Re: [PATCH v4 1/2] ocfs2: snapshot dentry names in file and setattr traces

[Joseph Qi <joseph.qi@linux.alibaba.com>]

On 10/22/26 5:08 PM, Cen Zhang wrote:
> The open, fsync, read, write and splice-read trace calls pass the live
> dentry name and length to the shared ocfs2__file_ops event class.
> ocfs2_setattr() passes the same unprotected arguments to its own event.
> Both events size and copy a __string field separately. A reference to
> the dentry does not pin the external storage backing an individual name.
> 
> With an event enabled, a caller can be preempted after loading the name
> pointer. A long-to-short rename can then replace the name and reclaim its
> old external allocation before the trace callback sizes or copies it,
> provided no other snapshot retains that allocation.
> 
> The setattr inode lock does not exclude every rename: a same-directory
> rename of a source directory need not take that directory's inode lock.
> It can therefore change the dentry name while setattr records its event.
> Inline names and separately loaded lengths can also change during trace
> record sizing and copying.
> 
> Take a dentry name snapshot around each of these six trace calls and
> pass both the string and length from the snapshot. Check event enablement
> before taking a snapshot. Keep the event classes and formats unchanged.
> 
> Also remove the redundant NULL-inode check in the read callback.
> file_inode() returns the open file's inode, which is already used by the
> trace call above the check.
> 
> The historical report below is from the read path.
> 
> KASAN report as below:
> 
>     BUG: KASAN: slab-use-after-free in strlen+0x85/0xa0
>     Read of size 1 at addr ffff88810a5b2b18 by task python3/496
> 
>     [CPU and host details omitted.]
>     Call Trace:
>      <TASK>
>      dump_stack_lvl+0x93/0xd0
>      print_report+0xce/0x630
>      ? strlen+0x85/0xa0
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      ? __virt_addr_valid+0x20e/0x420
>      ? strlen+0x85/0xa0
>      kasan_report+0xe0/0x110
>      ? strlen+0x85/0xa0
>      strlen+0x85/0xa0
>      trace_event_raw_event_ocfs2__file_ops+0xf0/0x480
>      ? __pfx_trace_event_raw_event_ocfs2__file_ops+0x10/0x10
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      ? pmbd_probe_hit_cookie+0xe7/0x1c0
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      ? __pfx_pmbd_probe_hit_cookie+0x10/0x10
>      ocfs2_file_read_iter+0x6cd/0xb30
>      ? __pfx_ocfs2_file_read_iter+0x10/0x10
>      ? selinux_file_permission+0x11d/0x540
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      ? security_file_permission+0x26/0x80
>      vfs_read+0x7d2/0xc20
>      ? __pfx_vfs_read+0x10/0x10
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      ? __pfx_do_sys_openat2+0x10/0x10
>      ksys_read+0x111/0x200
>      ? __pfx_ksys_read+0x10/0x10
>      ? irqentry_exit+0xbe/0x820
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      ? trace_hardirqs_on_prepare+0x11d/0x150
>      ? srso_alias_return_thunk+0x5/0xfbef5
>      do_syscall_64+0x114/0x620
>      entry_SYSCALL_64_after_hwframe+0x77/0x7f
>     [User register dump omitted.]
>      </TASK>
> 
>     Allocated by task 489:
>      kasan_save_stack+0x33/0x60
>      kasan_save_track+0x14/0x30
>      __kasan_kmalloc+0xaa/0xb0
>      __kmalloc_noprof+0x2de/0x780
>      __d_alloc+0x5fc/0x8c0
>      d_alloc_parallel+0x106/0x11d0
>      lookup_open+0x3ff/0x13e0
>      path_openat+0x95e/0x2020
>      do_file_open+0x21e/0x470
>      do_sys_openat2+0xf4/0x1b0
>      __x64_sys_openat+0x136/0x1e0
>      do_syscall_64+0x114/0x620
>      entry_SYSCALL_64_after_hwframe+0x77/0x7f
> 
>     Freed by task 0:
>      kasan_save_stack+0x33/0x60
>      kasan_save_track+0x14/0x30
>      kasan_save_free_info+0x3b/0x60
>      __kasan_slab_free+0x5f/0x80
>      __rcu_free_sheaf_prepare+0x65/0x2a0
>      rcu_free_sheaf_nobarn+0x1d/0x50
>      rcu_core+0x6be/0x1ed0
>      handle_softirqs+0x1fa/0x8d0
>      __irq_exit_rcu+0x113/0x1e0
>      irq_exit_rcu+0xe/0x20
>      sysvec_apic_timer_interrupt+0x6c/0x80
>      asm_sysvec_apic_timer_interrupt+0x1a/0x20
> 
>     The buggy address belongs to the object at ffff88810a5b2b00
>      which belongs to the cache kmalloc-rcl-192 of size 192
>     The buggy address is located 24 bytes inside of
>      freed 192-byte region [ffff88810a5b2b00, ffff88810a5b2bc0)
> 
>     [Page and shadow-memory dumps omitted.]
> 
> Fixes: 468eedde23d6 ("ocfs2: Remove mlog(0) from fs/ocfs2/file.c")
> Cc: stable@vger.kernel.org
> Assisted-by: LLM
> Signed-off-by: Cen Zhang <zzzccc427@gmail.com>

Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>

> ---
>  fs/ocfs2/file.c | 100 +++++++++++++++++++++++++++++++-----------------
>  1 file changed, 64 insertions(+), 36 deletions(-)
> 
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index d6e977ba6565..c6e7606ff9e1 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -85,10 +85,17 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
>  	int mode = file->f_flags;
>  	struct ocfs2_inode_info *oi = OCFS2_I(inode);
>  
> -	trace_ocfs2_file_open(inode, file, file->f_path.dentry,
> -			      (unsigned long long)oi->ip_blkno,
> -			      file->f_path.dentry->d_name.len,
> -			      file->f_path.dentry->d_name.name, mode);
> +	if (trace_ocfs2_file_open_enabled()) {
> +		struct dentry *dentry = file->f_path.dentry;
> +		struct name_snapshot name;
> +
> +		take_dentry_name_snapshot(&name, dentry);
> +		trace_ocfs2_file_open(inode, file, dentry,
> +				      oi->ip_blkno,
> +				      name.name.len, name.name.name,
> +				      mode);
> +		release_dentry_name_snapshot(&name);
> +	}
>  
>  	if (file->f_mode & FMODE_WRITE) {
>  		status = dquot_initialize(inode);
> @@ -174,11 +181,17 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
>  	tid_t commit_tid;
>  	bool needs_barrier = false;
>  
> -	trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
> -			      oi->ip_blkno,
> -			      file->f_path.dentry->d_name.len,
> -			      file->f_path.dentry->d_name.name,
> -			      (unsigned long long)datasync);
> +	if (trace_ocfs2_sync_file_enabled()) {
> +		struct dentry *dentry = file->f_path.dentry;
> +		struct name_snapshot name;
> +
> +		take_dentry_name_snapshot(&name, dentry);
> +		trace_ocfs2_sync_file(inode, file, dentry,
> +				      oi->ip_blkno,
> +				      name.name.len, name.name.name,
> +				      (unsigned long long)datasync);
> +		release_dentry_name_snapshot(&name);
> +	}
>  
>  	if (unlikely(ocfs2_emergency_state(osb)))
>  		return -EROFS;
> @@ -1132,15 +1145,19 @@ int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
>  	int had_lock;
>  	struct ocfs2_lock_holder oh;
>  
> -	trace_ocfs2_setattr(inode, dentry,
> -			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
> -			    dentry->d_name.len, dentry->d_name.name,
> -			    attr->ia_valid,
> -				attr->ia_valid & ATTR_MODE ? attr->ia_mode : 0,
> -				attr->ia_valid & ATTR_UID ?
> +	if (trace_ocfs2_setattr_enabled()) {
> +		struct name_snapshot name;
> +
> +		take_dentry_name_snapshot(&name, dentry);
> +		trace_ocfs2_setattr(inode, dentry, OCFS2_I(inode)->ip_blkno,
> +				    name.name.len, name.name.name, attr->ia_valid,
> +				    attr->ia_valid & ATTR_MODE ? attr->ia_mode : 0,
> +				    attr->ia_valid & ATTR_UID ?
>  					from_kuid(&init_user_ns, attr->ia_uid) : 0,
> -				attr->ia_valid & ATTR_GID ?
> +				    attr->ia_valid & ATTR_GID ?
>  					from_kgid(&init_user_ns, attr->ia_gid) : 0);
> +		release_dentry_name_snapshot(&name);
> +	}
>  
>  	status = ocfs2_emergency_state(osb);
>  	if (unlikely(status)) {
> @@ -2392,11 +2409,17 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
>  	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
>  	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
>  
> -	trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry,
> -		(unsigned long long)OCFS2_I(inode)->ip_blkno,
> -		file->f_path.dentry->d_name.len,
> -		file->f_path.dentry->d_name.name,
> -		(unsigned int)from->nr_segs);	/* GRRRRR */
> +	if (trace_ocfs2_file_write_iter_enabled()) {
> +		struct dentry *dentry = file->f_path.dentry;
> +		struct name_snapshot name;
> +
> +		take_dentry_name_snapshot(&name, dentry);
> +		trace_ocfs2_file_write_iter(inode, file, dentry,
> +					    OCFS2_I(inode)->ip_blkno,
> +					    name.name.len, name.name.name,
> +					    (unsigned int)from->nr_segs);
> +		release_dentry_name_snapshot(&name);
> +	}
>  
>  	if (!direct_io && nowait)
>  		return -EOPNOTSUPP;
> @@ -2542,17 +2565,16 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
>  	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
>  	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
>  
> -	trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry,
> -			(unsigned long long)OCFS2_I(inode)->ip_blkno,
> -			filp->f_path.dentry->d_name.len,
> -			filp->f_path.dentry->d_name.name,
> -			to->nr_segs);	/* GRRRRR */
> -
> +	if (trace_ocfs2_file_read_iter_enabled()) {
> +		struct dentry *dentry = filp->f_path.dentry;
> +		struct name_snapshot name;
>  
> -	if (!inode) {
> -		ret = -EINVAL;
> -		mlog_errno(ret);
> -		goto bail;
> +		take_dentry_name_snapshot(&name, dentry);
> +		trace_ocfs2_file_read_iter(inode, filp, dentry,
> +					   OCFS2_I(inode)->ip_blkno,
> +					   name.name.len, name.name.name,
> +					   to->nr_segs);
> +		release_dentry_name_snapshot(&name);
>  	}
>  
>  	if (!direct_io && nowait)
> @@ -2624,11 +2646,17 @@ static ssize_t ocfs2_file_splice_read(struct file *in, loff_t *ppos,
>  	ssize_t ret = 0;
>  	int lock_level = 0;
>  
> -	trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
> -				     (unsigned long long)OCFS2_I(inode)->ip_blkno,
> -				     in->f_path.dentry->d_name.len,
> -				     in->f_path.dentry->d_name.name,
> -				     flags);
> +	if (trace_ocfs2_file_splice_read_enabled()) {
> +		struct dentry *dentry = in->f_path.dentry;
> +		struct name_snapshot name;
> +
> +		take_dentry_name_snapshot(&name, dentry);
> +		trace_ocfs2_file_splice_read(inode, in, dentry,
> +					     OCFS2_I(inode)->ip_blkno,
> +					     name.name.len, name.name.name,
> +					     flags);
> +		release_dentry_name_snapshot(&name);
> +	}
>  
>  	/*
>  	 * We're fine letting folks race truncates and extending writes with