diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-02 22:25:03 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-02 22:25:03 +0300 |
commit | c03098d4b9ad76bca2966a8769dcfe59f7f85103 (patch) | |
tree | e7e2a6a0a84ad29baa14c018e3d4dcb12bd08fd6 /fs/iomap/direct-io.c | |
parent | ab2e7f4b46bf8fccf088ec496b3bb26b43e91340 (diff) | |
parent | b01b2d72da25c000aeb124bc78daf3fb998be2b6 (diff) | |
download | linux-c03098d4b9ad76bca2966a8769dcfe59f7f85103.tar.xz |
Merge tag 'gfs2-v5.15-rc5-mmap-fault' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2
Pull gfs2 mmap + page fault deadlocks fixes from Andreas Gruenbacher:
"Functions gfs2_file_read_iter and gfs2_file_write_iter are both
accessing the user buffer to write to or read from while holding the
inode glock.
In the most basic deadlock scenario, that buffer will not be resident
and it will be mapped to the same file. Accessing the buffer will
trigger a page fault, and gfs2 will deadlock trying to take the same
inode glock again while trying to handle that fault.
Fix that and similar, more complex scenarios by disabling page faults
while accessing user buffers. To make this work, introduce a small
amount of new infrastructure and fix some bugs that didn't trigger so
far, with page faults enabled"
* tag 'gfs2-v5.15-rc5-mmap-fault' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
gfs2: Fix mmap + page fault deadlocks for direct I/O
iov_iter: Introduce nofault flag to disable page faults
gup: Introduce FOLL_NOFAULT flag to disable page faults
iomap: Add done_before argument to iomap_dio_rw
iomap: Support partial direct I/O on user copy failures
iomap: Fix iomap_dio_rw return value for user copies
gfs2: Fix mmap + page fault deadlocks for buffered I/O
gfs2: Eliminate ip->i_gh
gfs2: Move the inode glock locking to gfs2_file_buffered_write
gfs2: Introduce flag for glock holder auto-demotion
gfs2: Clean up function may_grant
gfs2: Add wrapper for iomap_file_buffered_write
iov_iter: Introduce fault_in_iov_iter_writeable
iov_iter: Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable
gup: Turn fault_in_pages_{readable,writeable} into fault_in_{readable,writeable}
powerpc/kvm: Fix kvm_use_magic_page
iov_iter: Fix iov_iter_get_pages{,_alloc} page fault return value
Diffstat (limited to 'fs/iomap/direct-io.c')
-rw-r--r-- | fs/iomap/direct-io.c | 29 |
1 files changed, 26 insertions, 3 deletions
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 811c898125a5..b4dc51063d36 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -31,6 +31,7 @@ struct iomap_dio { atomic_t ref; unsigned flags; int error; + size_t done_before; bool wait_for_completion; union { @@ -114,6 +115,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC)) ret = generic_write_sync(iocb, ret); + if (ret > 0) + ret += dio->done_before; + kfree(dio); return ret; @@ -375,6 +379,8 @@ static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter, loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter); dio->size += length; + if (!length) + return -EFAULT; return length; } @@ -406,6 +412,8 @@ static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi, copied = copy_to_iter(inline_data, length, iter); } dio->size += copied; + if (!copied) + return -EFAULT; return copied; } @@ -450,13 +458,21 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter, * may be pure data writes. In that case, we still need to do a full data sync * completion. * + * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL, + * __iomap_dio_rw can return a partial result if it encounters a non-resident + * page in @iter after preparing a transfer. In that case, the non-resident + * pages can be faulted in and the request resumed with @done_before set to the + * number of bytes previously transferred. The request will then complete with + * the correct total number of bytes transferred; this is essential for + * completing partial requests asynchronously. + * * Returns -ENOTBLK In case of a page invalidation invalidation failure for * writes. The callers needs to fall back to buffered I/O in this case. */ struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags) + unsigned int dio_flags, size_t done_before) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); @@ -486,6 +502,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->dops = dops; dio->error = 0; dio->flags = 0; + dio->done_before = done_before; dio->submit.iter = iter; dio->submit.waiter = current; @@ -587,6 +604,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size) iov_iter_revert(iter, iomi.pos - dio->i_size); + if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) { + if (!(iocb->ki_flags & IOCB_NOWAIT)) + wait_for_completion = true; + ret = 0; + } + /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { wait_for_completion = true; @@ -649,11 +672,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags) + unsigned int dio_flags, size_t done_before) { struct iomap_dio *dio; - dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags); + dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); |