From 9b3bd581a0492bdfe788539ca65a14da570faad1 Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Wed, 9 Mar 2016 09:18:07 -0600 Subject: debugfs: Make automount point inodes permanently empty commit 87243deb88671f70def4c52dfa7ca7830707bd31 upstream. Starting with 4.1 the tracing subsystem has its own filesystem which is automounted in the tracing subdirectory of debugfs. Prior to this debugfs could be bind mounted in a cloned mount namespace, but if tracefs has been mounted under debugfs this now fails because there is a locked child mount. This creates a regression for container software which bind mounts debugfs to satisfy the assumption of some userspace software. In other pseudo filesystems such as proc and sysfs we're already creating mountpoints like this in such a way that no dirents can be created in the directories, allowing them to be exceptions to some MNT_LOCKED tests. In fact we're already do this for the tracefs mountpoint in sysfs. Do the same in debugfs_create_automount(), since the intention here is clearly to create a mountpoint. This fixes the regression, as locked child mounts on permanently empty directories do not cause a bind mount to fail. Signed-off-by: Seth Forshee Acked-by: Serge Hallyn Signed-off-by: Greg Kroah-Hartman --- fs/debugfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b7fcc0de0b2f..0f5d05bf2131 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -457,7 +457,7 @@ struct dentry *debugfs_create_automount(const char *name, if (unlikely(!inode)) return failed_creating(dentry); - inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; dentry->d_fsdata = (void *)f; -- cgit v1.2.3 From e513b90a9aef91e6399decb8e9592f2d75f7ebad Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 28 Apr 2016 16:18:35 -0700 Subject: numa: fix /proc//numa_maps for THP commit 28093f9f34cedeaea0f481c58446d9dac6dd620f upstream. In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer Cc: Naoya Horiguchi Cc: "Kirill A . Shutemov" Cc: Konstantin Khlebnikov Cc: Michal Hocko Cc: Vlastimil Babka Cc: Jerome Marchand Cc: Johannes Weiner Cc: Dave Hansen Cc: Mel Gorman Cc: Dan Williams Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/proc/task_mmu.c | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 09cd3edde08a..f6478301db00 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1435,6 +1435,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static struct page *can_gather_numa_stats_pmd(pmd_t pmd, + struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pmd_present(pmd)) + return NULL; + + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + return NULL; + + if (PageReserved(page)) + return NULL; + + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_MEMORY])) + return NULL; + + return page; +} +#endif + static int gather_pte_stats(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -1444,13 +1470,13 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { - pte_t huge_pte = *(pte_t *)pmd; struct page *page; - page = can_gather_numa_stats(huge_pte, vma, addr); + page = can_gather_numa_stats_pmd(*pmd, vma, addr); if (page) - gather_stats(page, md, pte_dirty(huge_pte), + gather_stats(page, md, pmd_dirty(*pmd), HPAGE_PMD_SIZE/PAGE_SIZE); spin_unlock(ptl); return 0; @@ -1458,6 +1484,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; +#endif orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); do { struct page *page = can_gather_numa_stats(*pte, vma, addr); -- cgit v1.2.3 From c745297ba18668f8a760493d7d769563c818616e Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Sat, 12 Mar 2016 21:40:32 -0500 Subject: ext4: fix NULL pointer dereference in ext4_mark_inode_dirty() commit 5e1021f2b6dff1a86a468a1424d59faae2bc63c1 upstream. ext4_reserve_inode_write() in ext4_mark_inode_dirty() could fail on error (e.g. EIO) and iloc.bh can be NULL in this case. But the error is ignored in the following "if" condition and ext4_expand_extra_isize() might be called with NULL iloc.bh set, which triggers NULL pointer dereference. This is uncovered by commit 8b4953e13f4c ("ext4: reserve code points for the project quota feature"), which enlarges the ext4_inode size, and run the following script on new kernel but with old mke2fs: #/bin/bash mnt=/mnt/ext4 devname=ext4-error dev=/dev/mapper/$devname fsimg=/home/fs.img trap cleanup 0 1 2 3 9 15 cleanup() { umount $mnt >/dev/null 2>&1 dmsetup remove $devname losetup -d $backend_dev rm -f $fsimg exit 0 } rm -f $fsimg fallocate -l 1g $fsimg backend_dev=`losetup -f --show $fsimg` devsize=`blockdev --getsz $backend_dev` good_tab="0 $devsize linear $backend_dev 0" error_tab="0 $devsize error $backend_dev 0" dmsetup create $devname --table "$good_tab" mkfs -t ext4 $dev mount -t ext4 -o errors=continue,strictatime $dev $mnt dmsetup load $devname --table "$error_tab" && dmsetup resume $devname echo 3 > /proc/sys/vm/drop_caches ls -l $mnt exit 0 [ Patch changed to simplify the function a tiny bit. -- Ted ] Signed-off-by: Eryu Guan Signed-off-by: Theodore Ts'o Cc: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 06bda0361e7c..547600556bb9 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5109,6 +5109,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + return err; if (ext4_handle_valid(handle) && EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { @@ -5139,9 +5141,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) } } } - if (!err) - err = ext4_mark_iloc_dirty(handle, inode, &iloc); - return err; + return ext4_mark_iloc_dirty(handle, inode, &iloc); } /* -- cgit v1.2.3 From 0b680de452570274716c2c9990903acea525f0d0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 14:28:03 -0500 Subject: ext4: fix races between page faults and hole punching commit ea3d7209ca01da209cda6f0dea8be9cc4b7a933b upstream. Currently, page faults and hole punching are completely unsynchronized. This can result in page fault faulting in a page into a range that we are punching after truncate_pagecache_range() has been called and thus we can end up with a page mapped to disk blocks that will be shortly freed. Filesystem corruption will shortly follow. Note that the same race is avoided for truncate by checking page fault offset against i_size but there isn't similar mechanism available for punching holes. Fix the problem by creating new rw semaphore i_mmap_sem in inode and grab it for writing over truncate, hole punching, and other functions removing blocks from extent tree and for read over page faults. We cannot easily use i_data_sem for this since that ranks below transaction start and we need something ranking above it so that it can be held over the whole truncate / hole punching operation. Also remove various workarounds we had in the code to reduce race window when page fault could have created pages with stale mapping information. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 10 +++++++++ fs/ext4/extents.c | 54 ++++++++++++++++++++++++-------------------- fs/ext4/file.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++-------- fs/ext4/inode.c | 36 +++++++++++++++++++++-------- fs/ext4/super.c | 1 + fs/ext4/truncate.h | 2 ++ 6 files changed, 127 insertions(+), 42 deletions(-) (limited to 'fs') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d4156e1c128d..89df9f55595b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -933,6 +933,15 @@ struct ext4_inode_info { * by other means, so we have i_data_sem. */ struct rw_semaphore i_data_sem; + /* + * i_mmap_sem is for serializing page faults with truncate / punch hole + * operations. We have to make sure that new page cannot be faulted in + * a section of the inode that is being punched. We cannot easily use + * i_data_sem for this since we need protection for the whole punch + * operation and i_data_sem ranks below transaction start so we have + * to occasionally drop it. + */ + struct rw_semaphore i_mmap_sem; struct inode vfs_inode; struct jbd2_inode *jinode; @@ -2507,6 +2516,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 551353b1b17a..5be9ca5a8a7a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4770,7 +4770,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, int partial_begin, partial_end; loff_t start, end; ext4_lblk_t lblk; - struct address_space *mapping = inode->i_mapping; unsigned int blkbits = inode->i_blkbits; trace_ext4_zero_range(inode, offset, len, mode); @@ -4785,17 +4784,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, return ret; } - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - ret = filemap_write_and_wait_range(mapping, offset, - offset + len - 1); - if (ret) - return ret; - } - /* * Round up offset. This is not fallocate, we neet to zero out * blocks, so convert interior block aligned part of the range to @@ -4856,16 +4844,22 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); - /* Now release the pages and zero block aligned part of pages*/ - truncate_pagecache_range(inode, start, end - 1); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - /* Wait all existing dio workers, newcomers will block on i_mutex */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have + * released from page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* Now release the pages and zero block aligned part of pages */ + truncate_pagecache_range(inode, start, end - 1); + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + up_write(&EXT4_I(inode)->i_mmap_sem); if (ret) goto out_dio; } @@ -5524,17 +5518,22 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } down_write(&EXT4_I(inode)->i_data_sem); @@ -5573,7 +5572,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -5660,17 +5660,22 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } /* Expand file to avoid data loss if there is error while shifting */ @@ -5741,7 +5746,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 113837e7ba98..0d24ebcd7c9e 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -209,15 +209,18 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { int result; handle_t *handle = NULL; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; bool write = vmf->flags & FAULT_FLAG_WRITE; if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, EXT4_DATA_TRANS_BLOCKS(sb)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; @@ -228,8 +231,10 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } @@ -246,10 +251,12 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, ext4_chunk_trans_blocks(inode, PMD_SIZE / PAGE_SIZE)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; @@ -260,30 +267,71 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_mkwrite(vma, vmf, ext4_get_block_dax, - ext4_end_io_unwritten); + int err; + struct inode *inode = file_inode(vma->vm_file); + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + err = __dax_mkwrite(vma, vmf, ext4_get_block_dax, + ext4_end_io_unwritten); + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(inode->i_sb); + + return err; +} + +/* + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * handler we check for races agaist truncate. Note that since we cycle through + * i_mmap_sem, we are sure that also any hole punching that began before we + * were called is finished by now and so if it included part of the file we + * are working on, our pte will get unmapped and the check for pte_same() in + * wp_pfn_shared() fails. Thus fault gets retried and things work out as + * desired. + */ +static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; + int ret = VM_FAULT_NOPAGE; + loff_t size; + + sb_start_pagefault(sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(sb); + + return ret; } static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, .page_mkwrite = ext4_dax_mkwrite, - .pfn_mkwrite = dax_pfn_mkwrite, + .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops #endif static const struct vm_operations_struct ext4_file_vm_ops = { - .fault = filemap_fault, + .fault = ext4_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 547600556bb9..214e30a3ef9e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3651,6 +3651,15 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); first_block_offset = round_up(offset, sb->s_blocksize); last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; @@ -3659,10 +3668,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) truncate_pagecache_range(inode, first_block_offset, last_block_offset); - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); else @@ -3708,16 +3713,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (IS_SYNC(inode)) ext4_handle_sync(handle); - /* Now release the pages again to reduce race window */ - if (last_block_offset > first_block_offset) - truncate_pagecache_range(inode, first_block_offset, - last_block_offset); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); out_stop: ext4_journal_stop(handle); out_dio: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -4851,6 +4852,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } else ext4_wait_for_tail_page_commit(inode); } + down_write(&EXT4_I(inode)->i_mmap_sem); /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. @@ -4858,6 +4860,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) truncate_pagecache(inode, inode->i_size); if (shrink) ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } if (!rc) { @@ -5306,6 +5309,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); + + down_read(&EXT4_I(inode)->i_mmap_sem); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -5375,6 +5380,19 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; } + +int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + int err; + + down_read(&EXT4_I(inode)->i_mmap_sem); + err = filemap_fault(vma, vmf); + up_read(&EXT4_I(inode)->i_mmap_sem); + + return err; +} diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba1cf0bf2f81..852c26806af2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -958,6 +958,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); + init_rwsem(&ei->i_mmap_sem); inode_init_once(&ei->vfs_inode); } diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h index 011ba6670d99..c70d06a383e2 100644 --- a/fs/ext4/truncate.h +++ b/fs/ext4/truncate.h @@ -10,8 +10,10 @@ */ static inline void ext4_truncate_failed_write(struct inode *inode) { + down_write(&EXT4_I(inode)->i_mmap_sem); truncate_inode_pages(inode->i_mapping, inode->i_size); ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } /* -- cgit v1.2.3 From e096ade68c13011ba6548a542c1fc00e14555f5c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 14:29:17 -0500 Subject: ext4: move unlocked dio protection from ext4_alloc_file_blocks() commit 17048e8a083fec7ad841d88ef0812707fbc7e39f upstream. Currently ext4_alloc_file_blocks() was handling protection against unlocked DIO. However we now need to sometimes call it under i_mmap_sem and sometimes not and DIO protection ranks above it (although strictly speaking this cannot currently create any deadlocks). Also ext4_zero_range() was actually getting & releasing unlocked DIO protection twice in some cases. Luckily it didn't introduce any real bug but it was a land mine waiting to be stepped on. So move DIO protection out from ext4_alloc_file_blocks() into the two callsites. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/extents.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5be9ca5a8a7a..65b5ada2833f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4685,10 +4685,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - /* * credits to insert 1 extent into extent tree */ @@ -4752,8 +4748,6 @@ retry: goto retry; } - ext4_inode_resume_unlocked_dio(inode); - return ret > 0 ? ret2 : ret; } @@ -4827,6 +4821,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (mode & FALLOC_FL_KEEP_SIZE) flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4835,7 +4833,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, round_down(offset, 1 << blkbits)) >> blkbits, new_size, flags, mode); if (ret) - goto out_mutex; + goto out_dio; } @@ -4844,10 +4842,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - /* * Prevent page faults from reinstantiating pages we have * released from page cache. @@ -4992,8 +4986,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + ext4_inode_resume_unlocked_dio(inode); if (ret) goto out; -- cgit v1.2.3 From 1f7b7e9a4ba3d60af27c78a149743d269e6fb848 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 14:31:11 -0500 Subject: ext4: fix races between buffered IO and collapse / insert range commit 32ebffd3bbb4162da5ff88f9a35dd32d0a28ea70 upstream. Current code implementing FALLOC_FL_COLLAPSE_RANGE and FALLOC_FL_INSERT_RANGE is prone to races with buffered writes and page faults. If buffered write or write via mmap manages to squeeze between filemap_write_and_wait_range() and truncate_pagecache() in the fallocate implementations, the written data is simply discarded by truncate_pagecache() although it should have been shifted. Fix the problem by moving filemap_write_and_wait_range() call inside i_mutex and i_mmap_sem. That way we are protected against races with both buffered writes and page faults. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/extents.c | 59 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 31 insertions(+), 28 deletions(-) (limited to 'fs') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 65b5ada2833f..4b105c96df08 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5487,21 +5487,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down offset to be aligned with page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation @@ -5526,6 +5512,27 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) * page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down offset to be aligned with page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* + * Write tail of the last page before removed range since it will get + * removed from the page cache below. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset); + if (ret) + goto out_mmap; + /* + * Write data that will be shifted to preserve them when discarding + * page cache below. We are also protected from pages becoming dirty + * by i_mmap_sem. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset + len, + LLONG_MAX); + if (ret) + goto out_mmap; truncate_pagecache(inode, ioffset); credits = ext4_writepage_trans_blocks(inode); @@ -5626,21 +5633,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down to align start offset to page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; @@ -5668,6 +5661,16 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) * page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down to align start offset to page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* Write out all dirty pages */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, + LLONG_MAX); + if (ret) + goto out_mmap; truncate_pagecache(inode, ioffset); credits = ext4_writepage_trans_blocks(inode); -- cgit v1.2.3 From 21228341bf17496062b0e6a1b37265f6bcf5c8f3 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 14:34:49 -0500 Subject: ext4: fix races of writeback with punch hole and zero range commit 011278485ecc3cd2a3954b5d4c73101d919bf1fa upstream. When doing delayed allocation, update of on-disk inode size is postponed until IO submission time. However hole punch or zero range fallocate calls can end up discarding the tail page cache page and thus on-disk inode size would never be properly updated. Make sure the on-disk inode size is updated before truncating page cache. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/ext4.h | 3 +++ fs/ext4/extents.c | 5 +++++ fs/ext4/inode.c | 35 ++++++++++++++++++++++++++++++++++- 3 files changed, 42 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 89df9f55595b..b7e921d207fb 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2881,6 +2881,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) return changed; } +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len); + struct ext4_group_info { unsigned long bb_state; struct rb_root bb_free_root; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4b105c96df08..3578b25fccfd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4847,6 +4847,11 @@ static long ext4_zero_range(struct file *file, loff_t offset, * released from page cache. */ down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_update_disksize_before_punch(inode, offset, len); + if (ret) { + up_write(&EXT4_I(inode)->i_mmap_sem); + goto out_dio; + } /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 214e30a3ef9e..e31d762eedce 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3586,6 +3586,35 @@ int ext4_can_truncate(struct inode *inode) return 0; } +/* + * We have to make sure i_disksize gets properly updated before we truncate + * page cache due to hole punching or zero range. Otherwise i_disksize update + * can get lost as it may have been postponed to submission of writeback but + * that will never happen after we truncate page cache. + */ +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len) +{ + handle_t *handle; + loff_t size = i_size_read(inode); + + WARN_ON(!mutex_is_locked(&inode->i_mutex)); + if (offset > size || offset + len < size) + return 0; + + if (EXT4_I(inode)->i_disksize >= size) + return 0; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_update_i_disksize(inode, size); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + + return 0; +} + /* * ext4_punch_hole: punches a hole in a file by releaseing the blocks * associated with the given offset and length @@ -3664,9 +3693,13 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; /* Now release the pages and zero block aligned part of pages*/ - if (last_block_offset > first_block_offset) + if (last_block_offset > first_block_offset) { + ret = ext4_update_disksize_before_punch(inode, offset, length); + if (ret) + goto out_dio; truncate_pagecache_range(inode, first_block_offset, last_block_offset); + } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); -- cgit v1.2.3