From: Linus Torvalds Date: Sun, 16 Aug 2020 17:55:12 +0000 (-0700) Subject: Merge tag 'io_uring-5.9-2020-08-15' of git://git.kernel.dk/linux-block X-Git-Tag: v5.9-rc1~1 X-Git-Url: https://repo.jachan.dev/linux.git/commitdiff_plain/2cc3c4b3c2e9c99e90aaf19cd801ff2c160f283c?hp=-c Merge tag 'io_uring-5.9-2020-08-15' of git://git.kernel.dk/linux-block Pull io_uring fixes from Jens Axboe: "A few differerent things in here. Seems like syzbot got some more io_uring bits wired up, and we got a handful of reports and the associated fixes are in here. General fixes too, and a lot of them marked for stable. Lastly, a bit of fallout from the async buffered reads, where we now more easily trigger short reads. Some applications don't really like that, so the io_read() code now handles short reads internally, and got a cleanup along the way so that it's now easier to read (and documented). We're now passing tests that failed before" * tag 'io_uring-5.9-2020-08-15' of git://git.kernel.dk/linux-block: io_uring: short circuit -EAGAIN for blocking read attempt io_uring: sanitize double poll handling io_uring: internally retry short reads io_uring: retain iov_iter state over io_read/io_write calls task_work: only grab task signal lock when needed io_uring: enable lookup of links holding inflight files io_uring: fail poll arm on queue proc failure io_uring: hold 'ctx' reference around task_work queue + execute fs: RWF_NOWAIT should imply IOCB_NOIO io_uring: defer file table grabbing request cleanup for locked requests io_uring: add missing REQ_F_COMP_LOCKED for nested requests io_uring: fix recursive completion locking on oveflow flush io_uring: use TWA_SIGNAL for task_work uncondtionally io_uring: account locked memory before potential error case io_uring: set ctx sq/cq entry count earlier io_uring: Fix NULL pointer dereference in loop_rw_iter() io_uring: add comments on how the async buffered read retry works io_uring: io_async_buf_func() need not test page bit --- 2cc3c4b3c2e9c99e90aaf19cd801ff2c160f283c diff --combined include/linux/fs.h index 7c69dd7c6160,f1cca4bfdd7b..e019ea2f1347 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@@ -518,16 -518,6 +518,16 @@@ static inline void i_mmap_unlock_read(s up_read(&mapping->i_mmap_rwsem); } +static inline void i_mmap_assert_locked(struct address_space *mapping) +{ + lockdep_assert_held(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_assert_write_locked(struct address_space *mapping) +{ + lockdep_assert_held_write(&mapping->i_mmap_rwsem); +} + /* * Might pages of this file be mapped into userspace? */ @@@ -538,7 -528,7 +538,7 @@@ static inline int mapping_mapped(struc /* * Might pages of this file have been modified in userspace? - * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff + * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * @@@ -1722,10 -1712,6 +1722,10 @@@ int vfs_mkobj(struct dentry *, umode_t int (*f)(struct dentry *, umode_t, void *), void *); +int vfs_fchown(struct file *file, uid_t user, gid_t group); +int vfs_fchmod(struct file *file, umode_t mode); +int vfs_utimes(const struct path *path, struct timespec64 *times); + extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT @@@ -1956,27 -1942,27 +1956,27 @@@ struct super_operations /* * Inode flags - they have no relation to superblock flags now */ -#define S_SYNC 1 /* Writes are synced at once */ -#define S_NOATIME 2 /* Do not update access times */ -#define S_APPEND 4 /* Append-only file */ -#define S_IMMUTABLE 8 /* Immutable file */ -#define S_DEAD 16 /* removed, but still open directory */ -#define S_NOQUOTA 32 /* Inode is not counted to quota */ -#define S_DIRSYNC 64 /* Directory modifications are synchronous */ -#define S_NOCMTIME 128 /* Do not update file c/mtime */ -#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ -#define S_PRIVATE 512 /* Inode is fs-internal */ -#define S_IMA 1024 /* Inode has an associated IMA struct */ -#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ -#define S_NOSEC 4096 /* no suid or xattr security attributes */ +#define S_SYNC (1 << 0) /* Writes are synced at once */ +#define S_NOATIME (1 << 1) /* Do not update access times */ +#define S_APPEND (1 << 2) /* Append-only file */ +#define S_IMMUTABLE (1 << 3) /* Immutable file */ +#define S_DEAD (1 << 4) /* removed, but still open directory */ +#define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ +#define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ +#define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ +#define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ +#define S_PRIVATE (1 << 9) /* Inode is fs-internal */ +#define S_IMA (1 << 10) /* Inode has an associated IMA struct */ +#define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ +#define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX -#define S_DAX 8192 /* Direct Access, avoiding the page cache */ +#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else -#define S_DAX 0 /* Make all the DAX code disappear */ +#define S_DAX 0 /* Make all the DAX code disappear */ #endif -#define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ -#define S_CASEFOLD 32768 /* Casefolded file */ -#define S_VERITY 65536 /* Verity file (using fs/verity/) */ +#define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ +#define S_CASEFOLD (1 << 15) /* Casefolded file */ +#define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@@ -2660,7 -2646,7 +2660,7 @@@ static inline void filemap_set_wb_err(s } /** - * filemap_check_wb_error - has an error occurred since the mark was sampled? + * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * @@@ -2689,7 -2675,7 +2689,7 @@@ static inline errseq_t filemap_sample_w /** * file_sample_sb_err - sample the current errseq_t to test for later errors - * @mapping: mapping to be sampled + * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. @@@ -2960,21 -2946,6 +2960,21 @@@ extern void discard_new_inode(struct in extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +/* + * Userspace may rely on the the inode number being non-zero. For example, glibc + * simply ignores files with zero i_ino in unlink() and other places. + * + * As an additional complication, if userspace was compiled with + * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the + * lower 32 bits, so we need to check that those aren't zero explicitly. With + * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but + * better safe than sorry. + */ +static inline bool is_zero_ino(ino_t ino) +{ + return (u32)ino == 0; +} + extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); @@@ -3322,7 -3293,7 +3322,7 @@@ static inline int kiocb_set_rw_flags(st if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - kiocb_flags |= IOCB_NOWAIT; + kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO; } if (flags & RWF_HIPRI) kiocb_flags |= IOCB_HIPRI;