc); + ocfs2_xa_wipe_namevalue(loc); + } else + ocfs2_xa_add_entry(loc, name_hash); /* * If we get here, we have a blank entry. Fill it. We grow our -- cgit v1.2.3 From 7ce700bf11b5e2cb84e4352bbdf2123a7a239c84 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 21 Nov 2019 17:53:56 -0800 Subject: mm/memory_hotplug: don't access uninitialized memmaps in shrink_zone_span() Let's limit shrinking to !ZONE_DEVICE so we can fix the current code. We should never try to touch the memmap of offline sections where we could have uninitialized memmaps and could trigger BUGs when calling page_to_nid() on poisoned pages. There is no reliable way to distinguish an uninitialized memmap from an initialized memmap that belongs to ZONE_DEVICE, as we don't have anything like SECTION_IS_ONLINE we can use similar to pfn_to_online_section() for !ZONE_DEVICE memory. E.g., set_zone_contiguous() similarly relies on pfn_to_online_section() and will therefore never set a ZONE_DEVICE zone consecutive. Stopping to shrink the ZONE_DEVICE therefore results in no observable changes, besides /proc/zoneinfo indicating different boundaries - something we can totally live with. Before commit d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug"), the memmap was initialized with 0 and the node with the right value. So the zone might be wrong but not garbage. After that commit, both the zone and the node will be garbage when touching uninitialized memmaps. Toshiki reported a BUG (race between delayed initialization of ZONE_DEVICE memmaps without holding the memory hotplug lock and concurrent zone shrinking). https://lkml.org/lkml/2019/11/14/1040 "Iteration of create and destroy namespace causes the panic as below: kernel BUG at mm/page_alloc.c:535! CPU: 7 PID: 2766 Comm: ndctl Not tainted 5.4.0-rc4 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:set_pfnblock_flags_mask+0x95/0xf0 Call Trace: memmap_init_zone_device+0x165/0x17c memremap_pages+0x4c1/0x540 devm_memremap_pages+0x1d/0x60 pmem_attach_disk+0x16b/0x600 [nd_pmem] nvdimm_bus_probe+0x69/0x1c0 really_probe+0x1c2/0x3e0 driver_probe_device+0xb4/0x100 device_driver_attach+0x4f/0x60 bind_store+0xc9/0x110 kernfs_fop_write+0x116/0x190 vfs_write+0xa5/0x1a0 ksys_write+0x59/0xd0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 While creating a namespace and initializing memmap, if you destroy the namespace and shrink the zone, it will initialize the memmap outside the zone and trigger VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page) in set_pfnblock_flags_mask()." This BUG is also mitigated by this commit, where we for now stop to shrink the ZONE_DEVICE zone until we can do it in a safe and clean way. Link: http://lkml.kernel.org/r/20191006085646.5768-5-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: Aneesh Kumar K.V Reported-by: Toshiki Fukasawa Cc: Oscar Salvador Cc: David Hildenbrand Cc: Michal Hocko Cc: Pavel Tatashin Cc: Dan Williams Cc: Alexander Duyck Cc: Alexander Potapenko Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Damian Tometzki Cc: Dave Hansen Cc: Fenghua Yu Cc: Gerald Schaefer Cc: Greg Kroah-Hartman Cc: Halil Pasic Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jun Yao Cc: Logan Gunthorpe Cc: Mark Rutland Cc: Masahiro Yamada Cc: "Matthew Wilcox (Oracle)" Cc: Mel Gorman Cc: Michael Ellerman Cc: Mike Rapoport Cc: Pankaj Gupta Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Qian Cai Cc: Rich Felker Cc: Robin Murphy Cc: Steve Capper Cc: Thomas Gleixner Cc: Tom Lendacky Cc: Tony Luck Cc: Vasily Gorbik Cc: Vlastimil Babka Cc: Wei Yang Cc: Wei Yang Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Cc: [4.13+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3b62a9ff8ea0..f307bd82d750 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -331,7 +331,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long end_pfn) { for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(start_pfn))) + if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) @@ -356,7 +356,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) @@ -415,7 +415,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, */ pfn = zone_start_pfn; for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (page_zone(pfn_to_page(pfn)) != zone) @@ -471,6 +471,16 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); -- cgit v1.2.3 From 9a63236f1ad82d71a98aa80320b6cb618fb32f44 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 21 Nov 2019 17:54:01 -0800 Subject: mm/ksm.c: don't WARN if page is still mapped in remove_stable_node() It's possible to hit the WARN_ON_ONCE(page_mapped(page)) in remove_stable_node() when it races with __mmput() and squeezes in between ksm_exit() and exit_mmap(). WARNING: CPU: 0 PID: 3295 at mm/ksm.c:888 remove_stable_node+0x10c/0x150 Call Trace: remove_all_stable_nodes+0x12b/0x330 run_store+0x4ef/0x7b0 kernfs_fop_write+0x200/0x420 vfs_write+0x154/0x450 ksys_write+0xf9/0x1d0 do_syscall_64+0x99/0x510 entry_SYSCALL_64_after_hwframe+0x49/0xbe Remove the warning as there is nothing scary going on. Link: http://lkml.kernel.org/r/20191119131850.5675-1-aryabinin@virtuozzo.com Fixes: cbf86cfe04a6 ("ksm: remove old stable nodes more thoroughly") Signed-off-by: Andrey Ryabinin Acked-by: Hugh Dickins Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ksm.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/mm/ksm.c b/mm/ksm.c index dbee2eb4dd05..7905934cd3ad 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -885,13 +885,13 @@ static int remove_stable_node(struct stable_node *stable_node) return 0; } - if (WARN_ON_ONCE(page_mapped(page))) { - /* - * This should not happen: but if it does, just refuse to let - * merge_across_nodes be switched - there is no need to panic. - */ - err = -EBUSY; - } else { + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!page_mapped(page)) { /* * The stable node did not yet appear stale to get_ksm_page(), * since that allows for an unmapped ksm page to be recognized -- cgit v1.2.3