From: Greg Kroah-Hartman Date: Mon, 16 Dec 2019 13:41:44 +0000 (+0100) Subject: 4.9-stable patches X-Git-Tag: v5.4.4~29 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=f188a0de2ff83544c039589993a56dc8b6f52c45;p=thirdparty%2Fkernel%2Fstable-queue.git 4.9-stable patches added patches: ext4-fix-a-bug-in-ext4_wait_for_tail_page_commit.patch mm-shmem.c-cast-the-type-of-unmap_start-to-u64.patch --- diff --git a/queue-4.9/ext4-fix-a-bug-in-ext4_wait_for_tail_page_commit.patch b/queue-4.9/ext4-fix-a-bug-in-ext4_wait_for_tail_page_commit.patch new file mode 100644 index 00000000000..e18e33d6aad --- /dev/null +++ b/queue-4.9/ext4-fix-a-bug-in-ext4_wait_for_tail_page_commit.patch @@ -0,0 +1,120 @@ +From 565333a1554d704789e74205989305c811fd9c7a Mon Sep 17 00:00:00 2001 +From: yangerkun +Date: Thu, 19 Sep 2019 14:35:08 +0800 +Subject: ext4: fix a bug in ext4_wait_for_tail_page_commit + +From: yangerkun + +commit 565333a1554d704789e74205989305c811fd9c7a upstream. + +No need to wait for any commit once the page is fully truncated. +Besides, it may confuse e.g. concurrent ext4_writepage() with the page +still be dirty (will be cleared by truncate_pagecache() in +ext4_setattr()) but buffers has been freed; and then trigger a bug +show as below: + +[ 26.057508] ------------[ cut here ]------------ +[ 26.058531] kernel BUG at fs/ext4/inode.c:2134! +... +[ 26.088130] Call trace: +[ 26.088695] ext4_writepage+0x914/0xb28 +[ 26.089541] writeout.isra.4+0x1b4/0x2b8 +[ 26.090409] move_to_new_page+0x3b0/0x568 +[ 26.091338] __unmap_and_move+0x648/0x988 +[ 26.092241] unmap_and_move+0x48c/0xbb8 +[ 26.093096] migrate_pages+0x220/0xb28 +[ 26.093945] kernel_mbind+0x828/0xa18 +[ 26.094791] __arm64_sys_mbind+0xc8/0x138 +[ 26.095716] el0_svc_common+0x190/0x490 +[ 26.096571] el0_svc_handler+0x60/0xd0 +[ 26.097423] el0_svc+0x8/0xc + +Run the procedure (generate by syzkaller) parallel with ext3. + +void main() +{ + int fd, fd1, ret; + void *addr; + size_t length = 4096; + int flags; + off_t offset = 0; + char *str = "12345"; + + fd = open("a", O_RDWR | O_CREAT); + assert(fd >= 0); + + /* Truncate to 4k */ + ret = ftruncate(fd, length); + assert(ret == 0); + + /* Journal data mode */ + flags = 0xc00f; + ret = ioctl(fd, _IOW('f', 2, long), &flags); + assert(ret == 0); + + /* Truncate to 0 */ + fd1 = open("a", O_TRUNC | O_NOATIME); + assert(fd1 >= 0); + + addr = mmap(NULL, length, PROT_WRITE | PROT_READ, + MAP_SHARED, fd, offset); + assert(addr != (void *)-1); + + memcpy(addr, str, 5); + mbind(addr, length, 0, 0, 0, MPOL_MF_MOVE); +} + +And the bug will be triggered once we seen the below order. + +reproduce1 reproduce2 + +... | ... +truncate to 4k | +change to journal data mode | + | memcpy(set page dirty) +truncate to 0: | +ext4_setattr: | +... | +ext4_wait_for_tail_page_commit | + | mbind(trigger bug) +truncate_pagecache(clean dirty)| ... +... | + +mbind will call ext4_writepage() since the page still be dirty, and then +report the bug since the buffers has been free. Fix it by return +directly once offset equals to 0 which means the page has been fully +truncated. + +Reported-by: Hulk Robot +Signed-off-by: yangerkun +Link: https://lore.kernel.org/r/20190919063508.1045-1-yangerkun@huawei.com +Reviewed-by: Jan Kara +Signed-off-by: Theodore Ts'o +Signed-off-by: Greg Kroah-Hartman + +--- + fs/ext4/inode.c | 12 ++++++++---- + 1 file changed, 8 insertions(+), 4 deletions(-) + +--- a/fs/ext4/inode.c ++++ b/fs/ext4/inode.c +@@ -5080,11 +5080,15 @@ static void ext4_wait_for_tail_page_comm + + offset = inode->i_size & (PAGE_SIZE - 1); + /* +- * All buffers in the last page remain valid? Then there's nothing to +- * do. We do the check mainly to optimize the common PAGE_SIZE == +- * blocksize case ++ * If the page is fully truncated, we don't need to wait for any commit ++ * (and we even should not as __ext4_journalled_invalidatepage() may ++ * strip all buffers from the page but keep the page dirty which can then ++ * confuse e.g. concurrent ext4_writepage() seeing dirty page without ++ * buffers). Also we don't need to wait for any commit if all buffers in ++ * the page remain valid. This is most beneficial for the common case of ++ * blocksize == PAGESIZE. + */ +- if (offset > PAGE_SIZE - i_blocksize(inode)) ++ if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) + return; + while (1) { + page = find_lock_page(inode->i_mapping, diff --git a/queue-4.9/mm-shmem.c-cast-the-type-of-unmap_start-to-u64.patch b/queue-4.9/mm-shmem.c-cast-the-type-of-unmap_start-to-u64.patch new file mode 100644 index 00000000000..d55251ece7f --- /dev/null +++ b/queue-4.9/mm-shmem.c-cast-the-type-of-unmap_start-to-u64.patch @@ -0,0 +1,73 @@ +From aa71ecd8d86500da6081a72da6b0b524007e0627 Mon Sep 17 00:00:00 2001 +From: Chen Jun +Date: Sat, 30 Nov 2019 17:58:11 -0800 +Subject: mm/shmem.c: cast the type of unmap_start to u64 + +From: Chen Jun + +commit aa71ecd8d86500da6081a72da6b0b524007e0627 upstream. + +In 64bit system. sb->s_maxbytes of shmem filesystem is MAX_LFS_FILESIZE, +which equal LLONG_MAX. + +If offset > LLONG_MAX - PAGE_SIZE, offset + len < LLONG_MAX in +shmem_fallocate, which will pass the checking in vfs_fallocate. + + /* Check for wrap through zero too */ + if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) + return -EFBIG; + +loff_t unmap_start = round_up(offset, PAGE_SIZE) in shmem_fallocate +causes a overflow. + +Syzkaller reports a overflow problem in mm/shmem: + + UBSAN: Undefined behaviour in mm/shmem.c:2014:10 + signed integer overflow: '9223372036854775807 + 1' cannot be represented in type 'long long int' + CPU: 0 PID:17076 Comm: syz-executor0 Not tainted 4.1.46+ #1 + Hardware name: linux, dummy-virt (DT) + Call trace: + dump_backtrace+0x0/0x2c8 arch/arm64/kernel/traps.c:100 + show_stack+0x20/0x30 arch/arm64/kernel/traps.c:238 + __dump_stack lib/dump_stack.c:15 [inline] + ubsan_epilogue+0x18/0x70 lib/ubsan.c:164 + handle_overflow+0x158/0x1b0 lib/ubsan.c:195 + shmem_fallocate+0x6d0/0x820 mm/shmem.c:2104 + vfs_fallocate+0x238/0x428 fs/open.c:312 + SYSC_fallocate fs/open.c:335 [inline] + SyS_fallocate+0x54/0xc8 fs/open.c:239 + +The highest bit of unmap_start will be appended with sign bit 1 +(overflow) when calculate shmem_falloc.start: + + shmem_falloc.start = unmap_start >> PAGE_SHIFT. + +Fix it by casting the type of unmap_start to u64, when right shifted. + +This bug is found in LTS Linux 4.1. It also seems to exist in mainline. + +Link: http://lkml.kernel.org/r/1573867464-5107-1-git-send-email-chenjun102@huawei.com +Signed-off-by: Chen Jun +Reviewed-by: Andrew Morton +Cc: Hugh Dickins +Cc: Qian Cai +Cc: Kefeng Wang +Signed-off-by: Andrew Morton +Signed-off-by: Linus Torvalds +Signed-off-by: Greg Kroah-Hartman + +--- + mm/shmem.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/mm/shmem.c ++++ b/mm/shmem.c +@@ -2695,7 +2695,7 @@ static long shmem_fallocate(struct file + } + + shmem_falloc.waitq = &shmem_falloc_waitq; +- shmem_falloc.start = unmap_start >> PAGE_SHIFT; ++ shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; + shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; + spin_lock(&inode->i_lock); + inode->i_private = &shmem_falloc; diff --git a/queue-4.9/series b/queue-4.9/series index 0b7ecb37662..8d5f8999954 100644 --- a/queue-4.9/series +++ b/queue-4.9/series @@ -166,3 +166,5 @@ scsi-qla2xxx-always-check-the-qla2x00_wait_for_hba_o.patch powerpc-fix-vdso-clock_getres.patch reiserfs-fix-extended-attributes-on-the-root-directo.patch firmware-qcom-scm-ensure-a0-status-code-is-treated-as-signed.patch +mm-shmem.c-cast-the-type-of-unmap_start-to-u64.patch +ext4-fix-a-bug-in-ext4_wait_for_tail_page_commit.patch