OpenCloudOS-Kernel/io_uring/rw.c

1082 lines
27 KiB
C
Raw Normal View History

// 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;
}
#ifdef CONFIG_COMPAT
static int io_iov_compat_buffer_select_prep(struct io_rw *rw)
{
struct compat_iovec __user *uiov;
compat_ssize_t clen;
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;
rw->len = clen;
return 0;
}
#endif
static int io_iov_buffer_select_prep(struct io_kiocb *req)
{
struct iovec __user *uiov;
struct iovec iov;
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
if (rw->len != 1)
return -EINVAL;
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
return io_iov_compat_buffer_select_prep(rw);
#endif
uiov = u64_to_user_ptr(rw->addr);
if (copy_from_user(&iov, uiov, sizeof(*uiov)))
return -EFAULT;
rw->len = iov.iov_len;
return 0;
}
int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
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);
/* Have to do this validation here, as this is in io_read() rw->len might
* have chanaged due to buffer selection
*/
if (req->opcode == IORING_OP_READV && req->flags & REQ_F_BUFFER_SELECT) {
ret = io_iov_buffer_select_prep(req);
if (ret)
return ret;
}
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, struct io_rw);
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);
}
}
/*
* Trigger the notifications after having done some IO, and finish the write
* accounting, if any.
*/
static void io_req_io_end(struct io_kiocb *req)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
if (rw->kiocb.ki_flags & IOCB_WRITE) {
kiocb_end_write(req);
fsnotify_modify(req->file);
} else {
fsnotify_access(req->file);
}
}
static bool __io_complete_rw_common(struct io_kiocb *req, long res)
{
if (unlikely(res != req->cqe.res)) {
if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
io_rw_should_reissue(req)) {
/*
* Reissue will start accounting again, finish the
* current cycle.
*/
io_req_io_end(req);
req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
return true;
}
req_set_fail(req);
req->cqe.res = res;
}
return false;
}
static inline int io_fixup_rw_res(struct io_kiocb *req, long res)
{
struct io_async_rw *io = req->async_data;
/* add previously done IO, if any */
if (req_has_async_data(req) && io->bytes_done > 0) {
if (res < 0)
res = io->bytes_done;
else
res += io->bytes_done;
}
return res;
}
io_uring/rw: defer fsnotify calls to task context We can't call these off the kiocb completion as that might be off soft/hard irq context. Defer the calls to when we process the task_work for this request. That avoids valid complaints like: stack backtrace: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_usage_bug kernel/locking/lockdep.c:3961 [inline] valid_state kernel/locking/lockdep.c:3973 [inline] mark_lock_irq kernel/locking/lockdep.c:4176 [inline] mark_lock.part.0.cold+0x18/0xd8 kernel/locking/lockdep.c:4632 mark_lock kernel/locking/lockdep.c:4596 [inline] mark_usage kernel/locking/lockdep.c:4527 [inline] __lock_acquire+0x11d9/0x56d0 kernel/locking/lockdep.c:5007 lock_acquire kernel/locking/lockdep.c:5666 [inline] lock_acquire+0x1ab/0x570 kernel/locking/lockdep.c:5631 __fs_reclaim_acquire mm/page_alloc.c:4674 [inline] fs_reclaim_acquire+0x115/0x160 mm/page_alloc.c:4688 might_alloc include/linux/sched/mm.h:271 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc mm/slab.c:3278 [inline] __kmem_cache_alloc_lru mm/slab.c:3471 [inline] kmem_cache_alloc+0x39/0x520 mm/slab.c:3491 fanotify_alloc_fid_event fs/notify/fanotify/fanotify.c:580 [inline] fanotify_alloc_event fs/notify/fanotify/fanotify.c:813 [inline] fanotify_handle_event+0x1130/0x3f40 fs/notify/fanotify/fanotify.c:948 send_to_group fs/notify/fsnotify.c:360 [inline] fsnotify+0xafb/0x1680 fs/notify/fsnotify.c:570 __fsnotify_parent+0x62f/0xa60 fs/notify/fsnotify.c:230 fsnotify_parent include/linux/fsnotify.h:77 [inline] fsnotify_file include/linux/fsnotify.h:99 [inline] fsnotify_access include/linux/fsnotify.h:309 [inline] __io_complete_rw_common+0x485/0x720 io_uring/rw.c:195 io_complete_rw+0x1a/0x1f0 io_uring/rw.c:228 iomap_dio_complete_work fs/iomap/direct-io.c:144 [inline] iomap_dio_bio_end_io+0x438/0x5e0 fs/iomap/direct-io.c:178 bio_endio+0x5f9/0x780 block/bio.c:1564 req_bio_endio block/blk-mq.c:695 [inline] blk_update_request+0x3fc/0x1300 block/blk-mq.c:825 scsi_end_request+0x7a/0x9a0 drivers/scsi/scsi_lib.c:541 scsi_io_completion+0x173/0x1f70 drivers/scsi/scsi_lib.c:971 scsi_complete+0x122/0x3b0 drivers/scsi/scsi_lib.c:1438 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1022 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x5/0x20 kernel/softirq.c:662 common_interrupt+0xa9/0xc0 arch/x86/kernel/irq.c:240 Fixes: f63cf5192fe3 ("io_uring: ensure that fsnotify is always called") Link: https://lore.kernel.org/all/20220929135627.ykivmdks2w5vzrwg@quack3/ Reported-by: syzbot+dfcc5f4da15868df7d4d@syzkaller.appspotmail.com Reported-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-09-30 00:57:05 +08:00
static void io_req_rw_complete(struct io_kiocb *req, bool *locked)
{
io_req_io_end(req);
if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
unsigned issue_flags = *locked ? 0 : IO_URING_F_UNLOCKED;
req->cqe.flags |= io_put_kbuf(req, issue_flags);
}
io_uring/rw: defer fsnotify calls to task context We can't call these off the kiocb completion as that might be off soft/hard irq context. Defer the calls to when we process the task_work for this request. That avoids valid complaints like: stack backtrace: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_usage_bug kernel/locking/lockdep.c:3961 [inline] valid_state kernel/locking/lockdep.c:3973 [inline] mark_lock_irq kernel/locking/lockdep.c:4176 [inline] mark_lock.part.0.cold+0x18/0xd8 kernel/locking/lockdep.c:4632 mark_lock kernel/locking/lockdep.c:4596 [inline] mark_usage kernel/locking/lockdep.c:4527 [inline] __lock_acquire+0x11d9/0x56d0 kernel/locking/lockdep.c:5007 lock_acquire kernel/locking/lockdep.c:5666 [inline] lock_acquire+0x1ab/0x570 kernel/locking/lockdep.c:5631 __fs_reclaim_acquire mm/page_alloc.c:4674 [inline] fs_reclaim_acquire+0x115/0x160 mm/page_alloc.c:4688 might_alloc include/linux/sched/mm.h:271 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc mm/slab.c:3278 [inline] __kmem_cache_alloc_lru mm/slab.c:3471 [inline] kmem_cache_alloc+0x39/0x520 mm/slab.c:3491 fanotify_alloc_fid_event fs/notify/fanotify/fanotify.c:580 [inline] fanotify_alloc_event fs/notify/fanotify/fanotify.c:813 [inline] fanotify_handle_event+0x1130/0x3f40 fs/notify/fanotify/fanotify.c:948 send_to_group fs/notify/fsnotify.c:360 [inline] fsnotify+0xafb/0x1680 fs/notify/fsnotify.c:570 __fsnotify_parent+0x62f/0xa60 fs/notify/fsnotify.c:230 fsnotify_parent include/linux/fsnotify.h:77 [inline] fsnotify_file include/linux/fsnotify.h:99 [inline] fsnotify_access include/linux/fsnotify.h:309 [inline] __io_complete_rw_common+0x485/0x720 io_uring/rw.c:195 io_complete_rw+0x1a/0x1f0 io_uring/rw.c:228 iomap_dio_complete_work fs/iomap/direct-io.c:144 [inline] iomap_dio_bio_end_io+0x438/0x5e0 fs/iomap/direct-io.c:178 bio_endio+0x5f9/0x780 block/bio.c:1564 req_bio_endio block/blk-mq.c:695 [inline] blk_update_request+0x3fc/0x1300 block/blk-mq.c:825 scsi_end_request+0x7a/0x9a0 drivers/scsi/scsi_lib.c:541 scsi_io_completion+0x173/0x1f70 drivers/scsi/scsi_lib.c:971 scsi_complete+0x122/0x3b0 drivers/scsi/scsi_lib.c:1438 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1022 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x5/0x20 kernel/softirq.c:662 common_interrupt+0xa9/0xc0 arch/x86/kernel/irq.c:240 Fixes: f63cf5192fe3 ("io_uring: ensure that fsnotify is always called") Link: https://lore.kernel.org/all/20220929135627.ykivmdks2w5vzrwg@quack3/ Reported-by: syzbot+dfcc5f4da15868df7d4d@syzkaller.appspotmail.com Reported-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-09-30 00:57:05 +08:00
io_req_task_complete(req, locked);
}
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, io_fixup_rw_res(req, res), 0);
io_uring/rw: defer fsnotify calls to task context We can't call these off the kiocb completion as that might be off soft/hard irq context. Defer the calls to when we process the task_work for this request. That avoids valid complaints like: stack backtrace: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.0.0-rc6-syzkaller-00321-g105a36f3694e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_usage_bug kernel/locking/lockdep.c:3961 [inline] valid_state kernel/locking/lockdep.c:3973 [inline] mark_lock_irq kernel/locking/lockdep.c:4176 [inline] mark_lock.part.0.cold+0x18/0xd8 kernel/locking/lockdep.c:4632 mark_lock kernel/locking/lockdep.c:4596 [inline] mark_usage kernel/locking/lockdep.c:4527 [inline] __lock_acquire+0x11d9/0x56d0 kernel/locking/lockdep.c:5007 lock_acquire kernel/locking/lockdep.c:5666 [inline] lock_acquire+0x1ab/0x570 kernel/locking/lockdep.c:5631 __fs_reclaim_acquire mm/page_alloc.c:4674 [inline] fs_reclaim_acquire+0x115/0x160 mm/page_alloc.c:4688 might_alloc include/linux/sched/mm.h:271 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc mm/slab.c:3278 [inline] __kmem_cache_alloc_lru mm/slab.c:3471 [inline] kmem_cache_alloc+0x39/0x520 mm/slab.c:3491 fanotify_alloc_fid_event fs/notify/fanotify/fanotify.c:580 [inline] fanotify_alloc_event fs/notify/fanotify/fanotify.c:813 [inline] fanotify_handle_event+0x1130/0x3f40 fs/notify/fanotify/fanotify.c:948 send_to_group fs/notify/fsnotify.c:360 [inline] fsnotify+0xafb/0x1680 fs/notify/fsnotify.c:570 __fsnotify_parent+0x62f/0xa60 fs/notify/fsnotify.c:230 fsnotify_parent include/linux/fsnotify.h:77 [inline] fsnotify_file include/linux/fsnotify.h:99 [inline] fsnotify_access include/linux/fsnotify.h:309 [inline] __io_complete_rw_common+0x485/0x720 io_uring/rw.c:195 io_complete_rw+0x1a/0x1f0 io_uring/rw.c:228 iomap_dio_complete_work fs/iomap/direct-io.c:144 [inline] iomap_dio_bio_end_io+0x438/0x5e0 fs/iomap/direct-io.c:178 bio_endio+0x5f9/0x780 block/bio.c:1564 req_bio_endio block/blk-mq.c:695 [inline] blk_update_request+0x3fc/0x1300 block/blk-mq.c:825 scsi_end_request+0x7a/0x9a0 drivers/scsi/scsi_lib.c:541 scsi_io_completion+0x173/0x1f70 drivers/scsi/scsi_lib.c:971 scsi_complete+0x122/0x3b0 drivers/scsi/scsi_lib.c:1438 blk_complete_reqs+0xad/0xe0 block/blk-mq.c:1022 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 invoke_softirq kernel/softirq.c:445 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:650 irq_exit_rcu+0x5/0x20 kernel/softirq.c:662 common_interrupt+0xa9/0xc0 arch/x86/kernel/irq.c:240 Fixes: f63cf5192fe3 ("io_uring: ensure that fsnotify is always called") Link: https://lore.kernel.org/all/20220929135627.ykivmdks2w5vzrwg@quack3/ Reported-by: syzbot+dfcc5f4da15868df7d4d@syzkaller.appspotmail.com Reported-by: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-09-30 00:57:05 +08:00
req->io_task_work.func = io_req_rw_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_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
unsigned final_ret = io_fixup_rw_res(req, ret);
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)) {
/*
* Safe to call io_end from here as we're inline
* from the submission path.
*/
io_req_io_end(req);
io_req_set_res(req, final_ret,
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, final_ret);
}
return IOU_ISSUE_SKIP_COMPLETE;
}
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 io_rw);
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 ||
(req->flags & REQ_F_BUFFER_SELECT)) {
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;
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, ITER_DEST);
}
int io_writev_prep_async(struct io_kiocb *req)
{
return io_rw_prep_async(req, ITER_SOURCE);
}
/*
* 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 io_rw);
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 io_rw);
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 io_rw);
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;
iov_iter work, 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 why 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... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQQqUNBr3gm4hGXdBJlZ7Krx/gZQ6wUCYurGOQAKCRBZ7Krx/gZQ 6ysyAP91lvBfMRepcxpd9kvtuzWkU8A3rfSziZZteEHANB9Q7QEAiPn2a2OjWkcZ uAyUWfCkHCNx+dSMkEvUgR5okQ0exAM= =9UCV -----END PGP SIGNATURE----- Merge tag 'pull-work.iov_iter-base' of git://git.kernel.org/pub/scm/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()
2022-08-04 04:50:22 +08:00
kiocb->ki_flags = file->f_iocb_flags;
ret = kiocb_set_rw_flags(kiocb, rw->flags);
if (unlikely(ret))
return ret;
kiocb->ki_flags |= IOCB_ALLOC_CACHE;
/*
* 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;
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);
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(ITER_DEST, 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(ITER_DEST, 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);
iovec = NULL;
if (ret2) {
ret = ret > 0 ? ret : ret2;
goto done;
}
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;
}
req->cqe.res = iov_iter_count(&s->iter);
/*
* 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);
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(ITER_SOURCE, 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 *io;
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);
io = req->async_data;
if (io)
io->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);
}
void io_rw_fail(struct io_kiocb *req)
{
int res;
res = io_fixup_rw_res(req, req->cqe.res);
io_req_set_res(req, res, req->cqe.flags);
}
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 file *file = req->file;
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;
if (req->opcode == IORING_OP_URING_CMD) {
struct io_uring_cmd *ioucmd;
ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
ret = file->f_op->uring_cmd_iopoll(ioucmd, &iob,
poll_flags);
} else {
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
ret = file->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);
if (unlikely(!__io_fill_cqe_req(ctx, req))) {
spin_lock(&ctx->completion_lock);
io_req_cqe_overflow(req);
spin_unlock(&ctx->completion_lock);
}
}
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;
}