From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 3 Aug 2022 20:50:22 +0000 (-0700)
Subject: Merge tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/linux/kernel...
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=5264406cdb66c7003eb3edf53c9773b1b20611b9;p=linux.git
Merge tag 'pull-work.iov_iter-base' of git://git./linux/kernel/git/viro/vfs
Pull vfs iov_iter updates from Al Viro:
"Part 1 - isolated cleanups and optimizations.
One of the goals is to reduce the overhead of using ->read_iter() and
->write_iter() instead of ->read()/->write().
new_sync_{read,write}() has a surprising amount of overhead, in
particular inside iocb_flags(). That's the explanation for the
beginning of the series is in this pile; it's not directly
iov_iter-related, but it's a part of the same work..."
* tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
first_iovec_segment(): just return address
iov_iter: massage calling conventions for first_{iovec,bvec}_segment()
iov_iter: first_{iovec,bvec}_segment() - simplify a bit
iov_iter: lift dealing with maxpages out of first_{iovec,bvec}_segment()
iov_iter_get_pages{,_alloc}(): cap the maxsize with MAX_RW_COUNT
iov_iter_bvec_advance(): don't bother with bvec_iter
copy_page_{to,from}_iter(): switch iovec variants to generic
keep iocb_flags() result cached in struct file
iocb: delay evaluation of IS_SYNC(...) until we want to check IOCB_DSYNC
struct file: use anonymous union member for rcuhead and llist
btrfs: use IOMAP_DIO_NOSYNC
teach iomap_dio_rw() to suppress dsync
No need of likely/unlikely on calls of check_copy_size()
---
5264406cdb66c7003eb3edf53c9773b1b20611b9
diff --cc block/fops.c
index 92ee820e40fde,6e86931ab8475..a564cd81340c1
--- a/block/fops.c
+++ b/block/fops.c
@@@ -32,21 -32,14 +32,21 @@@ static int blkdev_get_block(struct inod
return 0;
}
-static unsigned int dio_bio_write_op(struct kiocb *iocb)
+static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
{
- unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+ blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
/* avoid the need for a I/O completion work item */
- if (iocb->ki_flags & IOCB_DSYNC)
+ if (iocb_is_dsync(iocb))
- op |= REQ_FUA;
- return op;
+ opf |= REQ_FUA;
+ return opf;
+}
+
+static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
+ struct iov_iter *iter)
+{
+ return pos & (bdev_logical_block_size(bdev) - 1) ||
+ !bdev_iter_is_aligned(bdev, iter);
}
#define DIO_INLINE_BIO_VECS 4
diff --cc include/linux/fs.h
index 76f09f3ee4a58,c82b9d442f561..cc64873d76c59
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@@ -2324,12 -2196,10 +2325,10 @@@ static inline bool sb_rdonly(const stru
static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns,
struct inode *inode)
{
- return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
- !gid_valid(i_gid_into_mnt(mnt_userns, inode));
+ return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) ||
+ !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode));
}
- static inline int iocb_flags(struct file *file);
-
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
*kiocb = (struct kiocb) {
diff --cc io_uring/rw.c
index 2b784795103cc,0000000000000..b20ba87e4926f
mode 100644,000000..100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@@ -1,1049 -1,0 +1,1049 @@@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/blk-mq.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/fsnotify.h>
+#include <linux/poll.h>
+#include <linux/nospec.h>
+#include <linux/compat.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "opdef.h"
+#include "kbuf.h"
+#include "rsrc.h"
+#include "rw.h"
+
+struct io_rw {
+ /* NOTE: kiocb has the file as the first member, so don't do it here */
+ struct kiocb kiocb;
+ u64 addr;
+ u32 len;
+ rwf_t flags;
+};
+
+static inline bool io_file_supports_nowait(struct io_kiocb *req)
+{
+ return req->flags & REQ_F_SUPPORT_NOWAIT;
+}
+
+int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ unsigned ioprio;
+ int ret;
+
+ rw->kiocb.ki_pos = READ_ONCE(sqe->off);
+ /* used for fixed read/write too - just read unconditionally */
+ req->buf_index = READ_ONCE(sqe->buf_index);
+
+ if (req->opcode == IORING_OP_READ_FIXED ||
+ req->opcode == IORING_OP_WRITE_FIXED) {
+ struct io_ring_ctx *ctx = req->ctx;
+ u16 index;
+
+ if (unlikely(req->buf_index >= ctx->nr_user_bufs))
+ return -EFAULT;
+ index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
+ req->imu = ctx->user_bufs[index];
+ io_req_set_rsrc_node(req, ctx, 0);
+ }
+
+ ioprio = READ_ONCE(sqe->ioprio);
+ if (ioprio) {
+ ret = ioprio_check_cap(ioprio);
+ if (ret)
+ return ret;
+
+ rw->kiocb.ki_ioprio = ioprio;
+ } else {
+ rw->kiocb.ki_ioprio = get_current_ioprio();
+ }
+
+ rw->addr = READ_ONCE(sqe->addr);
+ rw->len = READ_ONCE(sqe->len);
+ rw->flags = READ_ONCE(sqe->rw_flags);
+ return 0;
+}
+
+void io_readv_writev_cleanup(struct io_kiocb *req)
+{
+ struct io_async_rw *io = req->async_data;
+
+ kfree(io->free_iovec);
+}
+
+static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+{
+ switch (ret) {
+ case -EIOCBQUEUED:
+ break;
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ case -ERESTARTNOHAND:
+ case -ERESTART_RESTARTBLOCK:
+ /*
+ * We can't just restart the syscall, since previously
+ * submitted sqes may already be in progress. Just fail this
+ * IO with EINTR.
+ */
+ ret = -EINTR;
+ fallthrough;
+ default:
+ kiocb->ki_complete(kiocb, ret);
+ }
+}
+
+static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+
+ if (rw->kiocb.ki_pos != -1)
+ return &rw->kiocb.ki_pos;
+
+ if (!(req->file->f_mode & FMODE_STREAM)) {
+ req->flags |= REQ_F_CUR_POS;
+ rw->kiocb.ki_pos = req->file->f_pos;
+ return &rw->kiocb.ki_pos;
+ }
+
+ rw->kiocb.ki_pos = 0;
+ return NULL;
+}
+
+static void io_req_task_queue_reissue(struct io_kiocb *req)
+{
+ req->io_task_work.func = io_queue_iowq;
+ io_req_task_work_add(req);
+}
+
+#ifdef CONFIG_BLOCK
+static bool io_resubmit_prep(struct io_kiocb *req)
+{
+ struct io_async_rw *io = req->async_data;
+
+ if (!req_has_async_data(req))
+ return !io_req_prep_async(req);
+ iov_iter_restore(&io->s.iter, &io->s.iter_state);
+ return true;
+}
+
+static bool io_rw_should_reissue(struct io_kiocb *req)
+{
+ umode_t mode = file_inode(req->file)->i_mode;
+ struct io_ring_ctx *ctx = req->ctx;
+
+ if (!S_ISBLK(mode) && !S_ISREG(mode))
+ return false;
+ if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() &&
+ !(ctx->flags & IORING_SETUP_IOPOLL)))
+ return false;
+ /*
+ * If ref is dying, we might be running poll reap from the exit work.
+ * Don't attempt to reissue from that path, just let it fail with
+ * -EAGAIN.
+ */
+ if (percpu_ref_is_dying(&ctx->refs))
+ return false;
+ /*
+ * Play it safe and assume not safe to re-import and reissue if we're
+ * not in the original thread group (or in task context).
+ */
+ if (!same_thread_group(req->task, current) || !in_task())
+ return false;
+ return true;
+}
+#else
+static bool io_resubmit_prep(struct io_kiocb *req)
+{
+ return false;
+}
+static bool io_rw_should_reissue(struct io_kiocb *req)
+{
+ return false;
+}
+#endif
+
+static void kiocb_end_write(struct io_kiocb *req)
+{
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ if (req->flags & REQ_F_ISREG) {
+ struct super_block *sb = file_inode(req->file)->i_sb;
+
+ __sb_writers_acquired(sb, SB_FREEZE_WRITE);
+ sb_end_write(sb);
+ }
+}
+
+static bool __io_complete_rw_common(struct io_kiocb *req, long res)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+
+ if (rw->kiocb.ki_flags & IOCB_WRITE) {
+ kiocb_end_write(req);
+ fsnotify_modify(req->file);
+ } else {
+ fsnotify_access(req->file);
+ }
+ if (unlikely(res != req->cqe.res)) {
+ if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
+ io_rw_should_reissue(req)) {
+ req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+ return true;
+ }
+ req_set_fail(req);
+ req->cqe.res = res;
+ }
+ return false;
+}
+
+static void io_complete_rw(struct kiocb *kiocb, long res)
+{
+ struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
+ struct io_kiocb *req = cmd_to_io_kiocb(rw);
+
+ if (__io_complete_rw_common(req, res))
+ return;
+ io_req_set_res(req, res, 0);
+ req->io_task_work.func = io_req_task_complete;
+ io_req_task_work_add(req);
+}
+
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
+{
+ struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
+ struct io_kiocb *req = cmd_to_io_kiocb(rw);
+
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
+ if (unlikely(res != req->cqe.res)) {
+ if (res == -EAGAIN && io_rw_should_reissue(req)) {
+ req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+ return;
+ }
+ req->cqe.res = res;
+ }
+
+ /* order with io_iopoll_complete() checking ->iopoll_completed */
+ smp_store_release(&req->iopoll_completed, 1);
+}
+
+static int kiocb_done(struct io_kiocb *req, ssize_t ret,
+ unsigned int issue_flags)
+{
+ struct io_async_rw *io = req->async_data;
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+
+ /* add previously done IO, if any */
+ if (req_has_async_data(req) && io->bytes_done > 0) {
+ if (ret < 0)
+ ret = io->bytes_done;
+ else
+ ret += io->bytes_done;
+ }
+
+ if (req->flags & REQ_F_CUR_POS)
+ req->file->f_pos = rw->kiocb.ki_pos;
+ if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) {
+ if (!__io_complete_rw_common(req, ret)) {
+ io_req_set_res(req, req->cqe.res,
+ io_put_kbuf(req, issue_flags));
+ return IOU_OK;
+ }
+ } else {
+ io_rw_done(&rw->kiocb, ret);
+ }
+
+ if (req->flags & REQ_F_REISSUE) {
+ req->flags &= ~REQ_F_REISSUE;
+ if (io_resubmit_prep(req))
+ io_req_task_queue_reissue(req);
+ else
+ io_req_task_queue_fail(req, ret);
+ }
+ return IOU_ISSUE_SKIP_COMPLETE;
+}
+
+#ifdef CONFIG_COMPAT
+static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
+ unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct compat_iovec __user *uiov;
+ compat_ssize_t clen;
+ void __user *buf;
+ size_t len;
+
+ uiov = u64_to_user_ptr(rw->addr);
+ if (!access_ok(uiov, sizeof(*uiov)))
+ return -EFAULT;
+ if (__get_user(clen, &uiov->iov_len))
+ return -EFAULT;
+ if (clen < 0)
+ return -EINVAL;
+
+ len = clen;
+ buf = io_buffer_select(req, &len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ rw->addr = (unsigned long) buf;
+ iov[0].iov_base = buf;
+ rw->len = iov[0].iov_len = (compat_size_t) len;
+ return 0;
+}
+#endif
+
+static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
+ unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct iovec __user *uiov = u64_to_user_ptr(rw->addr);
+ void __user *buf;
+ ssize_t len;
+
+ if (copy_from_user(iov, uiov, sizeof(*uiov)))
+ return -EFAULT;
+
+ len = iov[0].iov_len;
+ if (len < 0)
+ return -EINVAL;
+ buf = io_buffer_select(req, &len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ rw->addr = (unsigned long) buf;
+ iov[0].iov_base = buf;
+ rw->len = iov[0].iov_len = len;
+ return 0;
+}
+
+static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
+ unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+
+ if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
+ iov[0].iov_base = u64_to_user_ptr(rw->addr);
+ iov[0].iov_len = rw->len;
+ return 0;
+ }
+ if (rw->len != 1)
+ return -EINVAL;
+
+#ifdef CONFIG_COMPAT
+ if (req->ctx->compat)
+ return io_compat_import(req, iov, issue_flags);
+#endif
+
+ return __io_iov_buffer_select(req, iov, issue_flags);
+}
+
+static struct iovec *__io_import_iovec(int ddir, struct io_kiocb *req,
+ struct io_rw_state *s,
+ unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct iov_iter *iter = &s->iter;
+ u8 opcode = req->opcode;
+ struct iovec *iovec;
+ void __user *buf;
+ size_t sqe_len;
+ ssize_t ret;
+
+ if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
+ ret = io_import_fixed(ddir, iter, req->imu, rw->addr, rw->len);
+ if (ret)
+ return ERR_PTR(ret);
+ return NULL;
+ }
+
+ buf = u64_to_user_ptr(rw->addr);
+ sqe_len = rw->len;
+
+ if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
+ if (io_do_buffer_select(req)) {
+ buf = io_buffer_select(req, &sqe_len, issue_flags);
+ if (!buf)
+ return ERR_PTR(-ENOBUFS);
+ rw->addr = (unsigned long) buf;
+ rw->len = sqe_len;
+ }
+
+ ret = import_single_range(ddir, buf, sqe_len, s->fast_iov, iter);
+ if (ret)
+ return ERR_PTR(ret);
+ return NULL;
+ }
+
+ iovec = s->fast_iov;
+ if (req->flags & REQ_F_BUFFER_SELECT) {
+ ret = io_iov_buffer_select(req, iovec, issue_flags);
+ if (ret)
+ return ERR_PTR(ret);
+ iov_iter_init(iter, ddir, iovec, 1, iovec->iov_len);
+ return NULL;
+ }
+
+ ret = __import_iovec(ddir, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
+ req->ctx->compat);
+ if (unlikely(ret < 0))
+ return ERR_PTR(ret);
+ return iovec;
+}
+
+static inline int io_import_iovec(int rw, struct io_kiocb *req,
+ struct iovec **iovec, struct io_rw_state *s,
+ unsigned int issue_flags)
+{
+ *iovec = __io_import_iovec(rw, req, s, issue_flags);
+ if (unlikely(IS_ERR(*iovec)))
+ return PTR_ERR(*iovec);
+
+ iov_iter_save_state(&s->iter, &s->iter_state);
+ return 0;
+}
+
+static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
+{
+ return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos;
+}
+
+/*
+ * For files that don't have ->read_iter() and ->write_iter(), handle them
+ * by looping over ->read() or ->write() manually.
+ */
+static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
+{
+ struct kiocb *kiocb = &rw->kiocb;
+ struct file *file = kiocb->ki_filp;
+ ssize_t ret = 0;
+ loff_t *ppos;
+
+ /*
+ * Don't support polled IO through this interface, and we can't
+ * support non-blocking either. For the latter, this just causes
+ * the kiocb to be handled from an async context.
+ */
+ if (kiocb->ki_flags & IOCB_HIPRI)
+ return -EOPNOTSUPP;
+ if ((kiocb->ki_flags & IOCB_NOWAIT) &&
+ !(kiocb->ki_filp->f_flags & O_NONBLOCK))
+ return -EAGAIN;
+
+ ppos = io_kiocb_ppos(kiocb);
+
+ while (iov_iter_count(iter)) {
+ struct iovec iovec;
+ ssize_t nr;
+
+ if (!iov_iter_is_bvec(iter)) {
+ iovec = iov_iter_iovec(iter);
+ } else {
+ iovec.iov_base = u64_to_user_ptr(rw->addr);
+ iovec.iov_len = rw->len;
+ }
+
+ if (ddir == READ) {
+ nr = file->f_op->read(file, iovec.iov_base,
+ iovec.iov_len, ppos);
+ } else {
+ nr = file->f_op->write(file, iovec.iov_base,
+ iovec.iov_len, ppos);
+ }
+
+ if (nr < 0) {
+ if (!ret)
+ ret = nr;
+ break;
+ }
+ ret += nr;
+ if (!iov_iter_is_bvec(iter)) {
+ iov_iter_advance(iter, nr);
+ } else {
+ rw->addr += nr;
+ rw->len -= nr;
+ if (!rw->len)
+ break;
+ }
+ if (nr != iovec.iov_len)
+ break;
+ }
+
+ return ret;
+}
+
+static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
+ const struct iovec *fast_iov, struct iov_iter *iter)
+{
+ struct io_async_rw *io = req->async_data;
+
+ memcpy(&io->s.iter, iter, sizeof(*iter));
+ io->free_iovec = iovec;
+ io->bytes_done = 0;
+ /* can only be fixed buffers, no need to do anything */
+ if (iov_iter_is_bvec(iter))
+ return;
+ if (!iovec) {
+ unsigned iov_off = 0;
+
+ io->s.iter.iov = io->s.fast_iov;
+ if (iter->iov != fast_iov) {
+ iov_off = iter->iov - fast_iov;
+ io->s.iter.iov += iov_off;
+ }
+ if (io->s.fast_iov != fast_iov)
+ memcpy(io->s.fast_iov + iov_off, fast_iov + iov_off,
+ sizeof(struct iovec) * iter->nr_segs);
+ } else {
+ req->flags |= REQ_F_NEED_CLEANUP;
+ }
+}
+
+static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
+ struct io_rw_state *s, bool force)
+{
+ if (!force && !io_op_defs[req->opcode].prep_async)
+ return 0;
+ if (!req_has_async_data(req)) {
+ struct io_async_rw *iorw;
+
+ if (io_alloc_async_data(req)) {
+ kfree(iovec);
+ return -ENOMEM;
+ }
+
+ io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
+ iorw = req->async_data;
+ /* we've copied and mapped the iter, ensure state is saved */
+ iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
+ }
+ return 0;
+}
+
+static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
+{
+ struct io_async_rw *iorw = req->async_data;
+ struct iovec *iov;
+ int ret;
+
+ /* submission path, ->uring_lock should already be taken */
+ ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
+ if (unlikely(ret < 0))
+ return ret;
+
+ iorw->bytes_done = 0;
+ iorw->free_iovec = iov;
+ if (iov)
+ req->flags |= REQ_F_NEED_CLEANUP;
+ return 0;
+}
+
+int io_readv_prep_async(struct io_kiocb *req)
+{
+ return io_rw_prep_async(req, READ);
+}
+
+int io_writev_prep_async(struct io_kiocb *req)
+{
+ return io_rw_prep_async(req, WRITE);
+}
+
+/*
+ * This is our waitqueue callback handler, registered through __folio_lock_async()
+ * when we initially tried to do the IO with the iocb armed our waitqueue.
+ * This gets called when the page is unlocked, and we generally expect that to
+ * happen when the page IO is completed and the page is now uptodate. This will
+ * queue a task_work based retry of the operation, attempting to copy the data
+ * again. If the latter fails because the page was NOT uptodate, then we will
+ * do a thread based blocking retry of the operation. That's the unexpected
+ * slow path.
+ */
+static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
+ int sync, void *arg)
+{
+ struct wait_page_queue *wpq;
+ struct io_kiocb *req = wait->private;
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct wait_page_key *key = arg;
+
+ wpq = container_of(wait, struct wait_page_queue, wait);
+
+ if (!wake_page_match(wpq, key))
+ return 0;
+
+ rw->kiocb.ki_flags &= ~IOCB_WAITQ;
+ list_del_init(&wait->entry);
+ io_req_task_queue(req);
+ return 1;
+}
+
+/*
+ * This controls whether a given IO request should be armed for async page
+ * based retry. If we return false here, the request is handed to the async
+ * worker threads for retry. If we're doing buffered reads on a regular file,
+ * we prepare a private wait_page_queue entry and retry the operation. This
+ * will either succeed because the page is now uptodate and unlocked, or it
+ * will register a callback when the page is unlocked at IO completion. Through
+ * that callback, io_uring uses task_work to setup a retry of the operation.
+ * That retry will attempt the buffered read again. The retry will generally
+ * succeed, or in rare cases where it fails, we then fall back to using the
+ * async worker threads for a blocking retry.
+ */
+static bool io_rw_should_retry(struct io_kiocb *req)
+{
+ struct io_async_rw *io = req->async_data;
+ struct wait_page_queue *wait = &io->wpq;
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct kiocb *kiocb = &rw->kiocb;
+
+ /* never retry for NOWAIT, we just complete with -EAGAIN */
+ if (req->flags & REQ_F_NOWAIT)
+ return false;
+
+ /* Only for buffered IO */
+ if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI))
+ return false;
+
+ /*
+ * just use poll if we can, and don't attempt if the fs doesn't
+ * support callback based unlocks
+ */
+ if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+ return false;
+
+ wait->wait.func = io_async_buf_func;
+ wait->wait.private = req;
+ wait->wait.flags = 0;
+ INIT_LIST_HEAD(&wait->wait.entry);
+ kiocb->ki_flags |= IOCB_WAITQ;
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
+ kiocb->ki_waitq = wait;
+ return true;
+}
+
+static inline int io_iter_do_read(struct io_rw *rw, struct iov_iter *iter)
+{
+ struct file *file = rw->kiocb.ki_filp;
+
+ if (likely(file->f_op->read_iter))
+ return call_read_iter(file, &rw->kiocb, iter);
+ else if (file->f_op->read)
+ return loop_rw_iter(READ, rw, iter);
+ else
+ return -EINVAL;
+}
+
+static bool need_complete_io(struct io_kiocb *req)
+{
+ return req->flags & REQ_F_ISREG ||
+ S_ISBLK(file_inode(req->file)->i_mode);
+}
+
+static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct kiocb *kiocb = &rw->kiocb;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = req->file;
+ int ret;
+
+ if (unlikely(!file || !(file->f_mode & mode)))
+ return -EBADF;
+
+ if (!io_req_ffs_set(req))
+ req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
+
- kiocb->ki_flags = iocb_flags(file);
++ kiocb->ki_flags = file->f_iocb_flags;
+ ret = kiocb_set_rw_flags(kiocb, rw->flags);
+ if (unlikely(ret))
+ return ret;
+
+ /*
+ * If the file is marked O_NONBLOCK, still allow retry for it if it
+ * supports async. Otherwise it's impossible to use O_NONBLOCK files
+ * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
+ */
+ if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+ ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
+ req->flags |= REQ_F_NOWAIT;
+
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
+ return -EOPNOTSUPP;
+
+ kiocb->private = NULL;
+ kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
+ kiocb->ki_complete = io_complete_rw_iopoll;
+ req->iopoll_completed = 0;
+ } else {
+ if (kiocb->ki_flags & IOCB_HIPRI)
+ return -EINVAL;
+ kiocb->ki_complete = io_complete_rw;
+ }
+
+ return 0;
+}
+
+int io_read(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct io_rw_state __s, *s = &__s;
+ struct iovec *iovec;
+ struct kiocb *kiocb = &rw->kiocb;
+ bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ struct io_async_rw *io;
+ ssize_t ret, ret2;
+ loff_t *ppos;
+
+ if (!req_has_async_data(req)) {
+ ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
+ return ret;
+ } else {
+ io = req->async_data;
+ s = &io->s;
+
+ /*
+ * Safe and required to re-import if we're using provided
+ * buffers, as we dropped the selected one before retry.
+ */
+ if (io_do_buffer_select(req)) {
+ ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
+ return ret;
+ }
+
+ /*
+ * We come here from an earlier attempt, restore our state to
+ * match in case it doesn't. It's cheap enough that we don't
+ * need to make this conditional.
+ */
+ iov_iter_restore(&s->iter, &s->iter_state);
+ iovec = NULL;
+ }
+ ret = io_rw_init_file(req, FMODE_READ);
+ if (unlikely(ret)) {
+ kfree(iovec);
+ return ret;
+ }
+ req->cqe.res = iov_iter_count(&s->iter);
+
+ if (force_nonblock) {
+ /* If the file doesn't support async, just async punt */
+ if (unlikely(!io_file_supports_nowait(req))) {
+ ret = io_setup_async_rw(req, iovec, s, true);
+ return ret ?: -EAGAIN;
+ }
+ kiocb->ki_flags |= IOCB_NOWAIT;
+ } else {
+ /* Ensure we clear previously set non-block flag */
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
+ }
+
+ ppos = io_kiocb_update_pos(req);
+
+ ret = rw_verify_area(READ, req->file, ppos, req->cqe.res);
+ if (unlikely(ret)) {
+ kfree(iovec);
+ return ret;
+ }
+
+ ret = io_iter_do_read(rw, &s->iter);
+
+ if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+ req->flags &= ~REQ_F_REISSUE;
+ /* if we can poll, just do that */
+ if (req->opcode == IORING_OP_READ && file_can_poll(req->file))
+ return -EAGAIN;
+ /* IOPOLL retry should happen for io-wq threads */
+ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
+ goto done;
+ /* no retry on NONBLOCK nor RWF_NOWAIT */
+ if (req->flags & REQ_F_NOWAIT)
+ goto done;
+ ret = 0;
+ } else if (ret == -EIOCBQUEUED) {
+ if (iovec)
+ kfree(iovec);
+ return IOU_ISSUE_SKIP_COMPLETE;
+ } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
+ (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) {
+ /* read all, failed, already did sync or don't want to retry */
+ goto done;
+ }
+
+ /*
+ * Don't depend on the iter state matching what was consumed, or being
+ * untouched in case of error. Restore it and we'll advance it
+ * manually if we need to.
+ */
+ iov_iter_restore(&s->iter, &s->iter_state);
+
+ ret2 = io_setup_async_rw(req, iovec, s, true);
+ if (ret2)
+ return ret2;
+
+ iovec = NULL;
+ io = req->async_data;
+ s = &io->s;
+ /*
+ * Now use our persistent iterator and state, if we aren't already.
+ * We've restored and mapped the iter to match.
+ */
+
+ do {
+ /*
+ * We end up here because of a partial read, either from
+ * above or inside this loop. Advance the iter by the bytes
+ * that were consumed.
+ */
+ iov_iter_advance(&s->iter, ret);
+ if (!iov_iter_count(&s->iter))
+ break;
+ io->bytes_done += ret;
+ iov_iter_save_state(&s->iter, &s->iter_state);
+
+ /* if we can retry, do so with the callbacks armed */
+ if (!io_rw_should_retry(req)) {
+ kiocb->ki_flags &= ~IOCB_WAITQ;
+ return -EAGAIN;
+ }
+
+ /*
+ * Now retry read with the IOCB_WAITQ parts set in the iocb. If
+ * we get -EIOCBQUEUED, then we'll get a notification when the
+ * desired page gets unlocked. We can also get a partial read
+ * here, and if we do, then just retry at the new offset.
+ */
+ ret = io_iter_do_read(rw, &s->iter);
+ if (ret == -EIOCBQUEUED)
+ return IOU_ISSUE_SKIP_COMPLETE;
+ /* we got some bytes, but not all. retry. */
+ kiocb->ki_flags &= ~IOCB_WAITQ;
+ iov_iter_restore(&s->iter, &s->iter_state);
+ } while (ret > 0);
+done:
+ /* it's faster to check here then delegate to kfree */
+ if (iovec)
+ kfree(iovec);
+ return kiocb_done(req, ret, issue_flags);
+}
+
+int io_write(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ struct io_rw_state __s, *s = &__s;
+ struct iovec *iovec;
+ struct kiocb *kiocb = &rw->kiocb;
+ bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ ssize_t ret, ret2;
+ loff_t *ppos;
+
+ if (!req_has_async_data(req)) {
+ ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
+ return ret;
+ } else {
+ struct io_async_rw *io = req->async_data;
+
+ s = &io->s;
+ iov_iter_restore(&s->iter, &s->iter_state);
+ iovec = NULL;
+ }
+ ret = io_rw_init_file(req, FMODE_WRITE);
+ if (unlikely(ret)) {
+ kfree(iovec);
+ return ret;
+ }
+ req->cqe.res = iov_iter_count(&s->iter);
+
+ if (force_nonblock) {
+ /* If the file doesn't support async, just async punt */
+ if (unlikely(!io_file_supports_nowait(req)))
+ goto copy_iov;
+
+ /* File path supports NOWAIT for non-direct_IO only for block devices. */
+ if (!(kiocb->ki_flags & IOCB_DIRECT) &&
+ !(kiocb->ki_filp->f_mode & FMODE_BUF_WASYNC) &&
+ (req->flags & REQ_F_ISREG))
+ goto copy_iov;
+
+ kiocb->ki_flags |= IOCB_NOWAIT;
+ } else {
+ /* Ensure we clear previously set non-block flag */
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
+ }
+
+ ppos = io_kiocb_update_pos(req);
+
+ ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res);
+ if (unlikely(ret)) {
+ kfree(iovec);
+ return ret;
+ }
+
+ /*
+ * Open-code file_start_write here to grab freeze protection,
+ * which will be released by another thread in
+ * io_complete_rw(). Fool lockdep by telling it the lock got
+ * released so that it doesn't complain about the held lock when
+ * we return to userspace.
+ */
+ if (req->flags & REQ_F_ISREG) {
+ sb_start_write(file_inode(req->file)->i_sb);
+ __sb_writers_release(file_inode(req->file)->i_sb,
+ SB_FREEZE_WRITE);
+ }
+ kiocb->ki_flags |= IOCB_WRITE;
+
+ if (likely(req->file->f_op->write_iter))
+ ret2 = call_write_iter(req->file, kiocb, &s->iter);
+ else if (req->file->f_op->write)
+ ret2 = loop_rw_iter(WRITE, rw, &s->iter);
+ else
+ ret2 = -EINVAL;
+
+ if (req->flags & REQ_F_REISSUE) {
+ req->flags &= ~REQ_F_REISSUE;
+ ret2 = -EAGAIN;
+ }
+
+ /*
+ * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
+ * retry them without IOCB_NOWAIT.
+ */
+ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
+ ret2 = -EAGAIN;
+ /* no retry on NONBLOCK nor RWF_NOWAIT */
+ if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
+ goto done;
+ if (!force_nonblock || ret2 != -EAGAIN) {
+ /* IOPOLL retry should happen for io-wq threads */
+ if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
+ goto copy_iov;
+
+ if (ret2 != req->cqe.res && ret2 >= 0 && need_complete_io(req)) {
+ struct io_async_rw *rw;
+
+ trace_io_uring_short_write(req->ctx, kiocb->ki_pos - ret2,
+ req->cqe.res, ret2);
+
+ /* This is a partial write. The file pos has already been
+ * updated, setup the async struct to complete the request
+ * in the worker. Also update bytes_done to account for
+ * the bytes already written.
+ */
+ iov_iter_save_state(&s->iter, &s->iter_state);
+ ret = io_setup_async_rw(req, iovec, s, true);
+
+ rw = req->async_data;
+ if (rw)
+ rw->bytes_done += ret2;
+
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
+ return ret ? ret : -EAGAIN;
+ }
+done:
+ ret = kiocb_done(req, ret2, issue_flags);
+ } else {
+copy_iov:
+ iov_iter_restore(&s->iter, &s->iter_state);
+ ret = io_setup_async_rw(req, iovec, s, false);
+ if (!ret) {
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
+ return -EAGAIN;
+ }
+ return ret;
+ }
+ /* it's reportedly faster than delegating the null check to kfree() */
+ if (iovec)
+ kfree(iovec);
+ return ret;
+}
+
+static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
+{
+ io_commit_cqring_flush(ctx);
+ if (ctx->flags & IORING_SETUP_SQPOLL)
+ io_cqring_wake(ctx);
+}
+
+int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
+{
+ struct io_wq_work_node *pos, *start, *prev;
+ unsigned int poll_flags = BLK_POLL_NOSLEEP;
+ DEFINE_IO_COMP_BATCH(iob);
+ int nr_events = 0;
+
+ /*
+ * Only spin for completions if we don't have multiple devices hanging
+ * off our complete list.
+ */
+ if (ctx->poll_multi_queue || force_nonspin)
+ poll_flags |= BLK_POLL_ONESHOT;
+
+ wq_list_for_each(pos, start, &ctx->iopoll_list) {
+ struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
+ struct io_rw *rw = io_kiocb_to_cmd(req);
+ int ret;
+
+ /*
+ * Move completed and retryable entries to our local lists.
+ * If we find a request that requires polling, break out
+ * and complete those lists first, if we have entries there.
+ */
+ if (READ_ONCE(req->iopoll_completed))
+ break;
+
+ ret = rw->kiocb.ki_filp->f_op->iopoll(&rw->kiocb, &iob, poll_flags);
+ if (unlikely(ret < 0))
+ return ret;
+ else if (ret)
+ poll_flags |= BLK_POLL_ONESHOT;
+
+ /* iopoll may have completed current req */
+ if (!rq_list_empty(iob.req_list) ||
+ READ_ONCE(req->iopoll_completed))
+ break;
+ }
+
+ if (!rq_list_empty(iob.req_list))
+ iob.complete(&iob);
+ else if (!pos)
+ return 0;
+
+ prev = start;
+ wq_list_for_each_resume(pos, prev) {
+ struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
+
+ /* order with io_complete_rw_iopoll(), e.g. ->result updates */
+ if (!smp_load_acquire(&req->iopoll_completed))
+ break;
+ nr_events++;
+ if (unlikely(req->flags & REQ_F_CQE_SKIP))
+ continue;
+
+ req->cqe.flags = io_put_kbuf(req, 0);
+ __io_fill_cqe_req(req->ctx, req);
+ }
+
+ if (unlikely(!nr_events))
+ return 0;
+
+ io_commit_cqring(ctx);
+ io_cqring_ev_posted_iopoll(ctx);
+ pos = start ? start->next : ctx->iopoll_list.first;
+ wq_list_cut(&ctx->iopoll_list, prev, start);
+ io_free_batch_list(ctx, pos);
+ return nr_events;
+}