[syzbot] [trace?] [block?] KASAN: slab-use-after-free Read in blk_log_remap

[syzbot] [trace?] [block?] KASAN: slab-use-after-free Read in blk_log_remap

[syzbot]

Hello,

syzbot found the following issue on:

HEAD commit:    818bebeb63dd drm/xe: Don't hand out the flat CCS storage a..
git tree:       git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
console output: https://syzkaller.appspot.com/x/log.txt?x=1070f625580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=ccca94d2c01b9e78
dashboard link: https://syzkaller.appspot.com/bug?extid=4dfd96209d744263a972
compiler:       gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=10608c15580000

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+4dfd96209d744263a972@syzkaller.appspotmail.com

==================================================================
BUG: KASAN: slab-use-after-free in blk_log_remap+0x128/0x150 kernel/trace/blktrace.c:1635
Read of size 8 at addr ffff888046c23000 by task syz-executor875/6044

CPU: 1 UID: 0 PID: 6044 Comm: syz-executor875 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x100/0x190 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0x13d/0x4b0 mm/kasan/report.c:482
 kasan_report+0xdf/0x1c0 mm/kasan/report.c:595
 blk_log_remap+0x128/0x150 kernel/trace/blktrace.c:1635
 print_one_line+0x22f/0x430 kernel/trace/blktrace.c:1757
 print_trace_fmt kernel/trace/trace.c:3071 [inline]
 print_trace_line+0x97d/0x1790 kernel/trace/trace.c:3237
 tracing_read_pipe+0x586/0xd60 kernel/trace/trace.c:5446
 vfs_read+0x1e4/0xb40 fs/read_write.c:572
 ksys_read+0x12a/0x250 fs/read_write.c:716
 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline]
 do_syscall_64+0x123/0x790 arch/x86/entry/syscall_64.c:84
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fb70f890b9e
Code: 08 0f 85 f5 e2 ff ff 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 89 5c 24 08 0f 05 <c3> 90 41 57 41 56 4d 89 c6 41 55 4d 89 cd 41 54 55 53 48 83 ec 08
RSP: 002b:00007fb70f8201a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
RAX: ffffffffffffffda RBX: 00007fb70f8216c0 RCX: 00007fb70f890b9e
RDX: 0000000000001000 RSI: 00007fb70f820210 RDI: 0000000000000006
RBP: 0000000000000021 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: ffffffffffffffd0
R13: 0000000000000000 R14: 00007ffe57b20df0 R15: 00007ffe57b20ed8
 </TASK>

Allocated by task 5868:
 kasan_save_stack+0x30/0x50 mm/kasan/common.c:57
 kasan_save_track+0x14/0x30 mm/kasan/common.c:78
 unpoison_slab_object mm/kasan/common.c:340 [inline]
 __kasan_slab_alloc+0x89/0x90 mm/kasan/common.c:366
 kasan_slab_alloc include/linux/kasan.h:253 [inline]
 slab_post_alloc_hook mm/slub.c:4586 [inline]
 slab_alloc_node mm/slub.c:4919 [inline]
 kmem_cache_alloc_noprof+0x26b/0x6a0 mm/slub.c:4933
 __kernfs_new_node+0xd2/0xa10 fs/kernfs/dir.c:665
 kernfs_new_node+0x117/0x150 fs/kernfs/dir.c:751
 __kernfs_create_file+0x53/0x350 fs/kernfs/file.c:1050
 sysfs_add_file_mode_ns+0x207/0x3c0 fs/sysfs/file.c:316
 create_files fs/sysfs/group.c:82 [inline]
 internal_create_group+0x593/0xfb0 fs/sysfs/group.c:189
 internal_create_groups+0x9d/0x150 fs/sysfs/group.c:229
 device_add_groups drivers/base/core.c:2911 [inline]
 device_add_attrs drivers/base/core.c:2975 [inline]
 device_add+0x71a/0x1970 drivers/base/core.c:3715
 netdev_register_kobject+0x1df/0x410 net/core/net-sysfs.c:2340
 register_netdevice+0x15b6/0x25a0 net/core/dev.c:11503
 xfrmi_create net/xfrm/xfrm_interface_core.c:252 [inline]
 xfrmi_newlink+0x22e/0x560 net/xfrm/xfrm_interface_core.c:855
 rtnl_newlink_create net/core/rtnetlink.c:3969 [inline]
 __rtnl_newlink net/core/rtnetlink.c:4098 [inline]
 rtnl_newlink+0x1697/0x2620 net/core/rtnetlink.c:4215
 rtnetlink_rcv_msg+0x95e/0xe90 net/core/rtnetlink.c:7132
 netlink_rcv_skb+0x159/0x420 net/netlink/af_netlink.c:2556
 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
 netlink_unicast+0x585/0x850 net/netlink/af_netlink.c:1345
 netlink_sendmsg+0x8b0/0xda0 net/netlink/af_netlink.c:1900
 sock_sendmsg_nosec net/socket.c:800 [inline]
 __sock_sendmsg net/socket.c:815 [inline]
 __sys_sendto+0x48b/0x4e0 net/socket.c:2281
 __do_sys_sendto net/socket.c:2288 [inline]
 __se_sys_sendto net/socket.c:2284 [inline]
 __x64_sys_sendto+0xe0/0x1c0 net/socket.c:2284
 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline]
 do_syscall_64+0x123/0x790 arch/x86/entry/syscall_64.c:84
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 5124:
 kasan_save_stack+0x30/0x50 mm/kasan/common.c:57
 kasan_save_track+0x14/0x30 mm/kasan/common.c:78
 kasan_save_free_info+0x3b/0x70 mm/kasan/generic.c:584
 poison_slab_object mm/kasan/common.c:253 [inline]
 __kasan_slab_free+0x5f/0x80 mm/kasan/common.c:285
 kasan_slab_free include/linux/kasan.h:235 [inline]
 slab_free_hook mm/slub.c:2678 [inline]
 slab_free mm/slub.c:6372 [inline]
 kmem_cache_free+0x127/0x6b0 mm/slub.c:6499
 rcu_do_batch kernel/rcu/tree.c:2645 [inline]
 rcu_core+0x5a2/0x10e0 kernel/rcu/tree.c:2897
 handle_softirqs+0x1e6/0x9d0 kernel/softirq.c:645
 do_softirq kernel/softirq.c:546 [inline]
 do_softirq+0xaf/0xf0 kernel/softirq.c:533
 __local_bh_enable_ip+0xff/0x120 kernel/softirq.c:473
 local_bh_enable include/linux/bottom_half.h:33 [inline]
 __alloc_skb+0x5db/0x710 net/core/skbuff.c:699
 alloc_skb include/linux/skbuff.h:1384 [inline]
 alloc_skb_with_frags+0xdd/0x760 net/core/skbuff.c:6775
 sock_alloc_send_pskb+0x801/0x980 net/core/sock.c:3012
 unix_dgram_sendmsg+0x3c7/0x1810 net/unix/af_unix.c:2144
 sock_sendmsg_nosec net/socket.c:800 [inline]
 __sock_sendmsg net/socket.c:815 [inline]
 __sys_sendto+0x48b/0x4e0 net/socket.c:2281
 __do_sys_sendto net/socket.c:2288 [inline]
 __se_sys_sendto net/socket.c:2284 [inline]
 __x64_sys_sendto+0xe0/0x1c0 net/socket.c:2284
 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline]
 do_syscall_64+0x123/0x790 arch/x86/entry/syscall_64.c:84
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Last potentially related work creation:
 kasan_save_stack+0x30/0x50 mm/kasan/common.c:57
 kasan_record_aux_stack+0xa7/0xc0 mm/kasan/generic.c:556
 __call_rcu_common.constprop.0+0xa5/0x9b0 kernel/rcu/tree.c:3159
 kernfs_put.part.0+0x3a6/0xaa0 fs/kernfs/dir.c:618
 kernfs_put fs/kernfs/dir.c:1787 [inline]
 kernfs_remove_by_name_ns+0xf3/0x120 fs/kernfs/dir.c:1798
 kernfs_remove_by_name include/linux/kernfs.h:644 [inline]
 remove_files+0x96/0x1c0 fs/sysfs/group.c:28
 sysfs_remove_group+0x8b/0x1b0 fs/sysfs/group.c:328
 sysfs_remove_groups fs/sysfs/group.c:352 [inline]
 sysfs_remove_groups+0x60/0xb0 fs/sysfs/group.c:344
 device_remove_groups drivers/base/core.c:2918 [inline]
 device_remove_attrs+0x203/0x290 drivers/base/core.c:3054
 device_del+0x36e/0x9b0 drivers/base/core.c:3964
 unregister_netdevice_many_notify+0x1503/0x2150 net/core/dev.c:12551
 ops_exit_rtnl_list net/core/net_namespace.c:188 [inline]
 ops_undo_list+0x8ff/0xab0 net/core/net_namespace.c:249
 cleanup_net+0x499/0x920 net/core/net_namespace.c:706
 process_one_work+0xac7/0x1b10 kernel/workqueue.c:3387
 process_scheduled_works kernel/workqueue.c:3470 [inline]
 worker_thread+0x5ef/0xe50 kernel/workqueue.c:3551
 kthread+0x373/0x450 kernel/kthread.c:436
 ret_from_fork+0x730/0xd60 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245

The buggy address belongs to the object at ffff888046c23000
 which belongs to the cache kernfs_node_cache of size 176
The buggy address is located 0 bytes inside of
 freed 176-byte region [ffff888046c23000, ffff888046c230b0)

The buggy address belongs to the physical page:
page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888046c23690 pfn:0x46c23
flags: 0xfff00000000200(workingset|node=0|zone=1|lastcpupid=0x7ff)
page_type: f5(slab)
raw: 00fff00000000200 ffff88801dede500 ffffea00011b07d0 ffffea00011b09d0
raw: ffff888046c23690 0000000800110009 00000000f5000000 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 0, migratetype Unmovable, gfp_mask 0xd2cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 5868, tgid 5868 (syz-executor), ts 72534727158
 set_page_owner include/linux/page_owner.h:33 [inline]
 post_alloc_hook+0xfd/0x120 mm/page_alloc.c:1871
 prep_new_page mm/page_alloc.c:1879 [inline]
 get_page_from_freelist+0x110d/0x35b0 mm/page_alloc.c:3943
 __alloc_frozen_pages_noprof+0x2eb/0x3300 mm/page_alloc.c:5436
 alloc_slab_page mm/slub.c:3267 [inline]
 allocate_slab mm/slub.c:3382 [inline]
 new_slab+0xa5/0x640 mm/slub.c:3428
 refill_objects+0xe3/0x410 mm/slub.c:7305
 refill_sheaf mm/slub.c:2805 [inline]
 __pcs_replace_empty_main+0x372/0x680 mm/slub.c:4677
 alloc_from_pcs mm/slub.c:4775 [inline]
 slab_alloc_node mm/slub.c:4907 [inline]
 kmem_cache_alloc_noprof+0x46e/0x6a0 mm/slub.c:4933
 __kernfs_new_node+0xd2/0xa10 fs/kernfs/dir.c:665
 kernfs_new_node+0x117/0x150 fs/kernfs/dir.c:751
 kernfs_create_link+0xcc/0x240 fs/kernfs/symlink.c:39
 sysfs_do_create_link_sd+0x90/0x140 fs/sysfs/symlink.c:44
 sysfs_do_create_link fs/sysfs/symlink.c:80 [inline]
 sysfs_create_link+0x61/0xc0 fs/sysfs/symlink.c:92
 netdev_adjacent_sysfs_add net/core/dev.c:8764 [inline]
 __netdev_adjacent_dev_insert+0x819/0xbf0 net/core/dev.c:8820
 __netdev_adjacent_dev_link_lists net/core/dev.c:8897 [inline]
 __netdev_adjacent_dev_link_neighbour net/core/dev.c:8926 [inline]
 __netdev_upper_dev_link+0x3d8/0x7e0 net/core/dev.c:8986
 netdev_master_upper_dev_link+0x9f/0xd0 net/core/dev.c:9061
 batadv_hardif_enable_interface+0x87c/0xf80 net/batman-adv/hard-interface.c:845
page last free pid 5793 tgid 5793 ts 69952822053 stack trace:
 reset_page_owner include/linux/page_owner.h:26 [inline]
 __free_pages_prepare mm/page_alloc.c:1418 [inline]
 free_pages_prepare+0x586/0xe00 mm/page_alloc.c:1463
 __free_contig_range_common+0x14f/0x250 mm/page_alloc.c:7060
 __free_contig_range mm/page_alloc.c:7105 [inline]
 free_pages_bulk+0x12a/0x200 mm/page_alloc.c:5322
 vm_area_free_pages+0xad/0x2b0 mm/vmalloc.c:3462
 vfree mm/vmalloc.c:3511 [inline]
 vfree+0x108/0x730 mm/vmalloc.c:3485
 kcov_put kernel/kcov.c:447 [inline]
 kcov_put kernel/kcov.c:443 [inline]
 kcov_close+0x34/0x60 kernel/kcov.c:554
 __fput+0x3ff/0xb50 fs/file_table.c:512
 task_work_run+0x150/0x240 kernel/task_work.c:233
 exit_task_work include/linux/task_work.h:40 [inline]
 do_exit+0x951/0x2ae0 kernel/exit.c:1008
 do_group_exit+0xd5/0x2a0 kernel/exit.c:1151
 get_signal+0x1ec7/0x21e0 kernel/signal.c:3046
 arch_do_signal_or_restart+0x91/0x7e0 arch/x86/kernel/signal.c:337
 __exit_to_user_mode_loop kernel/entry/common.c:66 [inline]
 exit_to_user_mode_loop+0x139/0x700 kernel/entry/common.c:101
 __exit_to_user_mode_prepare include/linux/irq-entry-common.h:207 [inline]
 syscall_exit_to_user_mode_prepare include/linux/irq-entry-common.h:230 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:336 [inline]
 do_syscall_64+0x661/0x790 arch/x86/entry/syscall_64.c:89
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Memory state around the buggy address:
 ffff888046c22f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff888046c22f80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffff888046c23000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff888046c23080: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fa fb
 ffff888046c23100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================


---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.

syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.

If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title

If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.

If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)

If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report

If you want to undo deduplication, reply with:
#syz undup

Forwarded: [PATCH] blktrace: always record ftrace events as blk_io_trace2

[syzbot]

For archival purposes, forwarding an incoming command email to
linux-kernel@vger.kernel.org, syzkaller-bugs@googlegroups.com.

***

Subject: [PATCH] blktrace: always record ftrace events as blk_io_trace2
Author: adrianox@gmail.com

#syz test: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
The ftrace ring buffer always uses the v2 (blk_io_trace2) format, but
__blk_add_trace() switched the reserve size and record format on
bt->version. That field only describes the relay/classic blktrace record
format and must not change what goes into the ftrace buffer: the ftrace
readers (print_one_line() and friends) unconditionally parse blk_io_trace2.

The BLKTRACESETUP ioctl sets bt->version to 1. With the blk tracer also
enabled, __blk_add_trace() recorded a 48-byte v1 event into the ftrace
ring buffer, but the reader parses the 64-byte v2 layout, so pdu_start()
points 16 bytes past the PDU and blk_log_remap() reads out of bounds - a
use-after-free when the ring buffer page is resized concurrently.

Always use the v2 format in the blk_tracer path, and initialize
bt->version to 2 in blk_trace_setup_queue() so the sysfs-enabled path no
longer leaves it uninitialized.

Fixes: e48886b9d668 ("blktrace: for ftrace use correct trace format ver")
---
 kernel/trace/blktrace.c | 74 +++++++++++------------------------------
 1 file changed, 20 insertions(+), 54 deletions(-)

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 8cd2520b4c99..ae010969c144 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -385,66 +385,26 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		buffer = blk_tr->array_buffer.buffer;
 		trace_ctx = tracing_gen_ctx_flags(0);
-		switch (bt->version) {
-		case 1:
-			trace_len = sizeof(struct blk_io_trace);
-			break;
-		case 2:
-		default:
-			/*
-			 * ftrace always uses v2 (blk_io_trace2) format.
-			 *
-			 * For sysfs-enabled tracing path (enabled via
-			 * /sys/block/DEV/trace/enable), blk_trace_setup_queue()
-			 * never initializes bt->version, leaving it 0 from
-			 * kzalloc(). We must handle version==0 safely here.
-			 *
-			 * Fall through to default to ensure we never hit the
-			 * old bug where default set trace_len=0, causing
-			 * buffer underflow and memory corruption.
-			 *
-			 * Always use v2 format for ftrace and normalize
-			 * bt->version to 2 when uninitialized.
-			 */
-			trace_len = sizeof(struct blk_io_trace2);
-			if (bt->version == 0)
-				bt->version = 2;
-			break;
-		}
-		trace_len += pdu_len + cgid_len;
+		/*
+		 * The ftrace ring buffer always uses the v2 (blk_io_trace2)
+		 * format; the ftrace readers parse only that. bt->version
+		 * describes just the relay/classic blktrace record format.
+		 * Recording a v1-sized event here would shift pdu_start() 16
+		 * bytes past the PDU and make blk_log_remap() read past the
+		 * event (a use-after-free on concurrent buffer resize), and v1
+		 * cannot represent the newer 64-bit zone actions anyway.
+		 */
+		trace_len = sizeof(struct blk_io_trace2) + pdu_len + cgid_len;
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  trace_len, trace_ctx);
 		if (!event)
 			return;
 
 		tracing_record_cmdline(current);
-		switch (bt->version) {
-		case 1:
-			record_blktrace_event(ring_buffer_event_data(event),
-					      pid, cpu, sector, bytes,
-					      what, bt->dev, error, cgid, cgid_len,
-					      pdu_data, pdu_len);
-			break;
-		case 2:
-		default:
-			/*
-			 * Use v2 recording function (record_blktrace_event2)
-			 * which writes blk_io_trace2 structure with correct
-			 * field layout:
-			 *   - 32-bit pid at offset 28
-			 *   - 64-bit action at offset 32
-			 *
-			 * Fall through to default handles version==0 case
-			 * (from sysfs path), ensuring we always use correct
-			 * v2 recording function to match the v2 buffer
-			 * allocated above.
-			 */
-			record_blktrace_event2(ring_buffer_event_data(event),
-					       pid, cpu, sector, bytes,
-					       what, bt->dev, error, cgid, cgid_len,
-					       pdu_data, pdu_len);
-			break;
-		}
+		record_blktrace_event2(ring_buffer_event_data(event),
+				       pid, cpu, sector, bytes,
+				       what, bt->dev, error, cgid, cgid_len,
+				       pdu_data, pdu_len);
 
 		trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx);
 		return;
@@ -1913,6 +1873,12 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	bt->dev = bdev->bd_dev;
 	bt->act_mask = (u16)-1;
+	/*
+	 * This sysfs-enabled path feeds the ftrace blk tracer, which always
+	 * uses the v2 (blk_io_trace2) format. Initialize the version so it is
+	 * never left dangling as 0 for future consumers.
+	 */
+	bt->version = 2;
 
 	blk_trace_setup_lba(bt, bdev);
 
-- 
2.51.0