From daf60d6cca26e50d65dac374db92e58de745ad26 Mon Sep 17 00:00:00 2001 From: gaoming Date: Wed, 5 Jul 2023 15:15:15 +0800 Subject: [PATCH 1/3] exfat: use kvmalloc_array/kvfree instead of kmalloc_array/kfree The call stack shown below is a scenario in the Linux 4.19 kernel. Allocating memory failed where exfat fs use kmalloc_array due to system memory fragmentation, while the u-disk was inserted without recognition. Devices such as u-disk using the exfat file system are pluggable and may be insert into the system at any time. However, long-term running systems cannot guarantee the continuity of physical memory. Therefore, it's necessary to address this issue. Binder:2632_6: page allocation failure: order:4, mode:0x6040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null) Call trace: [242178.097582] dump_backtrace+0x0/0x4 [242178.097589] dump_stack+0xf4/0x134 [242178.097598] warn_alloc+0xd8/0x144 [242178.097603] __alloc_pages_nodemask+0x1364/0x1384 [242178.097608] kmalloc_order+0x2c/0x510 [242178.097612] kmalloc_order_trace+0x40/0x16c [242178.097618] __kmalloc+0x360/0x408 [242178.097624] load_alloc_bitmap+0x160/0x284 [242178.097628] exfat_fill_super+0xa3c/0xe7c [242178.097635] mount_bdev+0x2e8/0x3a0 [242178.097638] exfat_fs_mount+0x40/0x50 [242178.097643] mount_fs+0x138/0x2e8 [242178.097649] vfs_kern_mount+0x90/0x270 [242178.097655] do_mount+0x798/0x173c [242178.097659] ksys_mount+0x114/0x1ac [242178.097665] __arm64_sys_mount+0x24/0x34 [242178.097671] el0_svc_common+0xb8/0x1b8 [242178.097676] el0_svc_handler+0x74/0x90 [242178.097681] el0_svc+0x8/0x340 By analyzing the exfat code,we found that continuous physical memory is not required here,so kvmalloc_array is used can solve this problem. Cc: stable@vger.kernel.org Signed-off-by: gaoming Signed-off-by: Namjae Jeon --- fs/exfat/balloc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 9f42f25fab92..e918decb3735 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -69,7 +69,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, } sbi->map_sectors = ((need_map_size - 1) >> (sb->s_blocksize_bits)) + 1; - sbi->vol_amap = kmalloc_array(sbi->map_sectors, + sbi->vol_amap = kvmalloc_array(sbi->map_sectors, sizeof(struct buffer_head *), GFP_KERNEL); if (!sbi->vol_amap) return -ENOMEM; @@ -84,7 +84,7 @@ static int exfat_allocate_bitmap(struct super_block *sb, while (j < i) brelse(sbi->vol_amap[j++]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); sbi->vol_amap = NULL; return -EIO; } @@ -138,7 +138,7 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi) for (i = 0; i < sbi->map_sectors; i++) __brelse(sbi->vol_amap[i]); - kfree(sbi->vol_amap); + kvfree(sbi->vol_amap); } int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) From d42334578eba1390859012ebb91e1e556d51db49 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 13 Jul 2023 21:59:37 +0900 Subject: [PATCH 2/3] exfat: check if filename entries exceeds max filename length exfat_extract_uni_name copies characters from a given file name entry into the 'uniname' variable. This variable is actually defined on the stack of the exfat_readdir() function. According to the definition of the 'exfat_uni_name' type, the file name should be limited 255 characters (+ null teminator space), but the exfat_get_uniname_from_ext_entry() function can write more characters because there is no check if filename entries exceeds max filename length. This patch add the check not to copy filename characters when exceeding max filename length. Cc: stable@vger.kernel.org Cc: Yuezhang Mo Reported-by: Maxim Suhanov Reviewed-by: Sungjong Seo Signed-off-by: Namjae Jeon --- fs/exfat/dir.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index 957574180a5e..bc48f3329921 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -34,6 +34,7 @@ static int exfat_get_uniname_from_ext_entry(struct super_block *sb, { int i, err; struct exfat_entry_set_cache es; + unsigned int uni_len = 0, len; err = exfat_get_dentry_set(&es, sb, p_dir, entry, ES_ALL_ENTRIES); if (err) @@ -52,7 +53,10 @@ static int exfat_get_uniname_from_ext_entry(struct super_block *sb, if (exfat_get_entry_type(ep) != TYPE_EXTEND) break; - exfat_extract_uni_name(ep, uniname); + len = exfat_extract_uni_name(ep, uniname); + uni_len += len; + if (len != EXFAT_FILE_NAME_LEN || uni_len >= MAX_NAME_LENGTH) + break; uniname += EXFAT_FILE_NAME_LEN; } @@ -1079,7 +1083,8 @@ rewind: if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; - if (step != DIRENT_STEP_NAME) { + if (step != DIRENT_STEP_NAME || + name_len >= MAX_NAME_LENGTH) { step = DIRENT_STEP_FILE; continue; } From ff84772fd45d486e4fc78c82e2f70ce5333543e6 Mon Sep 17 00:00:00 2001 From: Sungjong Seo Date: Fri, 14 Jul 2023 17:43:54 +0900 Subject: [PATCH 3/3] exfat: release s_lock before calling dir_emit() There is a potential deadlock reported by syzbot as below: ====================================================== WARNING: possible circular locking dependency detected 6.4.0-next-20230707-syzkaller #0 Not tainted ------------------------------------------------------ syz-executor330/5073 is trying to acquire lock: ffff8880218527a0 (&mm->mmap_lock){++++}-{3:3}, at: mmap_read_lock_killable include/linux/mmap_lock.h:151 [inline] ffff8880218527a0 (&mm->mmap_lock){++++}-{3:3}, at: get_mmap_lock_carefully mm/memory.c:5293 [inline] ffff8880218527a0 (&mm->mmap_lock){++++}-{3:3}, at: lock_mm_and_find_vma+0x369/0x510 mm/memory.c:5344 but task is already holding lock: ffff888019f760e0 (&sbi->s_lock){+.+.}-{3:3}, at: exfat_iterate+0x117/0xb50 fs/exfat/dir.c:232 which lock already depends on the new lock. Chain exists of: &mm->mmap_lock --> mapping.invalidate_lock#3 --> &sbi->s_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sbi->s_lock); lock(mapping.invalidate_lock#3); lock(&sbi->s_lock); rlock(&mm->mmap_lock); Let's try to avoid above potential deadlock condition by moving dir_emit*() out of sbi->s_lock coverage. Fixes: ca06197382bd ("exfat: add directory operations") Cc: stable@vger.kernel.org #v5.7+ Reported-by: syzbot+1741a5d9b79989c10bdc@syzkaller.appspotmail.com Link: https://lore.kernel.org/lkml/00000000000078ee7e060066270b@google.com/T/#u Tested-by: syzbot+1741a5d9b79989c10bdc@syzkaller.appspotmail.com Signed-off-by: Sungjong Seo Signed-off-by: Namjae Jeon --- fs/exfat/dir.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index bc48f3329921..598081d0d059 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -218,7 +218,10 @@ static void exfat_free_namebuf(struct exfat_dentry_namebuf *nb) exfat_init_namebuf(nb); } -/* skip iterating emit_dots when dir is empty */ +/* + * Before calling dir_emit*(), sbi->s_lock should be released + * because page fault can occur in dir_emit*(). + */ #define ITER_POS_FILLED_DOTS (2) static int exfat_iterate(struct file *file, struct dir_context *ctx) { @@ -233,11 +236,10 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) int err = 0, fake_offset = 0; exfat_init_namebuf(nb); - mutex_lock(&EXFAT_SB(sb)->s_lock); cpos = ctx->pos; if (!dir_emit_dots(file, ctx)) - goto unlock; + goto out; if (ctx->pos == ITER_POS_FILLED_DOTS) { cpos = 0; @@ -249,16 +251,18 @@ static int exfat_iterate(struct file *file, struct dir_context *ctx) /* name buffer should be allocated before use */ err = exfat_alloc_namebuf(nb); if (err) - goto unlock; + goto out; get_new: + mutex_lock(&EXFAT_SB(sb)->s_lock); + if (ei->flags == ALLOC_NO_FAT_CHAIN && cpos >= i_size_read(inode)) goto end_of_dir; err = exfat_readdir(inode, &cpos, &de); if (err) { /* - * At least we tried to read a sector. Move cpos to next sector - * position (should be aligned). + * At least we tried to read a sector. + * Move cpos to next sector position (should be aligned). */ if (err == -EIO) { cpos += 1 << (sb->s_blocksize_bits); @@ -281,16 +285,10 @@ get_new: inum = iunique(sb, EXFAT_ROOT_INO); } - /* - * Before calling dir_emit(), sb_lock should be released. - * Because page fault can occur in dir_emit() when the size - * of buffer given from user is larger than one page size. - */ mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!dir_emit(ctx, nb->lfn, strlen(nb->lfn), inum, (de.attr & ATTR_SUBDIR) ? DT_DIR : DT_REG)) - goto out_unlocked; - mutex_lock(&EXFAT_SB(sb)->s_lock); + goto out; ctx->pos = cpos; goto get_new; @@ -298,9 +296,8 @@ end_of_dir: if (!cpos && fake_offset) cpos = ITER_POS_FILLED_DOTS; ctx->pos = cpos; -unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); -out_unlocked: +out: /* * To improve performance, free namebuf after unlock sb_lock. * If namebuf is not allocated, this function do nothing