From c412a769d2452161e97f163c4c4f31efc6626f06 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 28 Mar 2019 20:43:15 -0700 Subject: [PATCH 01/22] kasan: fix variable 'tag' set but not used warning set_tag() compiles away when CONFIG_KASAN_SW_TAGS=n, so make arch_kasan_set_tag() a static inline function to fix warnings below. mm/kasan/common.c: In function '__kasan_kmalloc': mm/kasan/common.c:475:5: warning: variable 'tag' set but not used [-Wunused-but-set-variable] u8 tag; ^~~ Link: http://lkml.kernel.org/r/20190307185244.54648-1-cai@lca.pw Signed-off-by: Qian Cai Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 3e0c11f7d7a1..3ce956efa0cb 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -163,7 +163,10 @@ static inline u8 random_tag(void) #endif #ifndef arch_kasan_set_tag -#define arch_kasan_set_tag(addr, tag) ((void *)(addr)) +static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) +{ + return addr; +} #endif #ifndef arch_kasan_reset_tag #define arch_kasan_reset_tag(addr) ((void *)(addr)) From cae85cb8add35f678cf487139d05e083ce2f570a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 28 Mar 2019 20:43:19 -0700 Subject: [PATCH 02/22] mm/memory.c: fix modifying of page protection by insert_pfn() Aneesh has reported that PPC triggers the following warning when excercising DAX code: IP set_pte_at+0x3c/0x190 LR insert_pfn+0x208/0x280 Call Trace: insert_pfn+0x68/0x280 dax_iomap_pte_fault.isra.7+0x734/0xa40 __xfs_filemap_fault+0x280/0x2d0 do_wp_page+0x48c/0xa40 __handle_mm_fault+0x8d0/0x1fd0 handle_mm_fault+0x140/0x250 __do_page_fault+0x300/0xd60 handle_page_fault+0x18 Now that is WARN_ON in set_pte_at which is VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep)); The problem is that on some architectures set_pte_at() cannot cope with a situation where there is already some (different) valid entry present. Use ptep_set_access_flags() instead to modify the pfn which is built to deal with modifying existing PTE. Link: http://lkml.kernel.org/r/20190311084537.16029-1-jack@suse.cz Fixes: b2770da64254 "mm: add vm_insert_mixed_mkwrite()" Signed-off-by: Jan Kara Reported-by: "Aneesh Kumar K.V" Reviewed-by: Aneesh Kumar K.V Acked-by: Dan Williams Cc: Chandan Rajendra Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 47fe250307c7..ab650c21bccd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1549,10 +1549,12 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } - entry = *pte; - goto out_mkwrite; - } else - goto out_unlock; + entry = pte_mkyoung(*pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, addr, pte, entry, 1)) + update_mmu_cache(vma, addr, pte); + } + goto out_unlock; } /* Ok, finally just insert the thing.. */ @@ -1561,7 +1563,6 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); -out_mkwrite: if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); From 44dc1b1fab787d265b9b3064bd564c87b6b86397 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 28 Mar 2019 20:43:23 -0700 Subject: [PATCH 03/22] mm/debug.c: add a cast to u64 for atomic64_read() atomic64_read() on ppc64le returns "long int", so fix the same way as commit d549f545e690 ("drm/virtio: use %llu format string form atomic64_t") by adding a cast to u64, which makes it work on all arches. In file included from ./include/linux/printk.h:7, from ./include/linux/kernel.h:15, from mm/debug.c:9: mm/debug.c: In function 'dump_mm': ./include/linux/kern_levels.h:5:18: warning: format '%llx' expects argument of type 'long long unsigned int', but argument 19 has type 'long int' [-Wformat=] #define KERN_SOH "A" /* ASCII Start Of Header */ ^~~~~~ ./include/linux/kern_levels.h:8:20: note: in expansion of macro 'KERN_SOH' #define KERN_EMERG KERN_SOH "0" /* system is unusable */ ^~~~~~~~ ./include/linux/printk.h:297:9: note: in expansion of macro 'KERN_EMERG' printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~ mm/debug.c:133:2: note: in expansion of macro 'pr_emerg' pr_emerg("mm %px mmap %px seqnum %llu task_size %lu" ^~~~~~~~ mm/debug.c:140:17: note: format string is defined here "pinned_vm %llx data_vm %lx exec_vm %lx stack_vm %lx" ~~~^ %lx Link: http://lkml.kernel.org/r/20190310183051.87303-1-cai@lca.pw Fixes: 70f8a3ca68d3 ("mm: make mm->pinned_vm an atomic64 counter") Signed-off-by: Qian Cai Acked-by: Davidlohr Bueso Cc: Jason Gunthorpe Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/debug.c b/mm/debug.c index c0b31b6c3877..45d9eb77b84e 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -168,7 +168,7 @@ void dump_mm(const struct mm_struct *mm) mm_pgtables_bytes(mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, - atomic64_read(&mm->pinned_vm), + (u64)atomic64_read(&mm->pinned_vm), mm->data_vm, mm->exec_vm, mm->stack_vm, mm->start_code, mm->end_code, mm->start_data, mm->end_data, mm->start_brk, mm->brk, mm->start_stack, From c1e287c11b752b055257196c5e98e4e91f401b32 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 28 Mar 2019 20:43:27 -0700 Subject: [PATCH 04/22] mailmap: add Changbin Du Add my email in the mailmap file to have a consistent shortlog output. Link: http://lkml.kernel.org/r/20190308142103.4929-1-changbin.du@gmail.com Signed-off-by: Changbin Du Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.mailmap b/.mailmap index 37e1847c7988..b2cde8668dcc 100644 --- a/.mailmap +++ b/.mailmap @@ -224,3 +224,5 @@ Yakir Yang Yusuke Goda Gustavo Padovan Gustavo Padovan +Changbin Du +Changbin Du From 73601ea5b7b18eb234219ae2adf77530f389da79 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 28 Mar 2019 20:43:30 -0700 Subject: [PATCH 05/22] fs/open.c: allow opening only regular files during execve() syzbot is hitting lockdep warning [1] due to trying to open a fifo during an execve() operation. But we don't need to open non regular files during an execve() operation, for all files which we will need are the executable file itself and the interpreter programs like /bin/sh and ld-linux.so.2 . Since the manpage for execve(2) says that execve() returns EACCES when the file or a script interpreter is not a regular file, and the manpage for uselib(2) says that uselib() can return EACCES, and we use FMODE_EXEC when opening for execve()/uselib(), we can bail out if a non regular file is requested with FMODE_EXEC set. Since this deadlock followed by khungtaskd warnings is trivially reproducible by a local unprivileged user, and syzbot's frequent crash due to this deadlock defers finding other bugs, let's workaround this deadlock until we get a chance to find a better solution. [1] https://syzkaller.appspot.com/bug?id=b5095bfec44ec84213bac54742a82483aad578ce Link: http://lkml.kernel.org/r/1552044017-7890-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp Reported-by: syzbot Fixes: 8924feff66f35fe2 ("splice: lift pipe_lock out of splice_to_pipe()") Signed-off-by: Tetsuo Handa Acked-by: Kees Cook Cc: Al Viro Cc: Eric Biggers Cc: Dmitry Vyukov Cc: [4.9+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/open.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/open.c b/fs/open.c index 0285ce7dbd51..f1c2f855fd43 100644 --- a/fs/open.c +++ b/fs/open.c @@ -733,6 +733,12 @@ static int do_dentry_open(struct file *f, return 0; } + /* Any file opened for execve()/uselib() has to be a regular file. */ + if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) { + error = -EACCES; + goto cleanup_file; + } + if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) From 9b7ea46a82b31c74a37e6ff1c2a1df7d53e392ab Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 28 Mar 2019 20:43:34 -0700 Subject: [PATCH 06/22] mm/hotplug: fix offline undo_isolate_page_range() Commit f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") introduced move_pfn_range_to_zone() which calls memmap_init_zone() during onlining a memory block. memmap_init_zone() will reset pagetype flags and makes migrate type to be MOVABLE. However, in __offline_pages(), it also call undo_isolate_page_range() after offline_isolated_pages() to do the same thing. Due to commit 2ce13640b3f4 ("mm: __first_valid_page skip over offline pages") changed __first_valid_page() to skip offline pages, undo_isolate_page_range() here just waste CPU cycles looping around the offlining PFN range while doing nothing, because __first_valid_page() will return NULL as offline_isolated_pages() has already marked all memory sections within the pfn range as offline via offline_mem_sections(). Also, after calling the "useless" undo_isolate_page_range() here, it reaches the point of no returning by notifying MEM_OFFLINE. Those pages will be marked as MIGRATE_MOVABLE again once onlining. The only thing left to do is to decrease the number of isolated pageblocks zone counter which would make some paths of the page allocation slower that the above commit introduced. Even if alloc_contig_range() can be used to isolate 16GB-hugetlb pages on ppc64, an "int" should still be enough to represent the number of pageblocks there. Fix an incorrect comment along the way. [cai@lca.pw: v4] Link: http://lkml.kernel.org/r/20190314150641.59358-1-cai@lca.pw Link: http://lkml.kernel.org/r/20190313143133.46200-1-cai@lca.pw Fixes: 2ce13640b3f4 ("mm: __first_valid_page skip over offline pages") Signed-off-by: Qian Cai Acked-by: Michal Hocko Reviewed-by: Oscar Salvador Cc: Vlastimil Babka Cc: [4.13+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-isolation.h | 10 ------- mm/memory_hotplug.c | 17 +++++++++--- mm/page_alloc.c | 2 +- mm/page_isolation.c | 48 +++++++++++++++++++++------------- mm/sparse.c | 2 +- 5 files changed, 45 insertions(+), 34 deletions(-) diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 4eb26d278046..280ae96dc4c3 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -41,16 +41,6 @@ int move_freepages_block(struct zone *zone, struct page *page, /* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. - * If specified range includes migrate types other than MOVABLE or CMA, - * this will fail with -EBUSY. - * - * For isolating all pages in the range finally, the caller have to - * free all pages in the range. test_page_isolated() can be used for - * test it. - * - * The following flags are allowed (they can be combined in a bit mask) - * SKIP_HWPOISON - ignore hwpoison pages - * REPORT_FAILURE - report details about the failure to isolate the range */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f767582af4f8..0e0a16021fd5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1576,7 +1576,7 @@ static int __ref __offline_pages(unsigned long start_pfn, { unsigned long pfn, nr_pages; long offlined_pages; - int ret, node; + int ret, node, nr_isolate_pageblock; unsigned long flags; unsigned long valid_start, valid_end; struct zone *zone; @@ -1602,10 +1602,11 @@ static int __ref __offline_pages(unsigned long start_pfn, ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); - if (ret) { + if (ret < 0) { reason = "failure to isolate range"; goto failed_removal; } + nr_isolate_pageblock = ret; arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -1657,8 +1658,16 @@ static int __ref __offline_pages(unsigned long start_pfn, /* Ok, all of our target is isolated. We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); - /* reset pagetype flags and makes migrate type to be MOVABLE */ - undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + + /* + * Onlining will reset pagetype flags and makes migrate type + * MOVABLE, so just need to decrease the number of isolated + * pageblocks zone counter here. + */ + spin_lock_irqsave(&zone->lock, flags); + zone->nr_isolate_pageblock -= nr_isolate_pageblock; + spin_unlock_irqrestore(&zone->lock, flags); + /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages); zone->present_pages -= offlined_pages; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 03fcf73d47da..d96ca5bc555b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8233,7 +8233,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = start_isolate_page_range(pfn_max_align_down(start), pfn_max_align_up(end), migratetype, 0); - if (ret) + if (ret < 0) return ret; /* diff --git a/mm/page_isolation.c b/mm/page_isolation.c index ce323e56b34d..bf4159d771c7 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -160,27 +160,36 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) return NULL; } -/* - * start_isolate_page_range() -- make page-allocation-type of range of pages - * to be MIGRATE_ISOLATE. - * @start_pfn: The lower PFN of the range to be isolated. - * @end_pfn: The upper PFN of the range to be isolated. - * @migratetype: migrate type to set in error recovery. +/** + * start_isolate_page_range() - make page-allocation-type of range of pages to + * be MIGRATE_ISOLATE. + * @start_pfn: The lower PFN of the range to be isolated. + * @end_pfn: The upper PFN of the range to be isolated. + * start_pfn/end_pfn must be aligned to pageblock_order. + * @migratetype: Migrate type to set in error recovery. + * @flags: The following flags are allowed (they can be combined in + * a bit mask) + * SKIP_HWPOISON - ignore hwpoison pages + * REPORT_FAILURE - report details about the failure to + * isolate the range * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the - * future will not be allocated again. - * - * start_pfn/end_pfn must be aligned to pageblock_order. - * Return 0 on success and -EBUSY if any part of range cannot be isolated. + * future will not be allocated again. If specified range includes migrate types + * other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all + * pages in the range finally, the caller have to free all pages in the range. + * test_page_isolated() can be used for test it. * * There is no high level synchronization mechanism that prevents two threads - * from trying to isolate overlapping ranges. If this happens, one thread + * from trying to isolate overlapping ranges. If this happens, one thread * will notice pageblocks in the overlapping range already set to isolate. * This happens in set_migratetype_isolate, and set_migratetype_isolate - * returns an error. We then clean up by restoring the migration type on - * pageblocks we may have modified and return -EBUSY to caller. This + * returns an error. We then clean up by restoring the migration type on + * pageblocks we may have modified and return -EBUSY to caller. This * prevents two threads from simultaneously working on overlapping ranges. + * + * Return: the number of isolated pageblocks on success and -EBUSY if any part + * of range cannot be isolated. */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype, int flags) @@ -188,6 +197,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned long pfn; unsigned long undo_pfn; struct page *page; + int nr_isolate_pageblock = 0; BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); @@ -196,13 +206,15 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (page && - set_migratetype_isolate(page, migratetype, flags)) { - undo_pfn = pfn; - goto undo; + if (page) { + if (set_migratetype_isolate(page, migratetype, flags)) { + undo_pfn = pfn; + goto undo; + } + nr_isolate_pageblock++; } } - return 0; + return nr_isolate_pageblock; undo: for (pfn = start_pfn; pfn < undo_pfn; diff --git a/mm/sparse.c b/mm/sparse.c index 69904aa6165b..56e057c432f9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -567,7 +567,7 @@ void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn) } #ifdef CONFIG_MEMORY_HOTREMOVE -/* Mark all memory sections within the pfn range as online */ +/* Mark all memory sections within the pfn range as offline */ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; From e6a9467ea14bae8691b0f72c500510c42ea8edb8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 28 Mar 2019 20:43:38 -0700 Subject: [PATCH 07/22] ocfs2: fix inode bh swapping mixup in ocfs2_reflink_inodes_lock ocfs2_reflink_inodes_lock() can swap the inode1/inode2 variables so that we always grab cluster locks in order of increasing inode number. Unfortunately, we forget to swap the inode record buffer head pointers when we've done this, which leads to incorrect bookkeepping when we're trying to make the two inodes have the same refcount tree. This has the effect of causing filesystem shutdowns if you're trying to reflink data from inode 100 into inode 97, where inode 100 already has a refcount tree attached and inode 97 doesn't. The reflink code decides to copy the refcount tree pointer from 100 to 97, but uses inode 97's inode record to open the tree root (which it doesn't have) and blows up. This issue causes filesystem shutdowns and metadata corruption! Link: http://lkml.kernel.org/r/20190312214910.GK20533@magnolia Fixes: 29ac8e856cb369 ("ocfs2: implement the VFS clone_range, copy_range, and dedupe_range features") Signed-off-by: Darrick J. Wong Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/refcounttree.c | 42 +++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 18 deletions(-) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index a35259eebc56..1dc9a08e8bdc 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4719,22 +4719,23 @@ loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode, /* Lock an inode and grab a bh pointing to the inode. */ int ocfs2_reflink_inodes_lock(struct inode *s_inode, - struct buffer_head **bh1, + struct buffer_head **bh_s, struct inode *t_inode, - struct buffer_head **bh2) + struct buffer_head **bh_t) { - struct inode *inode1; - struct inode *inode2; + struct inode *inode1 = s_inode; + struct inode *inode2 = t_inode; struct ocfs2_inode_info *oi1; struct ocfs2_inode_info *oi2; + struct buffer_head *bh1 = NULL; + struct buffer_head *bh2 = NULL; bool same_inode = (s_inode == t_inode); + bool need_swap = (inode1->i_ino > inode2->i_ino); int status; /* First grab the VFS and rw locks. */ lock_two_nondirectories(s_inode, t_inode); - inode1 = s_inode; - inode2 = t_inode; - if (inode1->i_ino > inode2->i_ino) + if (need_swap) swap(inode1, inode2); status = ocfs2_rw_lock(inode1, 1); @@ -4757,17 +4758,13 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno); - if (*bh1) - *bh1 = NULL; - if (*bh2) - *bh2 = NULL; - /* We always want to lock the one with the lower lockid first. */ if (oi1->ip_blkno > oi2->ip_blkno) mlog_errno(-ENOLCK); /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); + status = ocfs2_inode_lock_nested(inode1, &bh1, 1, + OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -4776,15 +4773,25 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, /* lock id2 */ if (!same_inode) { - status = ocfs2_inode_lock_nested(inode2, bh2, 1, + status = ocfs2_inode_lock_nested(inode2, &bh2, 1, OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto out_cl1; } - } else - *bh2 = *bh1; + } else { + bh2 = bh1; + } + + /* + * If we swapped inode order above, we have to swap the buffer heads + * before passing them back to the caller. + */ + if (need_swap) + swap(bh1, bh2); + *bh_s = bh1; + *bh_t = bh2; trace_ocfs2_double_lock_end( (unsigned long long)oi1->ip_blkno, @@ -4794,8 +4801,7 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, out_cl1: ocfs2_inode_unlock(inode1, 1); - brelse(*bh1); - *bh1 = NULL; + brelse(bh1); out_rw2: ocfs2_rw_unlock(inode2, 1); out_i2: From 6d6ea1e967a246f12cfe2f5fb743b70b2e608d4a Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Thu, 28 Mar 2019 20:43:42 -0700 Subject: [PATCH 08/22] mm: add support for kmem caches in DMA32 zone Patch series "iommu/io-pgtable-arm-v7s: Use DMA32 zone for page tables", v6. This is a followup to the discussion in [1], [2]. IOMMUs using ARMv7 short-descriptor format require page tables (level 1 and 2) to be allocated within the first 4GB of RAM, even on 64-bit systems. For L1 tables that are bigger than a page, we can just use __get_free_pages with GFP_DMA32 (on arm64 systems only, arm would still use GFP_DMA). For L2 tables that only take 1KB, it would be a waste to allocate a full page, so we considered 3 approaches: 1. This series, adding support for GFP_DMA32 slab caches. 2. genalloc, which requires pre-allocating the maximum number of L2 page tables (4096, so 4MB of memory). 3. page_frag, which is not very memory-efficient as it is unable to reuse freed fragments until the whole page is freed. [3] This series is the most memory-efficient approach. stable@ note: We confirmed that this is a regression, and IOMMU errors happen on 4.19 and linux-next/master on MT8173 (elm, Acer Chromebook R13). The issue most likely starts from commit ad67f5a6545f ("arm64: replace ZONE_DMA with ZONE_DMA32"), i.e. 4.15, and presumably breaks a number of Mediatek platforms (and maybe others?). [1] https://lists.linuxfoundation.org/pipermail/iommu/2018-November/030876.html [2] https://lists.linuxfoundation.org/pipermail/iommu/2018-December/031696.html [3] https://patchwork.codeaurora.org/patch/671639/ This patch (of 3): IOMMUs using ARMv7 short-descriptor format require page tables to be allocated within the first 4GB of RAM, even on 64-bit systems. On arm64, this is done by passing GFP_DMA32 flag to memory allocation functions. For IOMMU L2 tables that only take 1KB, it would be a waste to allocate a full page using get_free_pages, so we considered 3 approaches: 1. This patch, adding support for GFP_DMA32 slab caches. 2. genalloc, which requires pre-allocating the maximum number of L2 page tables (4096, so 4MB of memory). 3. page_frag, which is not very memory-efficient as it is unable to reuse freed fragments until the whole page is freed. This change makes it possible to create a custom cache in DMA32 zone using kmem_cache_create, then allocate memory using kmem_cache_alloc. We do not create a DMA32 kmalloc cache array, as there are currently no users of kmalloc(..., GFP_DMA32). These calls will continue to trigger a warning, as we keep GFP_DMA32 in GFP_SLAB_BUG_MASK. This implies that calls to kmem_cache_*alloc on a SLAB_CACHE_DMA32 kmem_cache must _not_ use GFP_DMA32 (it is anyway redundant and unnecessary). Link: http://lkml.kernel.org/r/20181210011504.122604-2-drinkcat@chromium.org Signed-off-by: Nicolas Boichat Acked-by: Vlastimil Babka Acked-by: Will Deacon Cc: Robin Murphy Cc: Joerg Roedel Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Michal Hocko Cc: Mel Gorman Cc: Sasha Levin Cc: Huaisheng Ye Cc: Mike Rapoport Cc: Yong Wu Cc: Matthias Brugger Cc: Tomasz Figa Cc: Yingjoe Chen Cc: Christoph Hellwig Cc: Matthew Wilcox Cc: Hsin-Yi Wang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 ++ mm/slab.c | 2 ++ mm/slab.h | 3 ++- mm/slab_common.c | 2 +- mm/slub.c | 5 +++++ 5 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index 11b45f7ae405..9449b19c5f10 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -32,6 +32,8 @@ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) +/* Use GFP_DMA32 memory */ +#define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ diff --git a/mm/slab.c b/mm/slab.c index 28652e4218e0..329bfe67f2ca 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2115,6 +2115,8 @@ int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags) cachep->allocflags = __GFP_COMP; if (flags & SLAB_CACHE_DMA) cachep->allocflags |= GFP_DMA; + if (flags & SLAB_CACHE_DMA32) + cachep->allocflags |= GFP_DMA32; if (flags & SLAB_RECLAIM_ACCOUNT) cachep->allocflags |= __GFP_RECLAIMABLE; cachep->size = size; diff --git a/mm/slab.h b/mm/slab.h index e5e6658eeacc..43ac818b8592 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -127,7 +127,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size, /* Legal flag mask for kmem_cache_create(), for various configurations */ -#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \ +#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ + SLAB_CACHE_DMA32 | SLAB_PANIC | \ SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS ) #if defined(CONFIG_DEBUG_SLAB) diff --git a/mm/slab_common.c b/mm/slab_common.c index 03eeb8b7b4b1..58251ba63e4a 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -53,7 +53,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work, SLAB_FAILSLAB | SLAB_KASAN) #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ - SLAB_ACCOUNT) + SLAB_CACHE_DMA32 | SLAB_ACCOUNT) /* * Merge control. If this is set then no merging of slab caches will occur. diff --git a/mm/slub.c b/mm/slub.c index 1b08fbcb7e61..d30ede89f4a6 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3589,6 +3589,9 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) if (s->flags & SLAB_CACHE_DMA) s->allocflags |= GFP_DMA; + if (s->flags & SLAB_CACHE_DMA32) + s->allocflags |= GFP_DMA32; + if (s->flags & SLAB_RECLAIM_ACCOUNT) s->allocflags |= __GFP_RECLAIMABLE; @@ -5679,6 +5682,8 @@ static char *create_unique_id(struct kmem_cache *s) */ if (s->flags & SLAB_CACHE_DMA) *p++ = 'd'; + if (s->flags & SLAB_CACHE_DMA32) + *p++ = 'D'; if (s->flags & SLAB_RECLAIM_ACCOUNT) *p++ = 'a'; if (s->flags & SLAB_CONSISTENCY_CHECKS) From 0a352554da69b02f75ca3389c885c741f1f63235 Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Thu, 28 Mar 2019 20:43:46 -0700 Subject: [PATCH 09/22] iommu/io-pgtable-arm-v7s: request DMA32 memory, and improve debugging IOMMUs using ARMv7 short-descriptor format require page tables (level 1 and 2) to be allocated within the first 4GB of RAM, even on 64-bit systems. For level 1/2 pages, ensure GFP_DMA32 is used if CONFIG_ZONE_DMA32 is defined (e.g. on arm64 platforms). For level 2 pages, allocate a slab cache in SLAB_CACHE_DMA32. Note that we do not explicitly pass GFP_DMA[32] to kmem_cache_zalloc, as this is not strictly necessary, and would cause a warning in mm/sl*b.c, as we did not update GFP_SLAB_BUG_MASK. Also, print an error when the physical address does not fit in 32-bit, to make debugging easier in the future. Link: http://lkml.kernel.org/r/20181210011504.122604-3-drinkcat@chromium.org Fixes: ad67f5a6545f ("arm64: replace ZONE_DMA with ZONE_DMA32") Signed-off-by: Nicolas Boichat Acked-by: Will Deacon Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Hsin-Yi Wang Cc: Huaisheng Ye Cc: Joerg Roedel Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Matthias Brugger Cc: Mel Gorman Cc: Michal Hocko Cc: Mike Rapoport Cc: Pekka Enberg Cc: Robin Murphy Cc: Sasha Levin Cc: Tomasz Figa Cc: Vlastimil Babka Cc: Yingjoe Chen Cc: Yong Wu Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/iommu/io-pgtable-arm-v7s.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index f101afc315ab..9a8a8870e267 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -160,6 +160,14 @@ #define ARM_V7S_TCR_PD1 BIT(5) +#ifdef CONFIG_ZONE_DMA32 +#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32 +#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32 +#else +#define ARM_V7S_TABLE_GFP_DMA GFP_DMA +#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA +#endif + typedef u32 arm_v7s_iopte; static bool selftest_running; @@ -197,13 +205,16 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, void *table = NULL; if (lvl == 1) - table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size)); + table = (void *)__get_free_pages( + __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size)); else if (lvl == 2) - table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA); + table = kmem_cache_zalloc(data->l2_tables, gfp); phys = virt_to_phys(table); - if (phys != (arm_v7s_iopte)phys) + if (phys != (arm_v7s_iopte)phys) { /* Doesn't fit in PTE */ + dev_err(dev, "Page table does not fit in PTE: %pa", &phys); goto out_free; + } if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) { dma = dma_map_single(dev, table, size, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma)) @@ -733,7 +744,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2", ARM_V7S_TABLE_SIZE(2), ARM_V7S_TABLE_SIZE(2), - SLAB_CACHE_DMA, NULL); + ARM_V7S_TABLE_SLAB_FLAGS, NULL); if (!data->l2_tables) goto out_free_data; From a953e7721fa9999fd628885ed451e16641a23d1e Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Thu, 28 Mar 2019 20:43:51 -0700 Subject: [PATCH 10/22] include/linux/hugetlb.h: convert to use vm_fault_t kbuild produces the below warning: tree: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master head: 5453a3df2a5eb49bc24615d4cf0d66b2aae05e5f commit 3d3539018d2c ("mm: create the new vm_fault_t type") reproduce: # apt-get install sparse git checkout 3d3539018d2cbd12e5af4a132636ee7fd8d43ef0 make ARCH=x86_64 allmodconfig make C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__' >> mm/memory.c:3968:21: sparse: incorrect type in assignment (different >> base types) @@ expected restricted vm_fault_t [usertype] ret @@ >> got e] ret @@ mm/memory.c:3968:21: expected restricted vm_fault_t [usertype] ret mm/memory.c:3968:21: got int This patch converts to return vm_fault_t type for hugetlb_fault() when CONFIG_HUGETLB_PAGE=n. Regarding the sparse warning, Luc said: : This is the expected behaviour. The constant 0 is magic regarding bitwise : types but ({ ...; 0; }) is not, it is just an ordinary expression of type : 'int'. : : So, IMHO, Souptick's patch is the right thing to do. Link: http://lkml.kernel.org/r/20190318162604.GA31553@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Mike Kravetz Cc: Matthew Wilcox Cc: Luc Van Oostenryck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ea35263eb76b..11943b60f208 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -203,7 +203,6 @@ static inline void hugetlb_show_meminfo(void) #define pud_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) -#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) #define huge_pte_offset(mm, address, sz) 0 @@ -234,6 +233,13 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, { BUG(); } +static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + unsigned int flags) +{ + BUG(); + return 0; +} #endif /* !CONFIG_HUGETLB_PAGE */ /* From a7f40cfe3b7ada57af9b62fd28430eeb4a7cfcb7 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 28 Mar 2019 20:43:55 -0700 Subject: [PATCH 11/22] mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified When MPOL_MF_STRICT was specified and an existing page was already on a node that does not follow the policy, mbind() should return -EIO. But commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") broke the rule. And commit c8633798497c ("mm: mempolicy: mbind and migrate_pages support thp migration") didn't return the correct value for THP mbind() too. If MPOL_MF_STRICT is set, ignore vma_migratable() to make sure it reaches queue_pages_to_pte_range() or queue_pages_pmd() to check if an existing page was already on a node that does not follow the policy. And, non-migratable vma may be used, return -EIO too if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified. Tested with https://github.com/metan-ucw/ltp/blob/master/testcases/kernel/syscalls/mbind/mbind02.c [akpm@linux-foundation.org: tweak code comment] Link: http://lkml.kernel.org/r/1553020556-38583-1-git-send-email-yang.shi@linux.alibaba.com Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") Signed-off-by: Yang Shi Signed-off-by: Oscar Salvador Reported-by: Cyril Hrubis Suggested-by: Kirill A. Shutemov Acked-by: Rafael Aquini Reviewed-by: Oscar Salvador Acked-by: David Rientjes Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index af171ccb56a2..2219e747df49 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -428,6 +428,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } +/* + * queue_pages_pmd() has three possible return values: + * 1 - pages are placed on the right node or queued successfully. + * 0 - THP was split. + * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing + * page was already on a node that does not follow the policy. + */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -437,7 +444,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) { - ret = 1; + ret = -EIO; goto unlock; } page = pmd_page(*pmd); @@ -454,8 +461,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(walk->vma)) { + ret = -EIO; + goto unlock; + } + migrate_page_add(page, qp->pagelist, flags); + } else + ret = -EIO; unlock: spin_unlock(ptl); out: @@ -480,8 +494,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret) + if (ret > 0) return 0; + else if (ret < 0) + return ret; } if (pmd_trans_unstable(pmd)) @@ -502,11 +518,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue; - migrate_page_add(page, qp->pagelist, flags); + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(vma)) + break; + migrate_page_add(page, qp->pagelist, flags); + } else + break; } pte_unmap_unlock(pte - 1, ptl); cond_resched(); - return 0; + return addr != end ? -EIO : 0; } static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, @@ -576,7 +597,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; - if (!vma_migratable(vma)) + /* + * Need check MPOL_MF_STRICT to return -EIO if possible + * regardless of vma_migratable + */ + if (!vma_migratable(vma) && + !(flags & MPOL_MF_STRICT)) return 1; if (endvma > end) @@ -603,7 +629,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, } /* queue pages from current vma */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & MPOL_MF_VALID) return 0; return 1; } From 5ae2efb1dea9f537453e841714e3ee2757595aec Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 28 Mar 2019 20:44:01 -0700 Subject: [PATCH 12/22] mm/debug.c: fix __dump_page when mapping->host is not set While debugging something, I added a dump_page() into do_swap_page(), and I got the splat from below. The issue happens when dereferencing mapping->host in __dump_page(): ... else if (mapping) { pr_warn("%ps ", mapping->a_ops); if (mapping->host->i_dentry.first) { struct dentry *dentry; dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias); pr_warn("name:\"%pd\" ", dentry); } } ... Swap address space does not contain an inode information, and so mapping->host equals NULL. Although the dump_page() call was added artificially into do_swap_page(), I am not sure if we can hit this from any other path, so it looks worth fixing it. We can easily do that by checking mapping->host first. Link: http://lkml.kernel.org/r/20190318072931.29094-1-osalvador@suse.de Fixes: 1c6fb1d89e73c ("mm: print more information about mapping in __dump_page") Signed-off-by: Oscar Salvador Acked-by: Michal Hocko Acked-by: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/debug.c b/mm/debug.c index 45d9eb77b84e..eee9c221280c 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -79,7 +79,7 @@ void __dump_page(struct page *page, const char *reason) pr_warn("ksm "); else if (mapping) { pr_warn("%ps ", mapping->a_ops); - if (mapping->host->i_dentry.first) { + if (mapping->host && mapping->host->i_dentry.first) { struct dentry *dentry; dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias); pr_warn("name:\"%pd\" ", dentry); From b736523f0759d1debeb56f8e0c4c87a2bea0fb23 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 28 Mar 2019 20:44:05 -0700 Subject: [PATCH 13/22] include/linux/list.h: fix list_is_first() kernel-doc Fix typo of kernel-doc parameter notation (there should be no space between '@' and the parameter name). Also fixes bogus kernel-doc notation output formatting. Link: http://lkml.kernel.org/r/ddce8b80-9a8a-d52d-3546-87b2211c089a@infradead.org Fixes: 70b44595eafe9 ("mm, compaction: use free lists to quickly locate a migration source") Signed-off-by: Randy Dunlap Acked-by: Mel Gorman Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/list.h b/include/linux/list.h index 79626b5ab36c..58aa3adf94e6 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -207,7 +207,7 @@ static inline void list_bulk_move_tail(struct list_head *head, } /** - * list_is_first -- tests whether @ list is the first entry in list @head + * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ From eebf36480678f948b3ed15d56ca7b8e6194e7c18 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 28 Mar 2019 20:44:09 -0700 Subject: [PATCH 14/22] fs/proc/kcore.c: make kcore_modules static Fix sparse warning: fs/proc/kcore.c:591:19: warning: symbol 'kcore_modules' was not declared. Should it be static? Link: http://lkml.kernel.org/r/20190320135417.13272-1-yuehaibing@huawei.com Signed-off-by: YueHaibing Acked-by: Mukesh Ojha Cc: Alexey Dobriyan Cc: Omar Sandoval Cc: James Morse Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kcore.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index d29d869abec1..f5834488b67d 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -615,7 +615,7 @@ static void __init proc_kcore_text_init(void) /* * MODULES_VADDR has no intersection with VMALLOC_ADDR. */ -struct kcore_list kcore_modules; +static struct kcore_list kcore_modules; static void __init add_modules_range(void) { if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) { From fcfc2aa0185f4a731d05a21e9f359968fdfd02e7 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Thu, 28 Mar 2019 20:44:13 -0700 Subject: [PATCH 15/22] ptrace: take into account saved_sigmask in PTRACE{GET,SET}SIGMASK There are a few system calls (pselect, ppoll, etc) which replace a task sigmask while they are running in a kernel-space When a task calls one of these syscalls, the kernel saves a current sigmask in task->saved_sigmask and sets a syscall sigmask. On syscall-exit-stop, ptrace traps a task before restoring the saved_sigmask, so PTRACE_GETSIGMASK returns the syscall sigmask and PTRACE_SETSIGMASK does nothing, because its sigmask is replaced by saved_sigmask, when the task returns to user-space. This patch fixes this problem. PTRACE_GETSIGMASK returns saved_sigmask if it's set. PTRACE_SETSIGMASK drops the TIF_RESTORE_SIGMASK flag. Link: http://lkml.kernel.org/r/20181120060616.6043-1-avagin@gmail.com Fixes: 29000caecbe8 ("ptrace: add ability to get/set signal-blocked mask") Signed-off-by: Andrei Vagin Acked-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/signal.h | 18 ++++++++++++++++++ kernel/ptrace.c | 15 +++++++++++++-- 2 files changed, 31 insertions(+), 2 deletions(-) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index ae5655197698..e412c092c1e8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -418,10 +418,20 @@ static inline void set_restore_sigmask(void) set_thread_flag(TIF_RESTORE_SIGMASK); WARN_ON(!test_thread_flag(TIF_SIGPENDING)); } + +static inline void clear_tsk_restore_sigmask(struct task_struct *tsk) +{ + clear_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK); +} + static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } +static inline bool test_tsk_restore_sigmask(struct task_struct *tsk) +{ + return test_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK); +} static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); @@ -439,6 +449,10 @@ static inline void set_restore_sigmask(void) current->restore_sigmask = true; WARN_ON(!test_thread_flag(TIF_SIGPENDING)); } +static inline void clear_tsk_restore_sigmask(struct task_struct *tsk) +{ + tsk->restore_sigmask = false; +} static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; @@ -447,6 +461,10 @@ static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } +static inline bool test_tsk_restore_sigmask(struct task_struct *tsk) +{ + return tsk->restore_sigmask; +} static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 771e93f9c43f..6f357f4fc859 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -29,6 +29,7 @@ #include #include #include +#include /* * Access another process' address space via ptrace. @@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setsiginfo(child, &siginfo); break; - case PTRACE_GETSIGMASK: + case PTRACE_GETSIGMASK: { + sigset_t *mask; + if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } - if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t))) + if (test_tsk_restore_sigmask(child)) + mask = &child->saved_sigmask; + else + mask = &child->blocked; + + if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; + } case PTRACE_SETSIGMASK: { sigset_t new_set; @@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request, child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); + clear_tsk_restore_sigmask(child); + ret = 0; break; } From c4efe484b5f0d768e23c9731082fec827723e738 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 28 Mar 2019 20:44:16 -0700 Subject: [PATCH 16/22] mm/memory_hotplug.c: fix notification in offline error path When start_isolate_page_range() returned -EBUSY in __offline_pages(), it calls memory_notify(MEM_CANCEL_OFFLINE, &arg) with an uninitialized "arg". As the result, it triggers warnings below. Also, it is only necessary to notify MEM_CANCEL_OFFLINE after MEM_GOING_OFFLINE. page:ffffea0001200000 count:1 mapcount:0 mapping:0000000000000000 index:0x0 flags: 0x3fffe000001000(reserved) raw: 003fffe000001000 ffffea0001200008 ffffea0001200008 0000000000000000 raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: unmovable page WARNING: CPU: 25 PID: 1665 at mm/kasan/common.c:665 kasan_mem_notifier+0x34/0x23b CPU: 25 PID: 1665 Comm: bash Tainted: G W 5.0.0+ #94 Hardware name: HP ProLiant DL180 Gen9/ProLiant DL180 Gen9, BIOS U20 10/25/2017 RIP: 0010:kasan_mem_notifier+0x34/0x23b RSP: 0018:ffff8883ec737890 EFLAGS: 00010206 RAX: 0000000000000246 RBX: ff10f0f4435f1000 RCX: f887a7a21af88000 RDX: dffffc0000000000 RSI: 0000000000000020 RDI: ffff8881f221af88 RBP: ffff8883ec737898 R08: ffff888000000000 R09: ffffffffb0bddcd0 R10: ffffed103e857088 R11: ffff8881f42b8443 R12: dffffc0000000000 R13: 00000000fffffff9 R14: dffffc0000000000 R15: 0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000560fbd31d730 CR3: 00000004049c6003 CR4: 00000000001606a0 Call Trace: notifier_call_chain+0xbf/0x130 __blocking_notifier_call_chain+0x76/0xc0 blocking_notifier_call_chain+0x16/0x20 memory_notify+0x1b/0x20 __offline_pages+0x3e2/0x1210 offline_pages+0x11/0x20 memory_block_action+0x144/0x300 memory_subsys_offline+0xe5/0x170 device_offline+0x13f/0x1e0 state_store+0xeb/0x110 dev_attr_store+0x3f/0x70 sysfs_kf_write+0x104/0x150 kernfs_fop_write+0x25c/0x410 __vfs_write+0x66/0x120 vfs_write+0x15a/0x4f0 ksys_write+0xd2/0x1b0 __x64_sys_write+0x73/0xb0 do_syscall_64+0xeb/0xb78 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f14f75cc3b8 RSP: 002b:00007ffe84d01d68 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000008 RCX: 00007f14f75cc3b8 RDX: 0000000000000008 RSI: 0000563f8e433d70 RDI: 0000000000000001 RBP: 0000563f8e433d70 R08: 000000000000000a R09: 00007ffe84d018f0 R10: 000000000000000a R11: 0000000000000246 R12: 00007f14f789e780 R13: 0000000000000008 R14: 00007f14f7899740 R15: 0000000000000008 Link: http://lkml.kernel.org/r/20190320204255.53571-1-cai@lca.pw Fixes: 7960509329c2 ("mm, memory_hotplug: print reason for the offlining failure") Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Signed-off-by: Qian Cai Reviewed-by: Andrew Morton Cc: [5.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0e0a16021fd5..0082d699be94 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1699,12 +1699,12 @@ static int __ref __offline_pages(unsigned long start_pfn, failed_removal_isolated: undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + memory_notify(MEM_CANCEL_OFFLINE, &arg); failed_removal: pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n", (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ mem_hotplug_done(); return ret; From f5777bc2d9cf0712554228b1a7927b6f13f5c1f0 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 28 Mar 2019 20:44:21 -0700 Subject: [PATCH 17/22] mm/page_isolation.c: fix a wrong flag in set_migratetype_isolate() Due to has_unmovable_pages() taking an incorrect irqsave flag instead of the isolation flag in set_migratetype_isolate(), there are issues with HWPOSION and error reporting where dump_page() is not called when there is an unmovable page. Link: http://lkml.kernel.org/r/20190320204941.53731-1-cai@lca.pw Fixes: d381c54760dc ("mm: only report isolation failures when offlining memory") Acked-by: Michal Hocko Reviewed-by: Oscar Salvador Signed-off-by: Qian Cai Cc: [5.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index bf4159d771c7..019280712e1b 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -59,7 +59,8 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. * We just check MOVABLE pages. */ - if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, flags)) + if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, + isol_flags)) ret = 0; /* From 0bc9f5d14a93971c6cd9c0d81b0fc154fc54c65d Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Mar 2019 20:44:24 -0700 Subject: [PATCH 18/22] drivers/block/zram/zram_drv.c: fix idle/writeback string compare Makoto report a below KASAN error: zram does out-of-bounds read. Because strscpy copies from source up to count bytes unconditionally. It could cause out-of-bounds read on next object in slab. To prevent it, use strlcpy which checks source's length automatically. BUG: KASAN: slab-out-of-bounds in strscpy+0x68/0x154 Read of size 8 at addr ffffffc0c3495a00 by task system_server/1314 .. Call trace: strscpy+0x68/0x154 idle_store+0xc4/0x34c dev_attr_store+0x50/0x6c sysfs_kf_write+0x98/0xb4 kernfs_fop_write+0x198/0x260 __vfs_write+0x10c/0x338 vfs_write+0x114/0x238 SyS_write+0xc8/0x168 __sys_trace_return+0x0/0x4 Allocated by task 1314: __kmalloc+0x280/0x318 kernfs_fop_write+0xac/0x260 __vfs_write+0x10c/0x338 vfs_write+0x114/0x238 SyS_write+0xc8/0x168 __sys_trace_return+0x0/0x4 Freed by task 2855: kfree+0x138/0x630 kernfs_put_open_node+0x10c/0x124 kernfs_fop_release+0xd8/0x114 __fput+0x130/0x2a4 ____fput+0x1c/0x28 task_work_run+0x16c/0x1c8 do_notify_resume+0x2bc/0x107c work_pending+0x8/0x10 The buggy address belongs to the object at ffffffc0c3495a00 which belongs to the cache kmalloc-128 of size 128 The buggy address is located 0 bytes inside of 128-byte region [ffffffc0c3495a00, ffffffc0c3495a80) The buggy address belongs to the page: page:ffffffbf030d2500 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0 flags: 0x4000000000010200(slab|head) page dumped because: kasan: bad access detected Memory state around the buggy address: ffffffc0c3495900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0c3495980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffffffc0c3495a00: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffffffc0c3495a80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffffc0c3495b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Link: http://lkml.kernel.org/r/20190319231911.145968-1-minchan@kernel.org Cc: [5.0] Signed-off-by: Minchan Kim Reported-by: Makoto Wu Reviewed-by: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 32 ++++++-------------------------- 1 file changed, 6 insertions(+), 26 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e7a5f1d1c314..399cad7daae7 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -290,18 +290,8 @@ static ssize_t idle_store(struct device *dev, struct zram *zram = dev_to_zram(dev); unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; int index; - char mode_buf[8]; - ssize_t sz; - sz = strscpy(mode_buf, buf, sizeof(mode_buf)); - if (sz <= 0) - return -EINVAL; - - /* ignore trailing new line */ - if (mode_buf[sz - 1] == '\n') - mode_buf[sz - 1] = 0x00; - - if (strcmp(mode_buf, "all")) + if (!sysfs_streq(buf, "all")) return -EINVAL; down_read(&zram->init_lock); @@ -635,25 +625,15 @@ static ssize_t writeback_store(struct device *dev, struct bio bio; struct bio_vec bio_vec; struct page *page; - ssize_t ret, sz; - char mode_buf[8]; - int mode = -1; + ssize_t ret; + int mode; unsigned long blk_idx = 0; - sz = strscpy(mode_buf, buf, sizeof(mode_buf)); - if (sz <= 0) - return -EINVAL; - - /* ignore trailing newline */ - if (mode_buf[sz - 1] == '\n') - mode_buf[sz - 1] = 0x00; - - if (!strcmp(mode_buf, "idle")) + if (sysfs_streq(buf, "idle")) mode = IDLE_WRITEBACK; - else if (!strcmp(mode_buf, "huge")) + else if (sysfs_streq(buf, "huge")) mode = HUGE_WRITEBACK; - - if (mode == -1) + else return -EINVAL; down_read(&zram->init_lock); From d2b2c6dd227ba5b8a802858748ec9a780cb75b47 Mon Sep 17 00:00:00 2001 From: Lars Persson Date: Thu, 28 Mar 2019 20:44:28 -0700 Subject: [PATCH 19/22] mm/migrate.c: add missing flush_dcache_page for non-mapped page migrate Our MIPS 1004Kc SoCs were seeing random userspace crashes with SIGILL and SIGSEGV that could not be traced back to a userspace code bug. They had all the magic signs of an I/D cache coherency issue. Now recently we noticed that the /proc/sys/vm/compact_memory interface was quite efficient at provoking this class of userspace crashes. Studying the code in mm/migrate.c there is a distinction made between migrating a page that is mapped at the instant of migration and one that is not mapped. Our problem turned out to be the non-mapped pages. For the non-mapped page the code performs a copy of the page content and all relevant meta-data of the page without doing the required D-cache maintenance. This leaves dirty data in the D-cache of the CPU and on the 1004K cores this data is not visible to the I-cache. A subsequent page-fault that triggers a mapping of the page will happily serve the process with potentially stale code. What about ARM then, this bug should have seen greater exposure? Well ARM became immune to this flaw back in 2010, see commit c01778001a4f ("ARM: 6379/1: Assume new page cache pages have dirty D-cache"). My proposed fix moves the D-cache maintenance inside move_to_new_page to make it common for both cases. Link: http://lkml.kernel.org/r/20190315083502.11849-1-larper@axis.com Fixes: 97ee0524614 ("flush cache before installing new page at migraton") Signed-off-by: Lars Persson Reviewed-by: Paul Burton Acked-by: Mel Gorman Cc: Ralf Baechle Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index ac6f4939bb59..663a5449367a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -248,10 +248,8 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, pte = swp_entry_to_pte(entry); } else if (is_device_public_page(new)) { pte = pte_mkdevmap(pte); - flush_dcache_page(new); } - } else - flush_dcache_page(new); + } #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { @@ -995,6 +993,13 @@ static int move_to_new_page(struct page *newpage, struct page *page, */ if (!PageMappingFlags(page)) page->mapping = NULL; + + if (unlikely(is_zone_device_page(newpage))) { + if (is_device_public_page(newpage)) + flush_dcache_page(newpage); + } else + flush_dcache_page(newpage); + } out: return rc; From 4462996ea3cc6bcf3c4efbd7bd2514a15dd8ece4 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 28 Mar 2019 20:44:32 -0700 Subject: [PATCH 20/22] checkpatch: add %pt as a valid vsprintf extension Commit 4d42c44727a0 ("lib/vsprintf: Print time and date in human readable format via %pt") introduced a new extension, %pt. Add it in the list of valid extensions. Link: http://lkml.kernel.org/r/20190314203719.29130-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkpatch.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 5b756278df13..a09333fd7cef 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5977,7 +5977,7 @@ sub process { while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) { $specifier = $1; $extension = $2; - if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOx]/) { + if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOxt]/) { $bad_specifier = $specifier; last; } From 2620327852478e695afb2eebe66c354b3bc456cc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 28 Mar 2019 20:44:36 -0700 Subject: [PATCH 21/22] fs: fs_parser: fix printk format warning Fix printk format warning (seen on i386 builds) by using ptrdiff format specifier (%t): fs/fs_parser.c:413:6: warning: format `%lu' expects argument of type `long unsigned int', but argument 3 has type `int' [-Wformat=] Link: http://lkml.kernel.org/r/19432668-ffd3-fbb2-af4f-1c8e48f6cc81@infradead.org Signed-off-by: Randy Dunlap Acked-by: Geert Uytterhoeven Cc: David Howells Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs_parser.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 842e8f749db6..570d71043acf 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -410,7 +410,7 @@ bool fs_validate_description(const struct fs_parameter_description *desc) for (param = desc->specs; param->name; param++) { if (param->opt == e->opt && param->type != fs_param_is_enum) { - pr_err("VALIDATE %s: e[%lu] enum val for %s\n", + pr_err("VALIDATE %s: e[%tu] enum val for %s\n", name, e - desc->enums, param->name); good = false; } From 23da9588037ecdd4901db76a5b79a42b529c4ec3 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 28 Mar 2019 20:44:40 -0700 Subject: [PATCH 22/22] fs/proc/proc_sysctl.c: fix NULL pointer dereference in put_links Syzkaller reports: kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI CPU: 1 PID: 5373 Comm: syz-executor.0 Not tainted 5.0.0-rc8+ #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 RIP: 0010:put_links+0x101/0x440 fs/proc/proc_sysctl.c:1599 Code: 00 0f 85 3a 03 00 00 48 8b 43 38 48 89 44 24 20 48 83 c0 38 48 89 c2 48 89 44 24 28 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 fe 02 00 00 48 8b 74 24 20 48 c7 c7 60 2a 9d 91 RSP: 0018:ffff8881d828f238 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff8881e01b1140 RCX: ffffffff8ee98267 RDX: 0000000000000007 RSI: ffffc90001479000 RDI: ffff8881e01b1178 RBP: dffffc0000000000 R08: ffffed103ee27259 R09: ffffed103ee27259 R10: 0000000000000001 R11: ffffed103ee27258 R12: fffffffffffffff4 R13: 0000000000000006 R14: ffff8881f59838c0 R15: dffffc0000000000 FS: 00007f072254f700(0000) GS:ffff8881f7100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fff8b286668 CR3: 00000001f0542002 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: drop_sysctl_table+0x152/0x9f0 fs/proc/proc_sysctl.c:1629 get_subdir fs/proc/proc_sysctl.c:1022 [inline] __register_sysctl_table+0xd65/0x1090 fs/proc/proc_sysctl.c:1335 br_netfilter_init+0xbc/0x1000 [br_netfilter] do_one_initcall+0xfa/0x5ca init/main.c:887 do_init_module+0x204/0x5f6 kernel/module.c:3460 load_module+0x66b2/0x8570 kernel/module.c:3808 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462e99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f072254ec58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99 RDX: 0000000000000000 RSI: 0000000020000280 RDI: 0000000000000003 RBP: 00007f072254ec70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f072254f6bc R13: 00000000004bcefa R14: 00000000006f6fb0 R15: 0000000000000004 Modules linked in: br_netfilter(+) dvb_usb_dibusb_mc_common dib3000mc dibx000_common dvb_usb_dibusb_common dvb_usb_dw2102 dvb_usb classmate_laptop palmas_regulator cn videobuf2_v4l2 v4l2_common snd_soc_bd28623 mptbase snd_usb_usx2y snd_usbmidi_lib snd_rawmidi wmi libnvdimm lockd sunrpc grace rc_kworld_pc150u rc_core rtc_da9063 sha1_ssse3 i2c_cros_ec_tunnel adxl34x_spi adxl34x nfnetlink lib80211 i5500_temp dvb_as102 dvb_core videobuf2_common videodev media videobuf2_vmalloc videobuf2_memops udc_core lnbp22 leds_lp3952 hid_roccat_ryos s1d13xxxfb mtd vport_geneve openvswitch nf_conncount nf_nat_ipv6 nsh geneve udp_tunnel ip6_udp_tunnel snd_soc_mt6351 sis_agp phylink snd_soc_adau1761_spi snd_soc_adau1761 snd_soc_adau17x1 snd_soc_core snd_pcm_dmaengine ac97_bus snd_compress snd_soc_adau_utils snd_soc_sigmadsp_regmap snd_soc_sigmadsp raid_class hid_roccat_konepure hid_roccat_common hid_roccat c2port_duramar2150 core mdio_bcm_unimac iptable_security iptable_raw iptable_mangle iptable_nat nf_nat_ipv4 nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 iptable_filter bpfilter ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel hsr veth netdevsim devlink vxcan batman_adv cfg80211 rfkill chnl_net caif nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel joydev mousedev ide_pci_generic piix aesni_intel aes_x86_64 ide_core crypto_simd atkbd cryptd glue_helper serio_raw ata_generic pata_acpi i2c_piix4 floppy sch_fq_codel ip_tables x_tables ipv6 [last unloaded: lm73] Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace 770020de38961fd0 ]--- A new dir entry can be created in get_subdir and its 'header->parent' is set to NULL. Only after insert_header success, it will be set to 'dir', otherwise 'header->parent' is set to NULL and drop_sysctl_table is called. However in err handling path of get_subdir, drop_sysctl_table also be called on 'new->header' regardless its value of parent pointer. Then put_links is called, which triggers NULL-ptr deref when access member of header->parent. In fact we have multiple error paths which call drop_sysctl_table() there, upon failure on insert_links() we also call drop_sysctl_table().And even in the successful case on __register_sysctl_table() we still always call drop_sysctl_table().This patch fix it. Link: http://lkml.kernel.org/r/20190314085527.13244-1-yuehaibing@huawei.com Fixes: 0e47c99d7fe25 ("sysctl: Replace root_list with links between sysctl_table_sets") Signed-off-by: YueHaibing Reported-by: Hulk Robot Acked-by: Luis Chamberlain Cc: Kees Cook Cc: Alexey Dobriyan Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Al Viro Cc: Eric W. Biederman Cc: [3.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 4d598a399bbf..d65390727541 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1626,7 +1626,8 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - put_links(header); + if (parent) + put_links(header); start_unregistering(header); if (!--header->count) kfree_rcu(header, rcu);