6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bharath SM bharathsm@microsoft.com
[ Upstream commit e4b61f3b1c67f5068590965f64ea6e8d5d5bd961 ]
In cases of large directories, the readdir operation may span multiple round trips to retrieve contents. This introduces a potential race condition in case of concurrent write and readdir operations. If the readdir operation initiates before a write has been processed by the server, it may update the file size attribute to an older value. Address this issue by avoiding file size updates from readdir when we have read/write lease.
Scenario: 1) process1: open dir xyz 2) process1: readdir instance 1 on xyz 3) process2: create file.txt for write 4) process2: write x bytes to file.txt 5) process2: close file.txt 6) process2: open file.txt for read 7) process1: readdir 2 - overwrites file.txt inode size to 0 8) process2: read contents of file.txt - bug, short read with 0 bytes
Cc: stable@vger.kernel.org Reviewed-by: Shyam Prasad N sprasad@microsoft.com Signed-off-by: Bharath SM bharathsm@microsoft.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/smb/client/cifsproto.h | 6 ++++-- fs/smb/client/file.c | 8 +++++--- fs/smb/client/inode.c | 13 +++++++------ fs/smb/client/readdir.c | 2 +- 4 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 260a6299bddb8..0cff4f5af1793 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -144,7 +144,8 @@ extern int cifs_reconnect(struct TCP_Server_Info *server, extern int checkSMB(char *buf, unsigned int len, struct TCP_Server_Info *srvr); extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *); extern bool backup_cred(struct cifs_sb_info *); -extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof); +extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof, + bool from_readdir); extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, unsigned int bytes_written); extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int); @@ -201,7 +202,8 @@ extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb); extern void cifs_dir_info_to_fattr(struct cifs_fattr *, FILE_DIRECTORY_INFO *, struct cifs_sb_info *); -extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); +extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir); extern struct inode *cifs_iget(struct super_block *sb, struct cifs_fattr *fattr);
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index c156460eb5587..c711d5eb2987e 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -329,7 +329,7 @@ int cifs_posix_open(const char *full_path, struct inode **pinode, } } else { cifs_revalidate_mapping(*pinode); - rc = cifs_fattr_to_inode(*pinode, &fattr); + rc = cifs_fattr_to_inode(*pinode, &fattr, false); }
posix_open_ret: @@ -4766,12 +4766,14 @@ static int is_inode_writable(struct cifsInodeInfo *cifs_inode) refreshing the inode only on increases in the file size but this is tricky to do without racing with writebehind page caching in the current Linux kernel design */ -bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) +bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, + bool from_readdir) { if (!cifsInode) return true;
- if (is_inode_writable(cifsInode)) { + if (is_inode_writable(cifsInode) || + ((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) { /* This inode is open for write at least once */ struct cifs_sb_info *cifs_sb;
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 471abc99bbf02..cb9e719e67ae2 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -147,7 +147,8 @@ cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
/* populate an inode with info from a cifs_fattr struct */ int -cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) +cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir) { struct cifsInodeInfo *cifs_i = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); @@ -199,7 +200,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) * Can't safely change the file size here if the client is writing to * it due to potential races. */ - if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) { + if (is_size_safe_to_change(cifs_i, fattr->cf_eof, from_readdir)) { i_size_write(inode, fattr->cf_eof);
/* @@ -368,7 +369,7 @@ static int update_inode_info(struct super_block *sb, CIFS_I(*inode)->time = 0; /* force reval */ return -ESTALE; } - return cifs_fattr_to_inode(*inode, fattr); + return cifs_fattr_to_inode(*inode, fattr, false); }
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY @@ -403,7 +404,7 @@ cifs_get_file_info_unix(struct file *filp) } else goto cifs_gfiunix_out;
- rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false);
cifs_gfiunix_out: free_xid(xid); @@ -928,7 +929,7 @@ cifs_get_file_info(struct file *filp) fattr.cf_uniqueid = CIFS_I(inode)->uniqueid; fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; /* if filetype is different, return error */ - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cgfi_exit: cifs_free_open_info(&data); free_xid(xid); @@ -1467,7 +1468,7 @@ cifs_iget(struct super_block *sb, struct cifs_fattr *fattr) }
/* can't fail - see cifs_find_inode() */ - cifs_fattr_to_inode(inode, fattr); + cifs_fattr_to_inode(inode, fattr, false); if (sb->s_flags & SB_NOATIME) inode->i_flags |= S_NOATIME | S_NOCMTIME; if (inode->i_state & I_NEW) { diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 520c490e844b5..56033e4e4bae9 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -148,7 +148,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, rc = -ESTALE; } } - if (!rc && !cifs_fattr_to_inode(inode, fattr)) { + if (!rc && !cifs_fattr_to_inode(inode, fattr, true)) { dput(dentry); return; }