From 3f8da3b7292abe93b6e14508b5f24358dbed1f94 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 18 Sep 2023 16:13:35 +0800 Subject: [PATCH 1/2] f2fs: fix to avoid NULL pointer dereference f2fs_write_end_io() stable inclusion from stable-v5.10.188 commit b39ef5b52f10b819bd0ceeb22e8f7df7800880ca category: bugfix issue: #I79GXD CVE: CVE-2023-2898 Signed-off-by: wanxiaoqing --------------------------------------- commit d8189834d4348ae608083e1f1f53792cfcc2a9bc upstream. butt3rflyh4ck reports a bug as below: When a thread always calls F2FS_IOC_RESIZE_FS to resize fs, if resize fs is failed, f2fs kernel thread would invoke callback function to update f2fs io info, it would call f2fs_write_end_io and may trigger null-ptr-deref in NODE_MAPPING. general protection fault, probably for non-canonical address KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037] RIP: 0010:NODE_MAPPING fs/f2fs/f2fs.h:1972 [inline] RIP: 0010:f2fs_write_end_io+0x727/0x1050 fs/f2fs/data.c:370 bio_endio+0x5af/0x6c0 block/bio.c:1608 req_bio_endio block/blk-mq.c:761 [inline] blk_update_request+0x5cc/0x1690 block/blk-mq.c:906 blk_mq_end_request+0x59/0x4c0 block/blk-mq.c:1023 lo_complete_rq+0x1c6/0x280 drivers/block/loop.c:370 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1101 __do_softirq+0x1d4/0x8ef kernel/softirq.c:571 run_ksoftirqd kernel/softirq.c:939 [inline] run_ksoftirqd+0x31/0x60 kernel/softirq.c:931 smpboot_thread_fn+0x659/0x9e0 kernel/smpboot.c:164 kthread+0x33e/0x440 kernel/kthread.c:379 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 The root cause is below race case can cause leaving dirty metadata in f2fs after filesystem is remount as ro: Thread A Thread B - f2fs_ioc_resize_fs - f2fs_readonly --- return false - f2fs_resize_fs - f2fs_remount - write_checkpoint - set f2fs as ro - free_segment_range - update meta_inode's data Then, if f2fs_put_super() fails to write_checkpoint due to readonly status, and meta_inode's dirty data will be writebacked after node_inode is put, finally, f2fs_write_end_io will access NULL pointer on sbi->node_inode. Thread A IRQ context - f2fs_put_super - write_checkpoint fails - iput(node_inode) - node_inode = NULL - iput(meta_inode) - write_inode_now - f2fs_write_meta_page - f2fs_write_end_io - NODE_MAPPING(sbi) : access NULL pointer on node_inode Fixes: b4b10061ef98 ("f2fs: refactor resize_fs to avoid meta updates in progress") Reported-by: butt3rflyh4ck Closes: https://lore.kernel.org/r/1684480657-2375-1-git-send-email-yangtiezhu@loongson.cn Tested-by: butt3rflyh4ck Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim Signed-off-by: Stefan Ghinea Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- fs/f2fs/f2fs.h | 2 +- fs/f2fs/file.c | 2 +- fs/f2fs/gc.c | 22 +++++++++++++++++++--- 3 files changed, 21 insertions(+), 5 deletions(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 14ea184d7460..aa1771913ea2 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3538,7 +3538,7 @@ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, bool force, unsigned int segno); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count); +int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d56fcace1821..30a257973e82 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3355,7 +3355,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) sizeof(block_count))) return -EFAULT; - return f2fs_resize_fs(sbi, block_count); + return f2fs_resize_fs(filp, block_count); } static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 10f9d453de21..cdf71e7773bd 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -7,6 +7,7 @@ */ #include #include +#include #include #include #include @@ -1995,8 +1996,9 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) } } -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) +int f2fs_resize_fs(struct file *filp, __u64 block_count) { + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); __u64 old_block_count, shrunk_blocks; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; unsigned int secs; @@ -2034,12 +2036,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) return -EINVAL; } + err = mnt_want_write_file(filp); + if (err) + return err; + shrunk_blocks = old_block_count - block_count; secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi)); /* stop other GC */ - if (!down_write_trylock(&sbi->gc_lock)) - return -EAGAIN; + if (!down_write_trylock(&sbi->gc_lock)) { + err = -EAGAIN; + goto out_drop_write; + } /* stop CP to protect MAIN_SEC in free_segment_range */ f2fs_lock_op(sbi); @@ -2059,10 +2067,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) out_unlock: f2fs_unlock_op(sbi); up_write(&sbi->gc_lock); +out_drop_write: + mnt_drop_write_file(filp); if (err) return err; freeze_super(sbi->sb); + + if (f2fs_readonly(sbi->sb)) { + thaw_super(sbi->sb); + return -EROFS; + } + down_write(&sbi->gc_lock); mutex_lock(&sbi->cp_mutex); -- Gitee From 8e8fb4a5cb6f73fcdfd65523ff2df5210c6470a7 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 18 Sep 2023 14:50:10 +0800 Subject: [PATCH 2/2] af_unix: Fix null-ptr-deref in unix_stream_sendpage(). stable inclusion from stable-v5.10.192 commit c080cee930303124624fe64fc504f66c815ee6b9 category: bugfix issue: #I7ZBXU CVE: CVE-2023-4622 Signed-off-by: wanxiaoqing --------------------------------------- Bing-Jhong Billy Jheng reported null-ptr-deref in unix_stream_sendpage() with detailed analysis and a nice repro. unix_stream_sendpage() tries to add data to the last skb in the peer's recv queue without locking the queue. If the peer's FD is passed to another socket and the socket's FD is passed to the peer, there is a loop between them. If we close both sockets without receiving FD, the sockets will be cleaned up by garbage collection. The garbage collection iterates such sockets and unlinks skb with FD from the socket's receive queue under the queue's lock. So, there is a race where unix_stream_sendpage() could access an skb locklessly that is being released by garbage collection, resulting in use-after-free. To avoid the issue, unix_stream_sendpage() must lock the peer's recv queue. Note the issue does not exist in 6.5+ thanks to the recent sendpage() refactoring. This patch is originally written by Linus Torvalds. BUG: unable to handle page fault for address: ffff988004dd6870 PF: supervisor read access in kernel mode PF: error_code(0x0000) - not-present page PGD 0 P4D 0 PREEMPT SMP PTI CPU: 4 PID: 297 Comm: garbage_uaf Not tainted 6.1.46 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:kmem_cache_alloc_node+0xa2/0x1e0 Code: c0 0f 84 32 01 00 00 41 83 fd ff 74 10 48 8b 00 48 c1 e8 3a 41 39 c5 0f 85 1c 01 00 00 41 8b 44 24 28 49 8b 3c 24 48 8d 4a 40 <49> 8b 1c 06 4c 89 f0 65 48 0f c7 0f 0f 94 c0 84 c0 74 a1 41 8b 44 RSP: 0018:ffffc9000079fac0 EFLAGS: 00000246 RAX: 0000000000000070 RBX: 0000000000000005 RCX: 000000000001a284 RDX: 000000000001a244 RSI: 0000000000400cc0 RDI: 000000000002eee0 RBP: 0000000000400cc0 R08: 0000000000400cc0 R09: 0000000000000003 R10: 0000000000000001 R11: 0000000000000000 R12: ffff888003970f00 R13: 00000000ffffffff R14: ffff988004dd6800 R15: 00000000000000e8 FS: 00007f174d6f3600(0000) GS:ffff88807db00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff988004dd6870 CR3: 00000000092be000 CR4: 00000000007506e0 PKRU: 55555554 Call Trace: ? __die_body.cold+0x1a/0x1f ? page_fault_oops+0xa9/0x1e0 ? fixup_exception+0x1d/0x310 ? exc_page_fault+0xa8/0x150 ? asm_exc_page_fault+0x22/0x30 ? kmem_cache_alloc_node+0xa2/0x1e0 ? __alloc_skb+0x16c/0x1e0 __alloc_skb+0x16c/0x1e0 alloc_skb_with_frags+0x48/0x1e0 sock_alloc_send_pskb+0x234/0x270 unix_stream_sendmsg+0x1f5/0x690 sock_sendmsg+0x5d/0x60 ____sys_sendmsg+0x210/0x260 ___sys_sendmsg+0x83/0xd0 ? kmem_cache_alloc+0xc6/0x1c0 ? avc_disable+0x20/0x20 ? percpu_counter_add_batch+0x53/0xc0 ? alloc_empty_file+0x5d/0xb0 ? alloc_file+0x91/0x170 ? alloc_file_pseudo+0x94/0x100 ? __fget_light+0x9f/0x120 __sys_sendmsg+0x54/0xa0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x69/0xd3 RIP: 0033:0x7f174d639a7d Code: 28 89 54 24 1c 48 89 74 24 10 89 7c 24 08 e8 8a c1 f4 ff 8b 54 24 1c 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 33 44 89 c7 48 89 44 24 08 e8 de c1 f4 ff 48 RSP: 002b:00007ffcb563ea50 EFLAGS: 00000293 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f174d639a7d RDX: 0000000000000000 RSI: 00007ffcb563eab0 RDI: 0000000000000007 RBP: 00007ffcb563eb10 R08: 0000000000000000 R09: 00000000ffffffff R10: 00000000004040a0 R11: 0000000000000293 R12: 00007ffcb563ec28 R13: 0000000000401398 R14: 0000000000403e00 R15: 00007f174d72c000 Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support") Reported-by: Bing-Jhong Billy Jheng Reviewed-by: Bing-Jhong Billy Jheng Co-developed-by: Linus Torvalds Signed-off-by: Linus Torvalds Signed-off-by: Kuniyuki Iwashima Signed-off-by: Greg Kroah-Hartman Signed-off-by: wanxiaoqing --- net/unix/af_unix.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 28721e9575b7..45aa3801e320 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2008,6 +2008,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, @@ -2047,6 +2048,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, init_scm = false; } + spin_lock(&other->sk_receive_queue.lock); skb = skb_peek_tail(&other->sk_receive_queue); if (tail && tail == skb) { skb = newskb; @@ -2077,14 +2079,11 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); + unix_scm_to_skb(&scm, skb, false); __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); } + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); -- Gitee