October 2024 - Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] svm: fix UAF/Double Free in svm
by Lin Ruifeng 25 Oct '24

25 Oct '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAZLJE CVE: NA Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- drivers/char/svm.c | 55 +++++++++++++++++++++++++++++++++------------- 1 file changed, 40 insertions(+), 15 deletions(-) diff --git a/drivers/char/svm.c b/drivers/char/svm.c index 4cd04ca378ff..d7f70f2019e2 100644 --- a/drivers/char/svm.c +++ b/drivers/char/svm.c @@ -1503,6 +1503,40 @@ static int svm_proc_load_flag(int __user *arg) return put_user(flag, arg); } +static void svm_vma_open(struct vm_area_struct *vma) +{ + struct page *page = vma->vm_private_data; + + if (page) + get_page(page); +} + +static void svm_vma_close(struct vm_area_struct *vma) +{ + struct page *page = vma->vm_private_data; + + put_page(page); +} + +/* avoid split */ +static int svm_vma_split(struct vm_area_struct *area, unsigned long addr) +{ + return -EINVAL; +} + +/* avoid mremap */ +static int svm_vma_mremap(struct vm_area_struct *area) +{ + return -EINVAL; +} + +static const struct vm_operations_struct svm_vma_ops = { + .open = svm_vma_open, + .close = svm_vma_close, + .split = svm_vma_split, + .mremap = svm_vma_mremap, +}; + static int svm_mmap(struct file *file, struct vm_area_struct *vma) { int err; @@ -1540,6 +1574,9 @@ static int svm_mmap(struct file *file, struct vm_area_struct *vma) dev_err(sdev->dev, "fail to remap 0x%pK err=%d\n", (void *)vma->vm_start, err); + + vma->vm_private_data = page; + vma->vm_ops = &svm_vma_ops; } else { if ((vma->vm_end < vma->vm_start) || ((vma->vm_end - vma->vm_start) > sdev->l2size)) @@ -1566,9 +1603,7 @@ static int svm_release_phys32(unsigned long __user *arg) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; - struct page *page = NULL; - pte_t *pte = NULL; - unsigned long phys, addr, offset; + unsigned long addr; unsigned int len = 0; if (arg == NULL) @@ -1578,28 +1613,18 @@ static int svm_release_phys32(unsigned long __user *arg) return -EFAULT; down_read(&mm->mmap_sem); - pte = svm_walk_pt(addr, NULL, &offset); - if (pte && pte_present(*pte)) { - phys = PFN_PHYS(pte_pfn(*pte)) + offset; - } else { - up_read(&mm->mmap_sem); - return -EINVAL; - } vma = find_vma(mm, addr); - if (!vma) { + if (!vma || addr != vma->vm_start) { up_read(&mm->mmap_sem); return -EFAULT; } - page = phys_to_page(phys); len = vma->vm_end - vma->vm_start; - __free_pages(page, get_order(len)); - up_read(&mm->mmap_sem); - return 0; + return vm_munmap(addr, len); } static unsigned long svm_sp_alloc_mem(unsigned long __user *arg) -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1 0/1] CVE-2024-43894
by Yongqiang Liu 25 Oct '24

25 Oct '24

Ma Ke (1): drm/client: fix null pointer dereference in drm_client_modeset_probe drivers/gpu/drm/drm_client_modeset.c | 5 +++++ 1 file changed, 5 insertions(+) -- 2.25.1

2 2

[PATCH OLK-6.6] jfs: Fix uaf in dbFreeBits
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Edward Adam Davis <eadavis(a)qq.com> stable inclusion from stable-v6.6.55 commit 4218b31ecc7af7e191768d32e32ed4386d8f9b76 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRCC CVE: CVE-2024-49903 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit d6c1b3599b2feb5c7291f5ac3a36e5fa7cedb234 ] [syzbot reported] ================================================================== BUG: KASAN: slab-use-after-free in __mutex_lock_common kernel/locking/mutex.c:587 [inline] BUG: KASAN: slab-use-after-free in __mutex_lock+0xfe/0xd70 kernel/locking/mutex.c:752 Read of size 8 at addr ffff8880229254b0 by task syz-executor357/5216 CPU: 0 UID: 0 PID: 5216 Comm: syz-executor357 Not tainted 6.11.0-rc3-syzkaller-00156-gd7a5aa4b3c00 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 __mutex_lock_common kernel/locking/mutex.c:587 [inline] __mutex_lock+0xfe/0xd70 kernel/locking/mutex.c:752 dbFreeBits+0x7ea/0xd90 fs/jfs/jfs_dmap.c:2390 dbFreeDmap fs/jfs/jfs_dmap.c:2089 [inline] dbFree+0x35b/0x680 fs/jfs/jfs_dmap.c:409 dbDiscardAG+0x8a9/0xa20 fs/jfs/jfs_dmap.c:1650 jfs_ioc_trim+0x433/0x670 fs/jfs/jfs_discard.c:100 jfs_ioctl+0x2d0/0x3e0 fs/jfs/ioctl.c:131 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 Freed by task 5218: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2252 [inline] slab_free mm/slub.c:4473 [inline] kfree+0x149/0x360 mm/slub.c:4594 dbUnmount+0x11d/0x190 fs/jfs/jfs_dmap.c:278 jfs_mount_rw+0x4ac/0x6a0 fs/jfs/jfs_mount.c:247 jfs_remount+0x3d1/0x6b0 fs/jfs/super.c:454 reconfigure_super+0x445/0x880 fs/super.c:1083 vfs_cmd_reconfigure fs/fsopen.c:263 [inline] vfs_fsconfig_locked fs/fsopen.c:292 [inline] __do_sys_fsconfig fs/fsopen.c:473 [inline] __se_sys_fsconfig+0xb6e/0xf80 fs/fsopen.c:345 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [Analysis] There are two paths (dbUnmount and jfs_ioc_trim) that generate race condition when accessing bmap, which leads to the occurrence of uaf. Use the lock s_umount to synchronize them, in order to avoid uaf caused by race condition. Reported-and-tested-by: syzbot+3c010e21296f33a5dc16(a)syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis <eadavis(a)qq.com> Signed-off-by: Dave Kleikamp <dave.kleikamp(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/jfs/jfs_discard.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/jfs/jfs_discard.c b/fs/jfs/jfs_discard.c index 575cb2ba74fc..5f4b305030ad 100644 --- a/fs/jfs/jfs_discard.c +++ b/fs/jfs/jfs_discard.c @@ -65,7 +65,7 @@ void jfs_issue_discard(struct inode *ip, u64 blkno, u64 nblocks) int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range) { struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; - struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; + struct bmap *bmp; struct super_block *sb = ipbmap->i_sb; int agno, agno_end; u64 start, end, minlen; @@ -83,10 +83,15 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range) if (minlen == 0) minlen = 1; + down_read(&sb->s_umount); + bmp = JFS_SBI(ip->i_sb)->bmap; + if (minlen > bmp->db_agsize || start >= bmp->db_mapsize || - range->len < sb->s_blocksize) + range->len < sb->s_blocksize) { + up_read(&sb->s_umount); return -EINVAL; + } if (end >= bmp->db_mapsize) end = bmp->db_mapsize - 1; @@ -100,6 +105,8 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range) trimmed += dbDiscardAG(ip, agno, minlen); agno++; } + + up_read(&sb->s_umount); range->len = trimmed << sb->s_blocksize_bits; return 0; -- 2.39.2

2 1

[PATCH OLK-6.6] jfs: check if leafidx greater than num leaves per dmap tree
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Edward Adam Davis <eadavis(a)qq.com> stable inclusion from stable-v6.6.55 commit 7fff9a9f866e99931cf6fa260288e55d01626582 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRAK CVE: CVE-2024-49902 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit d64ff0d2306713ff084d4b09f84ed1a8c75ecc32 ] syzbot report a out of bounds in dbSplit, it because dmt_leafidx greater than num leaves per dmap tree, add a checking for dmt_leafidx in dbFindLeaf. Shaggy: Modified sanity check to apply to control pages as well as leaf pages. Reported-and-tested-by: syzbot+dca05492eff41f604890(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=dca05492eff41f604890 Signed-off-by: Edward Adam Davis <eadavis(a)qq.com> Signed-off-by: Dave Kleikamp <dave.kleikamp(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/jfs/jfs_dmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 5713994328cb..7e8fa0c56a3d 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -2944,9 +2944,10 @@ static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; - int max_size; + int max_size, max_idx; max_size = is_ctl ? CTLTREESIZE : TREESIZE; + max_idx = is_ctl ? LPERCTL : LPERDMAP; /* first check the root of the tree to see if there is * sufficient free space. @@ -2978,6 +2979,8 @@ static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) */ assert(n < 4); } + if (le32_to_cpu(tp->dmt_leafidx) >= max_idx) + return -ENOSPC; /* set the return to the leftmost leaf describing sufficient * free space. -- 2.39.2

2 1

[PATCH OLK-6.6] btrfs: wait for fixup workers before stopping cleaner kthread during umount
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Filipe Manana <fdmanana(a)suse.com> stable inclusion from stable-v6.6.55 commit ed87190e9d9c80aad220fb6b0b03a84d22e2c95b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRA9 CVE: CVE-2024-49867 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 41fd1e94066a815a7ab0a7025359e9b40e4b3576 upstream. During unmount, at close_ctree(), we have the following steps in this order: 1) Park the cleaner kthread - this doesn't destroy the kthread, it basically halts its execution (wake ups against it work but do nothing); 2) We stop the cleaner kthread - this results in freeing the respective struct task_struct; 3) We call btrfs_stop_all_workers() which waits for any jobs running in all the work queues and then free the work queues. Syzbot reported a case where a fixup worker resulted in a crash when doing a delayed iput on its inode while attempting to wake up the cleaner at btrfs_add_delayed_iput(), because the task_struct of the cleaner kthread was already freed. This can happen during unmount because we don't wait for any fixup workers still running before we call kthread_stop() against the cleaner kthread, which stops and free all its resources. Fix this by waiting for any fixup workers at close_ctree() before we call kthread_stop() against the cleaner and run pending delayed iputs. The stack traces reported by syzbot were the following: BUG: KASAN: slab-use-after-free in __lock_acquire+0x77/0x2050 kernel/locking/lockdep.c:5065 Read of size 8 at addr ffff8880272a8a18 by task kworker/u8:3/52 CPU: 1 UID: 0 PID: 52 Comm: kworker/u8:3 Not tainted 6.12.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: btrfs-fixup btrfs_work_helper Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 __lock_acquire+0x77/0x2050 kernel/locking/lockdep.c:5065 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5825 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162 class_raw_spinlock_irqsave_constructor include/linux/spinlock.h:551 [inline] try_to_wake_up+0xb0/0x1480 kernel/sched/core.c:4154 btrfs_writepage_fixup_worker+0xc16/0xdf0 fs/btrfs/inode.c:2842 btrfs_work_helper+0x390/0xc50 fs/btrfs/async-thread.c:314 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa63/0x1850 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Allocated by task 2: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 unpoison_slab_object mm/kasan/common.c:319 [inline] __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:345 kasan_slab_alloc include/linux/kasan.h:247 [inline] slab_post_alloc_hook mm/slub.c:4086 [inline] slab_alloc_node mm/slub.c:4135 [inline] kmem_cache_alloc_node_noprof+0x16b/0x320 mm/slub.c:4187 alloc_task_struct_node kernel/fork.c:180 [inline] dup_task_struct+0x57/0x8c0 kernel/fork.c:1107 copy_process+0x5d1/0x3d50 kernel/fork.c:2206 kernel_clone+0x223/0x880 kernel/fork.c:2787 kernel_thread+0x1bc/0x240 kernel/fork.c:2849 create_kthread kernel/kthread.c:412 [inline] kthreadd+0x60d/0x810 kernel/kthread.c:765 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Freed by task 61: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:2343 [inline] slab_free mm/slub.c:4580 [inline] kmem_cache_free+0x1a2/0x420 mm/slub.c:4682 put_task_struct include/linux/sched/task.h:144 [inline] delayed_put_task_struct+0x125/0x300 kernel/exit.c:228 rcu_do_batch kernel/rcu/tree.c:2567 [inline] rcu_core+0xaaa/0x17a0 kernel/rcu/tree.c:2823 handle_softirqs+0x2c5/0x980 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637 irq_exit_rcu+0x9/0x30 kernel/softirq.c:649 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1037 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1037 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702 Last potentially related work creation: kasan_save_stack+0x3f/0x60 mm/kasan/common.c:47 __kasan_record_aux_stack+0xac/0xc0 mm/kasan/generic.c:541 __call_rcu_common kernel/rcu/tree.c:3086 [inline] call_rcu+0x167/0xa70 kernel/rcu/tree.c:3190 context_switch kernel/sched/core.c:5318 [inline] __schedule+0x184b/0x4ae0 kernel/sched/core.c:6675 schedule_idle+0x56/0x90 kernel/sched/core.c:6793 do_idle+0x56a/0x5d0 kernel/sched/idle.c:354 cpu_startup_entry+0x42/0x60 kernel/sched/idle.c:424 start_secondary+0x102/0x110 arch/x86/kernel/smpboot.c:314 common_startup_64+0x13e/0x147 The buggy address belongs to the object at ffff8880272a8000 which belongs to the cache task_struct of size 7424 The buggy address is located 2584 bytes inside of freed 7424-byte region [ffff8880272a8000, ffff8880272a9d00) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x272a8 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff) page_type: f5(slab) raw: 00fff00000000040 ffff88801bafa500 dead000000000122 0000000000000000 raw: 0000000000000000 0000000080040004 00000001f5000000 0000000000000000 head: 00fff00000000040 ffff88801bafa500 dead000000000122 0000000000000000 head: 0000000000000000 0000000080040004 00000001f5000000 0000000000000000 head: 00fff00000000003 ffffea00009caa01 ffffffffffffffff 0000000000000000 head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 2, tgid 2 (kthreadd), ts 71247381401, free_ts 71214998153 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1537 prep_new_page mm/page_alloc.c:1545 [inline] get_page_from_freelist+0x3039/0x3180 mm/page_alloc.c:3457 __alloc_pages_noprof+0x256/0x6c0 mm/page_alloc.c:4733 alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265 alloc_slab_page+0x6a/0x120 mm/slub.c:2413 allocate_slab+0x5a/0x2f0 mm/slub.c:2579 new_slab mm/slub.c:2632 [inline] ___slab_alloc+0xcd1/0x14b0 mm/slub.c:3819 __slab_alloc+0x58/0xa0 mm/slub.c:3909 __slab_alloc_node mm/slub.c:3962 [inline] slab_alloc_node mm/slub.c:4123 [inline] kmem_cache_alloc_node_noprof+0x1fe/0x320 mm/slub.c:4187 alloc_task_struct_node kernel/fork.c:180 [inline] dup_task_struct+0x57/0x8c0 kernel/fork.c:1107 copy_process+0x5d1/0x3d50 kernel/fork.c:2206 kernel_clone+0x223/0x880 kernel/fork.c:2787 kernel_thread+0x1bc/0x240 kernel/fork.c:2849 create_kthread kernel/kthread.c:412 [inline] kthreadd+0x60d/0x810 kernel/kthread.c:765 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 page last free pid 5230 tgid 5230 stack trace: reset_page_owner include/linux/page_owner.h:25 [inline] free_pages_prepare mm/page_alloc.c:1108 [inline] free_unref_page+0xcd0/0xf00 mm/page_alloc.c:2638 discard_slab mm/slub.c:2678 [inline] __put_partials+0xeb/0x130 mm/slub.c:3146 put_cpu_partial+0x17c/0x250 mm/slub.c:3221 __slab_free+0x2ea/0x3d0 mm/slub.c:4450 qlink_free mm/kasan/quarantine.c:163 [inline] qlist_free_all+0x9a/0x140 mm/kasan/quarantine.c:179 kasan_quarantine_reduce+0x14f/0x170 mm/kasan/quarantine.c:286 __kasan_slab_alloc+0x23/0x80 mm/kasan/common.c:329 kasan_slab_alloc include/linux/kasan.h:247 [inline] slab_post_alloc_hook mm/slub.c:4086 [inline] slab_alloc_node mm/slub.c:4135 [inline] kmem_cache_alloc_noprof+0x135/0x2a0 mm/slub.c:4142 getname_flags+0xb7/0x540 fs/namei.c:139 do_sys_openat2+0xd2/0x1d0 fs/open.c:1409 do_sys_open fs/open.c:1430 [inline] __do_sys_openat fs/open.c:1446 [inline] __se_sys_openat fs/open.c:1441 [inline] __x64_sys_openat+0x247/0x2a0 fs/open.c:1441 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Memory state around the buggy address: ffff8880272a8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880272a8980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880272a8a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880272a8a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880272a8b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Reported-by: syzbot+8aaf2df2ef0164ffe1fb(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/66fb36b1.050a0220.aab67.003b.GAE@google… CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/btrfs/disk-io.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index caedd4460d99..8ec411eb9c9b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4313,6 +4313,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * Wait for any fixup workers to complete. + * If we don't wait for them here and they are still running by the time + * we call kthread_stop() against the cleaner kthread further below, we + * get an use-after-free on the cleaner because the fixup worker adds an + * inode to the list of delayed iputs and then attempts to wakeup the + * cleaner kthread, which was already stopped and destroyed. We parked + * already the cleaner, but below we run all pending delayed iputs. + */ + btrfs_flush_workqueue(fs_info->fixup_workers); + /* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim -- 2.39.2

2 1

[PATCH OLK-6.6] btrfs: fix a NULL pointer dereference when failed to start a new trasacntion
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Qu Wenruo <wqu(a)suse.com> stable inclusion from stable-v6.6.55 commit 7ad0c5868f2f0418619089513d95230c66cb7eb4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRC7 CVE: CVE-2024-49868 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit c3b47f49e83197e8dffd023ec568403bcdbb774b upstream. [BUG] Syzbot reported a NULL pointer dereference with the following crash: FAULT_INJECTION: forcing a failure. start_transaction+0x830/0x1670 fs/btrfs/transaction.c:676 prepare_to_relocate+0x31f/0x4c0 fs/btrfs/relocation.c:3642 relocate_block_group+0x169/0xd20 fs/btrfs/relocation.c:3678 ... BTRFS info (device loop0): balance: ended with status: -12 Oops: general protection fault, probably for non-canonical address 0xdffffc00000000cc: 0000 [#1] PREEMPT SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000660-0x0000000000000667] RIP: 0010:btrfs_update_reloc_root+0x362/0xa80 fs/btrfs/relocation.c:926 Call Trace: <TASK> commit_fs_roots+0x2ee/0x720 fs/btrfs/transaction.c:1496 btrfs_commit_transaction+0xfaf/0x3740 fs/btrfs/transaction.c:2430 del_balance_item fs/btrfs/volumes.c:3678 [inline] reset_balance_state+0x25e/0x3c0 fs/btrfs/volumes.c:3742 btrfs_balance+0xead/0x10c0 fs/btrfs/volumes.c:4574 btrfs_ioctl_balance+0x493/0x7c0 fs/btrfs/ioctl.c:3673 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [CAUSE] The allocation failure happens at the start_transaction() inside prepare_to_relocate(), and during the error handling we call unset_reloc_control(), which makes fs_info->balance_ctl to be NULL. Then we continue the error path cleanup in btrfs_balance() by calling reset_balance_state() which will call del_balance_item() to fully delete the balance item in the root tree. However during the small window between set_reloc_contrl() and unset_reloc_control(), we can have a subvolume tree update and created a reloc_root for that subvolume. Then we go into the final btrfs_commit_transaction() of del_balance_item(), and into btrfs_update_reloc_root() inside commit_fs_roots(). That function checks if fs_info->reloc_ctl is in the merge_reloc_tree stage, but since fs_info->reloc_ctl is NULL, it results a NULL pointer dereference. [FIX] Just add extra check on fs_info->reloc_ctl inside btrfs_update_reloc_root(), before checking fs_info->reloc_ctl->merge_reloc_tree. That DEAD_RELOC_TREE handling is to prevent further modification to the reloc tree during merge stage, but since there is no reloc_ctl at all, we do not need to bother that. Reported-by: syzbot+283673dbc38527ef9f3d(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/66f6bfa7.050a0220.38ace9.0019.GAE@googl… CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/btrfs/relocation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 4eaac3ae5c36..05b2a59ce889 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -931,7 +931,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, btrfs_grab_root(reloc_root); /* root->reloc_root will stay until current relocation finished */ - if (fs_info->reloc_ctl->merge_reloc_tree && + if (fs_info->reloc_ctl && fs_info->reloc_ctl->merge_reloc_tree && btrfs_root_refs(root_item) == 0) { set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); /* -- 2.39.2

2 1

[PATCH OLK-5.10] jfs: Fix uaf in dbFreeBits
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Edward Adam Davis <eadavis(a)qq.com> stable inclusion from stable-v5.10.227 commit fd026b6b6758d5569705c02540b40f3bbf822b9a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRCC CVE: CVE-2024-49903 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit d6c1b3599b2feb5c7291f5ac3a36e5fa7cedb234 ] [syzbot reported] ================================================================== BUG: KASAN: slab-use-after-free in __mutex_lock_common kernel/locking/mutex.c:587 [inline] BUG: KASAN: slab-use-after-free in __mutex_lock+0xfe/0xd70 kernel/locking/mutex.c:752 Read of size 8 at addr ffff8880229254b0 by task syz-executor357/5216 CPU: 0 UID: 0 PID: 5216 Comm: syz-executor357 Not tainted 6.11.0-rc3-syzkaller-00156-gd7a5aa4b3c00 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 __mutex_lock_common kernel/locking/mutex.c:587 [inline] __mutex_lock+0xfe/0xd70 kernel/locking/mutex.c:752 dbFreeBits+0x7ea/0xd90 fs/jfs/jfs_dmap.c:2390 dbFreeDmap fs/jfs/jfs_dmap.c:2089 [inline] dbFree+0x35b/0x680 fs/jfs/jfs_dmap.c:409 dbDiscardAG+0x8a9/0xa20 fs/jfs/jfs_dmap.c:1650 jfs_ioc_trim+0x433/0x670 fs/jfs/jfs_discard.c:100 jfs_ioctl+0x2d0/0x3e0 fs/jfs/ioctl.c:131 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 Freed by task 5218: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2252 [inline] slab_free mm/slub.c:4473 [inline] kfree+0x149/0x360 mm/slub.c:4594 dbUnmount+0x11d/0x190 fs/jfs/jfs_dmap.c:278 jfs_mount_rw+0x4ac/0x6a0 fs/jfs/jfs_mount.c:247 jfs_remount+0x3d1/0x6b0 fs/jfs/super.c:454 reconfigure_super+0x445/0x880 fs/super.c:1083 vfs_cmd_reconfigure fs/fsopen.c:263 [inline] vfs_fsconfig_locked fs/fsopen.c:292 [inline] __do_sys_fsconfig fs/fsopen.c:473 [inline] __se_sys_fsconfig+0xb6e/0xf80 fs/fsopen.c:345 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [Analysis] There are two paths (dbUnmount and jfs_ioc_trim) that generate race condition when accessing bmap, which leads to the occurrence of uaf. Use the lock s_umount to synchronize them, in order to avoid uaf caused by race condition. Reported-and-tested-by: syzbot+3c010e21296f33a5dc16(a)syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis <eadavis(a)qq.com> Signed-off-by: Dave Kleikamp <dave.kleikamp(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/jfs/jfs_discard.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/jfs/jfs_discard.c b/fs/jfs/jfs_discard.c index 575cb2ba74fc..5f4b305030ad 100644 --- a/fs/jfs/jfs_discard.c +++ b/fs/jfs/jfs_discard.c @@ -65,7 +65,7 @@ void jfs_issue_discard(struct inode *ip, u64 blkno, u64 nblocks) int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range) { struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; - struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; + struct bmap *bmp; struct super_block *sb = ipbmap->i_sb; int agno, agno_end; u64 start, end, minlen; @@ -83,10 +83,15 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range) if (minlen == 0) minlen = 1; + down_read(&sb->s_umount); + bmp = JFS_SBI(ip->i_sb)->bmap; + if (minlen > bmp->db_agsize || start >= bmp->db_mapsize || - range->len < sb->s_blocksize) + range->len < sb->s_blocksize) { + up_read(&sb->s_umount); return -EINVAL; + } if (end >= bmp->db_mapsize) end = bmp->db_mapsize - 1; @@ -100,6 +105,8 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range) trimmed += dbDiscardAG(ip, agno, minlen); agno++; } + + up_read(&sb->s_umount); range->len = trimmed << sb->s_blocksize_bits; return 0; -- 2.39.2

2 1

[PATCH OLK-5.10] jfs: check if leafidx greater than num leaves per dmap tree
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Edward Adam Davis <eadavis(a)qq.com> stable inclusion from stable-v5.10.227 commit 2451e5917c56be45d4add786e2a059dd9c2c37c4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRAK CVE: CVE-2024-49902 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit d64ff0d2306713ff084d4b09f84ed1a8c75ecc32 ] syzbot report a out of bounds in dbSplit, it because dmt_leafidx greater than num leaves per dmap tree, add a checking for dmt_leafidx in dbFindLeaf. Shaggy: Modified sanity check to apply to control pages as well as leaf pages. Reported-and-tested-by: syzbot+dca05492eff41f604890(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=dca05492eff41f604890 Signed-off-by: Edward Adam Davis <eadavis(a)qq.com> Signed-off-by: Dave Kleikamp <dave.kleikamp(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/jfs/jfs_dmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 2bbdae936076..fa12fc979799 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -3011,9 +3011,10 @@ static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; - int max_size; + int max_size, max_idx; max_size = is_ctl ? CTLTREESIZE : TREESIZE; + max_idx = is_ctl ? LPERCTL : LPERDMAP; /* first check the root of the tree to see if there is * sufficient free space. @@ -3045,6 +3046,8 @@ static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) */ assert(n < 4); } + if (le32_to_cpu(tp->dmt_leafidx) >= max_idx) + return -ENOSPC; /* set the return to the leftmost leaf describing sufficient * free space. -- 2.39.2

2 1

[PATCH OLK-5.10] btrfs: wait for fixup workers before stopping cleaner kthread during umount
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Filipe Manana <fdmanana(a)suse.com> stable inclusion from stable-v5.10.227 commit 70b60c8d9b42763d6629e44f448aa5d8ae477d61 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRA9 CVE: CVE-2024-49867 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 41fd1e94066a815a7ab0a7025359e9b40e4b3576 upstream. During unmount, at close_ctree(), we have the following steps in this order: 1) Park the cleaner kthread - this doesn't destroy the kthread, it basically halts its execution (wake ups against it work but do nothing); 2) We stop the cleaner kthread - this results in freeing the respective struct task_struct; 3) We call btrfs_stop_all_workers() which waits for any jobs running in all the work queues and then free the work queues. Syzbot reported a case where a fixup worker resulted in a crash when doing a delayed iput on its inode while attempting to wake up the cleaner at btrfs_add_delayed_iput(), because the task_struct of the cleaner kthread was already freed. This can happen during unmount because we don't wait for any fixup workers still running before we call kthread_stop() against the cleaner kthread, which stops and free all its resources. Fix this by waiting for any fixup workers at close_ctree() before we call kthread_stop() against the cleaner and run pending delayed iputs. The stack traces reported by syzbot were the following: BUG: KASAN: slab-use-after-free in __lock_acquire+0x77/0x2050 kernel/locking/lockdep.c:5065 Read of size 8 at addr ffff8880272a8a18 by task kworker/u8:3/52 CPU: 1 UID: 0 PID: 52 Comm: kworker/u8:3 Not tainted 6.12.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: btrfs-fixup btrfs_work_helper Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 __lock_acquire+0x77/0x2050 kernel/locking/lockdep.c:5065 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5825 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162 class_raw_spinlock_irqsave_constructor include/linux/spinlock.h:551 [inline] try_to_wake_up+0xb0/0x1480 kernel/sched/core.c:4154 btrfs_writepage_fixup_worker+0xc16/0xdf0 fs/btrfs/inode.c:2842 btrfs_work_helper+0x390/0xc50 fs/btrfs/async-thread.c:314 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa63/0x1850 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Allocated by task 2: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 unpoison_slab_object mm/kasan/common.c:319 [inline] __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:345 kasan_slab_alloc include/linux/kasan.h:247 [inline] slab_post_alloc_hook mm/slub.c:4086 [inline] slab_alloc_node mm/slub.c:4135 [inline] kmem_cache_alloc_node_noprof+0x16b/0x320 mm/slub.c:4187 alloc_task_struct_node kernel/fork.c:180 [inline] dup_task_struct+0x57/0x8c0 kernel/fork.c:1107 copy_process+0x5d1/0x3d50 kernel/fork.c:2206 kernel_clone+0x223/0x880 kernel/fork.c:2787 kernel_thread+0x1bc/0x240 kernel/fork.c:2849 create_kthread kernel/kthread.c:412 [inline] kthreadd+0x60d/0x810 kernel/kthread.c:765 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Freed by task 61: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:2343 [inline] slab_free mm/slub.c:4580 [inline] kmem_cache_free+0x1a2/0x420 mm/slub.c:4682 put_task_struct include/linux/sched/task.h:144 [inline] delayed_put_task_struct+0x125/0x300 kernel/exit.c:228 rcu_do_batch kernel/rcu/tree.c:2567 [inline] rcu_core+0xaaa/0x17a0 kernel/rcu/tree.c:2823 handle_softirqs+0x2c5/0x980 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637 irq_exit_rcu+0x9/0x30 kernel/softirq.c:649 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1037 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1037 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702 Last potentially related work creation: kasan_save_stack+0x3f/0x60 mm/kasan/common.c:47 __kasan_record_aux_stack+0xac/0xc0 mm/kasan/generic.c:541 __call_rcu_common kernel/rcu/tree.c:3086 [inline] call_rcu+0x167/0xa70 kernel/rcu/tree.c:3190 context_switch kernel/sched/core.c:5318 [inline] __schedule+0x184b/0x4ae0 kernel/sched/core.c:6675 schedule_idle+0x56/0x90 kernel/sched/core.c:6793 do_idle+0x56a/0x5d0 kernel/sched/idle.c:354 cpu_startup_entry+0x42/0x60 kernel/sched/idle.c:424 start_secondary+0x102/0x110 arch/x86/kernel/smpboot.c:314 common_startup_64+0x13e/0x147 The buggy address belongs to the object at ffff8880272a8000 which belongs to the cache task_struct of size 7424 The buggy address is located 2584 bytes inside of freed 7424-byte region [ffff8880272a8000, ffff8880272a9d00) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x272a8 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff) page_type: f5(slab) raw: 00fff00000000040 ffff88801bafa500 dead000000000122 0000000000000000 raw: 0000000000000000 0000000080040004 00000001f5000000 0000000000000000 head: 00fff00000000040 ffff88801bafa500 dead000000000122 0000000000000000 head: 0000000000000000 0000000080040004 00000001f5000000 0000000000000000 head: 00fff00000000003 ffffea00009caa01 ffffffffffffffff 0000000000000000 head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 2, tgid 2 (kthreadd), ts 71247381401, free_ts 71214998153 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1537 prep_new_page mm/page_alloc.c:1545 [inline] get_page_from_freelist+0x3039/0x3180 mm/page_alloc.c:3457 __alloc_pages_noprof+0x256/0x6c0 mm/page_alloc.c:4733 alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265 alloc_slab_page+0x6a/0x120 mm/slub.c:2413 allocate_slab+0x5a/0x2f0 mm/slub.c:2579 new_slab mm/slub.c:2632 [inline] ___slab_alloc+0xcd1/0x14b0 mm/slub.c:3819 __slab_alloc+0x58/0xa0 mm/slub.c:3909 __slab_alloc_node mm/slub.c:3962 [inline] slab_alloc_node mm/slub.c:4123 [inline] kmem_cache_alloc_node_noprof+0x1fe/0x320 mm/slub.c:4187 alloc_task_struct_node kernel/fork.c:180 [inline] dup_task_struct+0x57/0x8c0 kernel/fork.c:1107 copy_process+0x5d1/0x3d50 kernel/fork.c:2206 kernel_clone+0x223/0x880 kernel/fork.c:2787 kernel_thread+0x1bc/0x240 kernel/fork.c:2849 create_kthread kernel/kthread.c:412 [inline] kthreadd+0x60d/0x810 kernel/kthread.c:765 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 page last free pid 5230 tgid 5230 stack trace: reset_page_owner include/linux/page_owner.h:25 [inline] free_pages_prepare mm/page_alloc.c:1108 [inline] free_unref_page+0xcd0/0xf00 mm/page_alloc.c:2638 discard_slab mm/slub.c:2678 [inline] __put_partials+0xeb/0x130 mm/slub.c:3146 put_cpu_partial+0x17c/0x250 mm/slub.c:3221 __slab_free+0x2ea/0x3d0 mm/slub.c:4450 qlink_free mm/kasan/quarantine.c:163 [inline] qlist_free_all+0x9a/0x140 mm/kasan/quarantine.c:179 kasan_quarantine_reduce+0x14f/0x170 mm/kasan/quarantine.c:286 __kasan_slab_alloc+0x23/0x80 mm/kasan/common.c:329 kasan_slab_alloc include/linux/kasan.h:247 [inline] slab_post_alloc_hook mm/slub.c:4086 [inline] slab_alloc_node mm/slub.c:4135 [inline] kmem_cache_alloc_noprof+0x135/0x2a0 mm/slub.c:4142 getname_flags+0xb7/0x540 fs/namei.c:139 do_sys_openat2+0xd2/0x1d0 fs/open.c:1409 do_sys_open fs/open.c:1430 [inline] __do_sys_openat fs/open.c:1446 [inline] __se_sys_openat fs/open.c:1441 [inline] __x64_sys_openat+0x247/0x2a0 fs/open.c:1441 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Memory state around the buggy address: ffff8880272a8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880272a8980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880272a8a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880272a8a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880272a8b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Reported-by: syzbot+8aaf2df2ef0164ffe1fb(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/66fb36b1.050a0220.aab67.003b.GAE@google… CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/btrfs/disk-io.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b923011dec85..5e42f339fa83 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4141,6 +4141,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * Wait for any fixup workers to complete. + * If we don't wait for them here and they are still running by the time + * we call kthread_stop() against the cleaner kthread further below, we + * get an use-after-free on the cleaner because the fixup worker adds an + * inode to the list of delayed iputs and then attempts to wakeup the + * cleaner kthread, which was already stopped and destroyed. We parked + * already the cleaner, but below we run all pending delayed iputs. + */ + btrfs_flush_workqueue(fs_info->fixup_workers); + /* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim -- 2.39.2

2 1

[PATCH OLK-5.10] btrfs: fix a NULL pointer dereference when failed to start a new trasacntion
by Yifan Qiao 25 Oct '24

25 Oct '24

From: Qu Wenruo <wqu(a)suse.com> stable inclusion from stable-v5.10.227 commit d73d48acf36f57362df7e4f9d76568168bf5e944 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRC7 CVE: CVE-2024-49868 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit c3b47f49e83197e8dffd023ec568403bcdbb774b upstream. [BUG] Syzbot reported a NULL pointer dereference with the following crash: FAULT_INJECTION: forcing a failure. start_transaction+0x830/0x1670 fs/btrfs/transaction.c:676 prepare_to_relocate+0x31f/0x4c0 fs/btrfs/relocation.c:3642 relocate_block_group+0x169/0xd20 fs/btrfs/relocation.c:3678 ... BTRFS info (device loop0): balance: ended with status: -12 Oops: general protection fault, probably for non-canonical address 0xdffffc00000000cc: 0000 [#1] PREEMPT SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000660-0x0000000000000667] RIP: 0010:btrfs_update_reloc_root+0x362/0xa80 fs/btrfs/relocation.c:926 Call Trace: <TASK> commit_fs_roots+0x2ee/0x720 fs/btrfs/transaction.c:1496 btrfs_commit_transaction+0xfaf/0x3740 fs/btrfs/transaction.c:2430 del_balance_item fs/btrfs/volumes.c:3678 [inline] reset_balance_state+0x25e/0x3c0 fs/btrfs/volumes.c:3742 btrfs_balance+0xead/0x10c0 fs/btrfs/volumes.c:4574 btrfs_ioctl_balance+0x493/0x7c0 fs/btrfs/ioctl.c:3673 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [CAUSE] The allocation failure happens at the start_transaction() inside prepare_to_relocate(), and during the error handling we call unset_reloc_control(), which makes fs_info->balance_ctl to be NULL. Then we continue the error path cleanup in btrfs_balance() by calling reset_balance_state() which will call del_balance_item() to fully delete the balance item in the root tree. However during the small window between set_reloc_contrl() and unset_reloc_control(), we can have a subvolume tree update and created a reloc_root for that subvolume. Then we go into the final btrfs_commit_transaction() of del_balance_item(), and into btrfs_update_reloc_root() inside commit_fs_roots(). That function checks if fs_info->reloc_ctl is in the merge_reloc_tree stage, but since fs_info->reloc_ctl is NULL, it results a NULL pointer dereference. [FIX] Just add extra check on fs_info->reloc_ctl inside btrfs_update_reloc_root(), before checking fs_info->reloc_ctl->merge_reloc_tree. That DEAD_RELOC_TREE handling is to prevent further modification to the reloc tree during merge stage, but since there is no reloc_ctl at all, we do not need to bother that. Reported-by: syzbot+283673dbc38527ef9f3d(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/66f6bfa7.050a0220.38ace9.0019.GAE@googl… CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/btrfs/relocation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index bdfa4a93d373..a67dd544a52d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -910,7 +910,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, btrfs_grab_root(reloc_root); /* root->reloc_root will stay until current relocation finished */ - if (fs_info->reloc_ctl->merge_reloc_tree && + if (fs_info->reloc_ctl && fs_info->reloc_ctl->merge_reloc_tree && btrfs_root_refs(root_item) == 0) { set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); /* -- 2.39.2

2 1