aboutsummaryrefslogtreecommitdiff
path: root/fs/io_uring.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/io_uring.c')
-rw-r--r--fs/io_uring.c948
1 files changed, 501 insertions, 447 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 381d50becd04..9fb0dc6033ba 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -142,7 +142,7 @@ struct io_rings {
*/
u32 sq_dropped;
/*
- * Runtime flags
+ * Runtime SQ flags
*
* Written by the kernel, shouldn't be modified by the
* application.
@@ -152,6 +152,13 @@ struct io_rings {
*/
u32 sq_flags;
/*
+ * Runtime CQ flags
+ *
+ * Written by the application, shouldn't be modified by the
+ * kernel.
+ */
+ u32 cq_flags;
+ /*
* Number of completion events lost because the queue was full;
* this should be avoided by the application by making sure
* there are not more requests pending than there is space in
@@ -191,7 +198,7 @@ struct fixed_file_ref_node {
struct list_head node;
struct list_head file_list;
struct fixed_file_data *file_data;
- struct work_struct work;
+ struct llist_node llist;
};
struct fixed_file_data {
@@ -279,8 +286,8 @@ struct io_ring_ctx {
const struct cred *creds;
- /* 0 is for ctx quiesce/reinit/free, 1 is for sqo_thread started */
- struct completion *completions;
+ struct completion ref_comp;
+ struct completion sq_thread_comp;
/* if all else fails... */
struct io_kiocb *fallback_req;
@@ -327,6 +334,9 @@ struct io_ring_ctx {
struct list_head inflight_list;
} ____cacheline_aligned_in_smp;
+ struct delayed_work file_put_work;
+ struct llist_head file_put_llist;
+
struct work_struct exit_work;
};
@@ -384,7 +394,8 @@ struct io_timeout {
struct file *file;
u64 addr;
int flags;
- u32 count;
+ u32 off;
+ u32 target_seq;
};
struct io_rw {
@@ -415,11 +426,7 @@ struct io_sr_msg {
struct io_open {
struct file *file;
int dfd;
- union {
- unsigned mask;
- };
struct filename *filename;
- struct statx __user *buffer;
struct open_how how;
unsigned long nofile;
};
@@ -471,6 +478,15 @@ struct io_provide_buf {
__u16 bid;
};
+struct io_statx {
+ struct file *file;
+ int dfd;
+ unsigned int mask;
+ unsigned int flags;
+ const char __user *filename;
+ struct statx __user *buffer;
+};
+
struct io_async_connect {
struct sockaddr_storage address;
};
@@ -524,6 +540,7 @@ enum {
REQ_F_OVERFLOW_BIT,
REQ_F_POLLED_BIT,
REQ_F_BUFFER_SELECTED_BIT,
+ REQ_F_NO_FILE_TABLE_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -577,6 +594,8 @@ enum {
REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
/* buffer already selected */
REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
+ /* doesn't need file table for this request */
+ REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT),
};
struct async_poll {
@@ -609,13 +628,15 @@ struct io_kiocb {
struct io_epoll epoll;
struct io_splice splice;
struct io_provide_buf pbuf;
+ struct io_statx statx;
};
struct io_async_ctx *io;
int cflags;
- bool needs_fixed_file;
u8 opcode;
+ u16 buf_index;
+
struct io_ring_ctx *ctx;
struct list_head list;
unsigned int flags;
@@ -677,8 +698,6 @@ struct io_op_def {
unsigned needs_mm : 1;
/* needs req->file assigned */
unsigned needs_file : 1;
- /* needs req->file assigned IFF fd is >= 0 */
- unsigned fd_non_neg : 1;
/* hash wq insertion if file is a regular file */
unsigned hash_reg_file : 1;
/* unbound wq insertion if file is a non-regular file */
@@ -781,13 +800,10 @@ static const struct io_op_def io_op_defs[] = {
.needs_file = 1,
},
[IORING_OP_OPENAT] = {
- .needs_file = 1,
- .fd_non_neg = 1,
.file_table = 1,
.needs_fs = 1,
},
[IORING_OP_CLOSE] = {
- .needs_file = 1,
.file_table = 1,
},
[IORING_OP_FILES_UPDATE] = {
@@ -796,9 +812,8 @@ static const struct io_op_def io_op_defs[] = {
},
[IORING_OP_STATX] = {
.needs_mm = 1,
- .needs_file = 1,
- .fd_non_neg = 1,
.needs_fs = 1,
+ .file_table = 1,
},
[IORING_OP_READ] = {
.needs_mm = 1,
@@ -833,8 +848,6 @@ static const struct io_op_def io_op_defs[] = {
.buffer_select = 1,
},
[IORING_OP_OPENAT2] = {
- .needs_file = 1,
- .fd_non_neg = 1,
.file_table = 1,
.needs_fs = 1,
},
@@ -849,6 +862,11 @@ static const struct io_op_def io_op_defs[] = {
},
[IORING_OP_PROVIDE_BUFFERS] = {},
[IORING_OP_REMOVE_BUFFERS] = {},
+ [IORING_OP_TEE] = {
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ },
};
static void io_wq_submit_work(struct io_wq_work **workptr);
@@ -884,11 +902,18 @@ struct sock *io_uring_get_socket(struct file *file)
}
EXPORT_SYMBOL(io_uring_get_socket);
+static void io_file_put_work(struct work_struct *work);
+
+static inline bool io_async_submit(struct io_ring_ctx *ctx)
+{
+ return ctx->flags & IORING_SETUP_SQPOLL;
+}
+
static void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
- complete(&ctx->completions[0]);
+ complete(&ctx->ref_comp);
}
static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
@@ -904,10 +929,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
if (!ctx->fallback_req)
goto err;
- ctx->completions = kmalloc(2 * sizeof(struct completion), GFP_KERNEL);
- if (!ctx->completions)
- goto err;
-
/*
* Use 5 bits less than the max cq entries, that should give us around
* 32 entries per hash list if totally full and uniformly spread.
@@ -928,10 +949,11 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
goto err;
ctx->flags = p->flags;
+ init_waitqueue_head(&ctx->sqo_wait);
init_waitqueue_head(&ctx->cq_wait);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
- init_completion(&ctx->completions[0]);
- init_completion(&ctx->completions[1]);
+ init_completion(&ctx->ref_comp);
+ init_completion(&ctx->sq_thread_comp);
idr_init(&ctx->io_buffer_idr);
idr_init(&ctx->personality_idr);
mutex_init(&ctx->uring_lock);
@@ -943,11 +965,12 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
init_waitqueue_head(&ctx->inflight_wait);
spin_lock_init(&ctx->inflight_lock);
INIT_LIST_HEAD(&ctx->inflight_list);
+ INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work);
+ init_llist_head(&ctx->file_put_llist);
return ctx;
err:
if (ctx->fallback_req)
kmem_cache_free(req_cachep, ctx->fallback_req);
- kfree(ctx->completions);
kfree(ctx->cancel_hash);
kfree(ctx);
return NULL;
@@ -969,36 +992,6 @@ static inline bool req_need_defer(struct io_kiocb *req)
return false;
}
-static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
-{
- struct io_kiocb *req;
-
- req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list);
- if (req && !req_need_defer(req)) {
- list_del_init(&req->list);
- return req;
- }
-
- return NULL;
-}
-
-static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx)
-{
- struct io_kiocb *req;
-
- req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list);
- if (req) {
- if (req->flags & REQ_F_TIMEOUT_NOSEQ)
- return NULL;
- if (!__req_need_defer(req)) {
- list_del_init(&req->list);
- return req;
- }
- }
-
- return NULL;
-}
-
static void __io_commit_cqring(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
@@ -1114,17 +1107,43 @@ static void io_kill_timeouts(struct io_ring_ctx *ctx)
spin_unlock_irq(&ctx->completion_lock);
}
-static void io_commit_cqring(struct io_ring_ctx *ctx)
+static void __io_queue_deferred(struct io_ring_ctx *ctx)
{
- struct io_kiocb *req;
+ do {
+ struct io_kiocb *req = list_first_entry(&ctx->defer_list,
+ struct io_kiocb, list);
+
+ if (req_need_defer(req))
+ break;
+ list_del_init(&req->list);
+ io_queue_async_work(req);
+ } while (!list_empty(&ctx->defer_list));
+}
+
+static void io_flush_timeouts(struct io_ring_ctx *ctx)
+{
+ while (!list_empty(&ctx->timeout_list)) {
+ struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
+ struct io_kiocb, list);
+
+ if (req->flags & REQ_F_TIMEOUT_NOSEQ)
+ break;
+ if (req->timeout.target_seq != ctx->cached_cq_tail
+ - atomic_read(&ctx->cq_timeouts))
+ break;
- while ((req = io_get_timeout_req(ctx)) != NULL)
+ list_del_init(&req->list);
io_kill_timeout(req);
+ }
+}
+static void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+ io_flush_timeouts(ctx);
__io_commit_cqring(ctx);
- while ((req = io_get_deferred_req(ctx)) != NULL)
- io_queue_async_work(req);
+ if (unlikely(!list_empty(&ctx->defer_list)))
+ __io_queue_deferred(ctx);
}
static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
@@ -1149,6 +1168,8 @@ static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
{
if (!ctx->cq_ev_fd)
return false;
+ if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
+ return false;
if (!ctx->eventfd_async)
return true;
return io_wq_current_is_worker();
@@ -1291,7 +1312,7 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
struct io_kiocb *req;
req = ctx->fallback_req;
- if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+ if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req))
return req;
return NULL;
@@ -1378,7 +1399,7 @@ static void __io_free_req(struct io_kiocb *req)
if (likely(!io_is_fallback_req(req)))
kmem_cache_free(req_cachep, req);
else
- clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+ clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req);
}
struct req_batch {
@@ -1398,10 +1419,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
for (i = 0; i < rb->to_free; i++) {
struct io_kiocb *req = rb->reqs[i];
- if (req->flags & REQ_F_FIXED_FILE) {
- req->file = NULL;
- percpu_ref_put(req->fixed_file_refs);
- }
if (req->flags & REQ_F_INFLIGHT)
inflight++;
__io_req_aux_free(req);
@@ -1674,7 +1691,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
return false;
- if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+ if (req->file || req->io)
rb->need_iter++;
rb->reqs[rb->to_free++] = req;
@@ -1989,15 +2006,19 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
wake_up(&ctx->sqo_wait);
}
-static void io_file_put(struct io_submit_state *state)
+static void __io_state_file_put(struct io_submit_state *state)
{
- if (state->file) {
- int diff = state->has_refs - state->used_refs;
+ int diff = state->has_refs - state->used_refs;
- if (diff)
- fput_many(state->file, diff);
- state->file = NULL;
- }
+ if (diff)
+ fput_many(state->file, diff);
+ state->file = NULL;
+}
+
+static inline void io_state_file_put(struct io_submit_state *state)
+{
+ if (state->file)
+ __io_state_file_put(state);
}
/*
@@ -2016,7 +2037,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
state->ios_left--;
return state->file;
}
- io_file_put(state);
+ __io_state_file_put(state);
}
state->file = fget_many(fd, state->ios_left);
if (!state->file)
@@ -2034,7 +2055,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
* any file. For now, just ensure that anything potentially problematic is done
* inline.
*/
-static bool io_file_supports_async(struct file *file)
+static bool io_file_supports_async(struct file *file, int rw)
{
umode_t mode = file_inode(file)->i_mode;
@@ -2043,7 +2064,13 @@ static bool io_file_supports_async(struct file *file)
if (S_ISREG(mode) && file->f_op != &io_uring_fops)
return true;
- return false;
+ if (!(file->f_mode & FMODE_NOWAIT))
+ return false;
+
+ if (rw == READ)
+ return file->f_op->read_iter != NULL;
+
+ return file->f_op->write_iter != NULL;
}
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
@@ -2102,9 +2129,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
- /* we own ->private, reuse it for the buffer index / buffer ID */
- req->rw.kiocb.private = (void *) (unsigned long)
- READ_ONCE(sqe->buf_index);
+ req->buf_index = READ_ONCE(sqe->buf_index);
return 0;
}
@@ -2147,7 +2172,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
struct io_ring_ctx *ctx = req->ctx;
size_t len = req->rw.len;
struct io_mapped_ubuf *imu;
- unsigned index, buf_index;
+ u16 index, buf_index;
size_t offset;
u64 buf_addr;
@@ -2155,7 +2180,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
if (unlikely(!ctx->user_bufs))
return -EFAULT;
- buf_index = (unsigned long) req->rw.kiocb.private;
+ buf_index = req->buf_index;
if (unlikely(buf_index >= ctx->nr_user_bufs))
return -EFAULT;
@@ -2271,10 +2296,10 @@ static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
bool needs_lock)
{
struct io_buffer *kbuf;
- int bgid;
+ u16 bgid;
kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
- bgid = (int) (unsigned long) req->rw.kiocb.private;
+ bgid = req->buf_index;
kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
if (IS_ERR(kbuf))
return kbuf;
@@ -2365,7 +2390,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
}
/* buffer index only valid with fixed read/write, or buffer select */
- if (req->rw.kiocb.private && !(req->flags & REQ_F_BUFFER_SELECT))
+ if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))
return -EINVAL;
if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
@@ -2571,7 +2596,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
* we know to async punt it even if it was opened O_NONBLOCK
*/
- if (force_nonblock && !io_file_supports_async(req->file))
+ if (force_nonblock && !io_file_supports_async(req->file, READ))
goto copy_iov;
iov_count = iov_iter_count(&iter);
@@ -2594,7 +2619,8 @@ copy_iov:
if (ret)
goto out_free;
/* any defer here is final, must blocking retry */
- if (!(req->flags & REQ_F_NOWAIT))
+ if (!(req->flags & REQ_F_NOWAIT) &&
+ !file_can_poll(req->file))
req->flags |= REQ_F_MUST_PUNT;
return -EAGAIN;
}
@@ -2662,7 +2688,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
* we know to async punt it even if it was opened O_NONBLOCK
*/
- if (force_nonblock && !io_file_supports_async(req->file))
+ if (force_nonblock && !io_file_supports_async(req->file, WRITE))
goto copy_iov;
/* file path doesn't support NOWAIT for non-direct_IO */
@@ -2716,7 +2742,8 @@ copy_iov:
if (ret)
goto out_free;
/* any defer here is final, must blocking retry */
- req->flags |= REQ_F_MUST_PUNT;
+ if (!file_can_poll(req->file))
+ req->flags |= REQ_F_MUST_PUNT;
return -EAGAIN;
}
}
@@ -2726,7 +2753,8 @@ out_free:
return ret;
}
-static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int __io_splice_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
{
struct io_splice* sp = &req->splice;
unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
@@ -2736,8 +2764,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return 0;
sp->file_in = NULL;
- sp->off_in = READ_ONCE(sqe->splice_off_in);
- sp->off_out = READ_ONCE(sqe->off);
sp->len = READ_ONCE(sqe->len);
sp->flags = READ_ONCE(sqe->splice_flags);
@@ -2756,13 +2782,44 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return 0;
}
-static bool io_splice_punt(struct file *file)
+static int io_tee_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
{
- if (get_pipe_info(file))
- return false;
- if (!io_file_supports_async(file))
- return true;
- return !(file->f_flags & O_NONBLOCK);
+ if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off))
+ return -EINVAL;
+ return __io_splice_prep(req, sqe);
+}
+
+static int io_tee(struct io_kiocb *req, bool force_nonblock)
+{
+ struct io_splice *sp = &req->splice;
+ struct file *in = sp->file_in;
+ struct file *out = sp->file_out;
+ unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+ long ret = 0;
+
+ if (force_nonblock)
+ return -EAGAIN;
+ if (sp->len)
+ ret = do_tee(in, out, sp->len, flags);
+
+ io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+
+ io_cqring_add_event(req, ret);
+ if (ret != sp->len)
+ req_set_fail_links(req);
+ io_put_req(req);
+ return 0;
+}
+
+static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_splice* sp = &req->splice;
+
+ sp->off_in = READ_ONCE(sqe->splice_off_in);
+ sp->off_out = READ_ONCE(sqe->off);
+ return __io_splice_prep(req, sqe);
}
static int io_splice(struct io_kiocb *req, bool force_nonblock)
@@ -2772,19 +2829,16 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock)
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
loff_t *poff_in, *poff_out;
- long ret;
+ long ret = 0;
- if (force_nonblock) {
- if (io_splice_punt(in) || io_splice_punt(out))
- return -EAGAIN;
- flags |= SPLICE_F_NONBLOCK;
- }
+ if (force_nonblock)
+ return -EAGAIN;
poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
- ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
- if (force_nonblock && ret == -EAGAIN)
- return -EAGAIN;
+
+ if (sp->len)
+ ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
req->flags &= ~REQ_F_NEED_CLEANUP;
@@ -3316,71 +3370,35 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock)
static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- const char __user *fname;
- unsigned lookup_flags;
- int ret;
-
if (sqe->ioprio || sqe->buf_index)
return -EINVAL;
if (req->flags & REQ_F_FIXED_FILE)
return -EBADF;
- if (req->flags & REQ_F_NEED_CLEANUP)
- return 0;
- req->open.dfd = READ_ONCE(sqe->fd);
- req->open.mask = READ_ONCE(sqe->len);
- fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
- req->open.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- req->open.how.flags = READ_ONCE(sqe->statx_flags);
-
- if (vfs_stat_set_lookup_flags(&lookup_flags, req->open.how.flags))
- return -EINVAL;
-
- req->open.filename = getname_flags(fname, lookup_flags, NULL);
- if (IS_ERR(req->open.filename)) {
- ret = PTR_ERR(req->open.filename);
- req->open.filename = NULL;
- return ret;
- }
+ req->statx.dfd = READ_ONCE(sqe->fd);
+ req->statx.mask = READ_ONCE(sqe->len);
+ req->statx.filename = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+ req->statx.flags = READ_ONCE(sqe->statx_flags);
- req->flags |= REQ_F_NEED_CLEANUP;
return 0;
}
static int io_statx(struct io_kiocb *req, bool force_nonblock)
{
- struct io_open *ctx = &req->open;
- unsigned lookup_flags;
- struct path path;
- struct kstat stat;
+ struct io_statx *ctx = &req->statx;
int ret;
- if (force_nonblock)
+ if (force_nonblock) {
+ /* only need file table for an actual valid fd */
+ if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD)
+ req->flags |= REQ_F_NO_FILE_TABLE;
return -EAGAIN;
+ }
- if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
- return -EINVAL;
-
-retry:
- /* filename_lookup() drops it, keep a reference */
- ctx->filename->refcnt++;
-
- ret = filename_lookup(ctx->dfd, ctx->filename, lookup_flags, &path,
- NULL);
- if (ret)
- goto err;
+ ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
+ ctx->buffer);
- ret = vfs_getattr(&path, &stat, ctx->mask, ctx->how.flags);
- path_put(&path);
- if (retry_estale(ret, lookup_flags)) {
- lookup_flags |= LOOKUP_REVAL;
- goto retry;
- }
- if (!ret)
- ret = cp_statx(&stat, ctx->buffer);
-err:
- putname(ctx->filename);
- req->flags &= ~REQ_F_NEED_CLEANUP;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
@@ -3403,10 +3421,6 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return -EBADF;
req->close.fd = READ_ONCE(sqe->fd);
- if (req->file->f_op == &io_uring_fops ||
- req->close.fd == req->ctx->ring_fd)
- return -EBADF;
-
return 0;
}
@@ -3439,21 +3453,14 @@ static int io_close(struct io_kiocb *req, bool force_nonblock)
req->close.put_file = NULL;
ret = __close_fd_get_file(req->close.fd, &req->close.put_file);
if (ret < 0)
- return ret;
+ return (ret == -ENOENT) ? -EBADF : ret;
/* if the file has a flush method, be safe and punt to async */
if (req->close.put_file->f_op->flush && force_nonblock) {
- /* submission ref will be dropped, take it for async */
- refcount_inc(&req->refs);
-
+ /* avoid grabbing files - we don't need the files */
+ req->flags |= REQ_F_NO_FILE_TABLE | REQ_F_MUST_PUNT;
req->work.func = io_close_finish;
- /*
- * Do manual async queue here to avoid grabbing files - we don't
- * need the files, and it'll cause io_close_finish() to close
- * the file again and cause a double CQE entry for this request
- */
- io_queue_async_work(req);
- return 0;
+ return -EAGAIN;
}
/*
@@ -3502,7 +3509,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr)
if (io_req_cancelled(req))
return;
__io_sync_file_range(req);
- io_put_req(req); /* put submission ref */
+ io_steal_work(req, workptr);
}
static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
@@ -4103,27 +4110,6 @@ struct io_poll_table {
int error;
};
-static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
- struct wait_queue_head *head)
-{
- if (unlikely(poll->head)) {
- pt->error = -EINVAL;
- return;
- }
-
- pt->error = 0;
- poll->head = head;
- add_wait_queue(head, &poll->wait);
-}
-
-static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
- struct poll_table_struct *p)
-{
- struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
-
- __io_queue_proc(&pt->req->apoll->poll, pt, head);
-}
-
static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
__poll_t mask, task_work_func_t func)
{
@@ -4142,12 +4128,14 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
req->result = mask;
init_task_work(&req->task_work, func);
/*
- * If this fails, then the task is exiting. Punt to one of the io-wq
- * threads to ensure the work gets run, we can't always rely on exit
- * cancelation taking care of this.
+ * If this fails, then the task is exiting. When a task exits, the
+ * work gets canceled, so just cancel this request as well instead
+ * of executing it. We can't safely execute it anyway, as we may not
+ * have the needed state needed for it anyway.
*/
ret = task_work_add(tsk, &req->task_work, true);
if (unlikely(ret)) {
+ WRITE_ONCE(poll->canceled, true);
tsk = io_wq_get_task(req->ctx->io_wq);
task_work_add(tsk, &req->task_work, true);
}
@@ -4175,12 +4163,150 @@ static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll)
return false;
}
+static void io_poll_remove_double(struct io_kiocb *req)
+{
+ struct io_poll_iocb *poll = (struct io_poll_iocb *) req->io;
+
+ lockdep_assert_held(&req->ctx->completion_lock);
+
+ if (poll && poll->head) {
+ struct wait_queue_head *head = poll->head;
+
+ spin_lock(&head->lock);
+ list_del_init(&poll->wait.entry);
+ if (poll->wait.private)
+ refcount_dec(&req->refs);
+ poll->head = NULL;
+ spin_unlock(&head->lock);
+ }
+}
+
+static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ io_poll_remove_double(req);
+ req->poll.done = true;
+ io_cqring_fill_event(req, error ? error : mangle_poll(mask));
+ io_commit_cqring(ctx);
+}
+
+static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ if (io_poll_rewait(req, &req->poll)) {
+ spin_unlock_irq(&ctx->completion_lock);
+ return;
+ }
+
+ hash_del(&req->hash_node);
+ io_poll_complete(req, req->result, 0);
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_put_req_find_next(req, nxt);
+ spin_unlock_irq(&ctx->completion_lock);
+
+ io_cqring_ev_posted(ctx);
+}
+
+static void io_poll_task_func(struct callback_head *cb)
+{
+ struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+ struct io_kiocb *nxt = NULL;
+
+ io_poll_task_handler(req, &nxt);
+ if (nxt) {
+ struct io_ring_ctx *ctx = nxt->ctx;
+
+ mutex_lock(&ctx->uring_lock);
+ __io_queue_sqe(nxt, NULL);
+ mutex_unlock(&ctx->uring_lock);
+ }
+}
+
+static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct io_kiocb *req = wait->private;
+ struct io_poll_iocb *poll = (struct io_poll_iocb *) req->io;
+ __poll_t mask = key_to_poll(key);
+
+ /* for instances that support it check for an event match first: */
+ if (mask && !(mask & poll->events))
+ return 0;
+
+ if (req->poll.head) {
+ bool done;
+
+ spin_lock(&req->poll.head->lock);
+ done = list_empty(&req->poll.wait.entry);
+ if (!done)
+ list_del_init(&req->poll.wait.entry);
+ spin_unlock(&req->poll.head->lock);
+ if (!done)
+ __io_async_wake(req, poll, mask, io_poll_task_func);
+ }
+ refcount_dec(&req->refs);
+ return 1;
+}
+
+static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
+ wait_queue_func_t wake_func)
+{
+ poll->head = NULL;
+ poll->done = false;
+ poll->canceled = false;
+ poll->events = events;
+ INIT_LIST_HEAD(&poll->wait.entry);
+ init_waitqueue_func_entry(&poll->wait, wake_func);
+}
+
+static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
+ struct wait_queue_head *head)
+{
+ struct io_kiocb *req = pt->req;
+
+ /*
+ * If poll->head is already set, it's because the file being polled
+ * uses multiple waitqueues for poll handling (eg one for read, one
+ * for write). Setup a separate io_poll_iocb if this happens.
+ */
+ if (unlikely(poll->head)) {
+ /* already have a 2nd entry, fail a third attempt */
+ if (req->io) {
+ pt->error = -EINVAL;
+ return;
+ }
+ poll = kmalloc(sizeof(*poll), GFP_ATOMIC);
+ if (!poll) {
+ pt->error = -ENOMEM;
+ return;
+ }
+ io_init_poll_iocb(poll, req->poll.events, io_poll_double_wake);
+ refcount_inc(&req->refs);
+ poll->wait.private = req;
+ req->io = (void *) poll;
+ }
+
+ pt->error = 0;
+ poll->head = head;
+ add_wait_queue(head, &poll->wait);
+}
+
+static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
+ struct poll_table_struct *p)
+{
+ struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+
+ __io_queue_proc(&pt->req->apoll->poll, pt, head);
+}
+
static void io_async_task_func(struct callback_head *cb)
{
struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
struct async_poll *apoll = req->apoll;
struct io_ring_ctx *ctx = req->ctx;
- bool canceled;
+ bool canceled = false;
trace_io_uring_task_run(req->ctx, req->opcode, req->user_data);
@@ -4189,34 +4315,33 @@ static void io_async_task_func(struct callback_head *cb)
return;
}
- if (hash_hashed(&req->hash_node))
+ /* If req is still hashed, it cannot have been canceled. Don't check. */
+ if (hash_hashed(&req->hash_node)) {
hash_del(&req->hash_node);
-
- canceled = READ_ONCE(apoll->poll.canceled);
- if (canceled) {
- io_cqring_fill_event(req, -ECANCELED);
- io_commit_cqring(ctx);
+ } else {
+ canceled = READ_ONCE(apoll->poll.canceled);
+ if (canceled) {
+ io_cqring_fill_event(req, -ECANCELED);
+ io_commit_cqring(ctx);
+ }
}
spin_unlock_irq(&ctx->completion_lock);
- if (canceled) {
- kfree(apoll);
- io_cqring_ev_posted(ctx);
- req_set_fail_links(req);
- io_put_req(req);
- return;
- }
-
/* restore ->work in case we need to retry again */
memcpy(&req->work, &apoll->work, sizeof(req->work));
-
- __set_current_state(TASK_RUNNING);
- mutex_lock(&ctx->uring_lock);
- __io_queue_sqe(req, NULL);
- mutex_unlock(&ctx->uring_lock);
-
kfree(apoll);
+
+ if (!canceled) {
+ __set_current_state(TASK_RUNNING);
+ mutex_lock(&ctx->uring_lock);
+ __io_queue_sqe(req, NULL);
+ mutex_unlock(&ctx->uring_lock);
+ } else {
+ io_cqring_ev_posted(ctx);
+ req_set_fail_links(req);
+ io_double_put_req(req);
+ }
}
static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
@@ -4250,18 +4375,13 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
bool cancel = false;
poll->file = req->file;
- poll->head = NULL;
- poll->done = poll->canceled = false;
- poll->events = mask;
+ io_init_poll_iocb(poll, mask, wake_func);
+ poll->wait.private = req;
ipt->pt._key = mask;
ipt->req = req;
ipt->error = -EINVAL;
- INIT_LIST_HEAD(&poll->wait.entry);
- init_waitqueue_func_entry(&poll->wait, wake_func);
- poll->wait.private = req;
-
mask = vfs_poll(req->file, &ipt->pt) & poll->events;
spin_lock_irq(&ctx->completion_lock);
@@ -4292,6 +4412,7 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
struct async_poll *apoll;
struct io_poll_table ipt;
__poll_t mask, ret;
+ bool had_io;
if (!req->file || !file_can_poll(req->file))
return false;
@@ -4306,6 +4427,7 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
req->flags |= REQ_F_POLLED;
memcpy(&apoll->work, &req->work, sizeof(req->work));
+ had_io = req->io != NULL;
get_task_struct(current);
req->task = current;
@@ -4325,7 +4447,9 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
io_async_wake);
if (ret) {
ipt.error = 0;
- apoll->poll.done = true;
+ /* only remove double add if we did it here */
+ if (!had_io)
+ io_poll_remove_double(req);
spin_unlock_irq(&ctx->completion_lock);
memcpy(&req->work, &apoll->work, sizeof(req->work));
kfree(apoll);
@@ -4349,32 +4473,32 @@ static bool __io_poll_remove_one(struct io_kiocb *req,
do_complete = true;
}
spin_unlock(&poll->head->lock);
+ hash_del(&req->hash_node);
return do_complete;
}
static bool io_poll_remove_one(struct io_kiocb *req)
{
- struct async_poll *apoll = NULL;
bool do_complete;
if (req->opcode == IORING_OP_POLL_ADD) {
+ io_poll_remove_double(req);
do_complete = __io_poll_remove_one(req, &req->poll);
} else {
- apoll = req->apoll;
+ struct async_poll *apoll = req->apoll;
+
/* non-poll requests have submit ref still */
- do_complete = __io_poll_remove_one(req, &req->apoll->poll);
- if (do_complete)
+ do_complete = __io_poll_remove_one(req, &apoll->poll);
+ if (do_complete) {
io_put_req(req);
- }
-
- hash_del(&req->hash_node);
-
- if (apoll) {
- /*
- * restore ->work because we need to call io_req_work_drop_env.
- */
- memcpy(&req->work, &apoll->work, sizeof(req->work));
- kfree(apoll);
+ /*
+ * restore ->work because we will call
+ * io_req_work_drop_env below when dropping the
+ * final reference.
+ */
+ memcpy(&req->work, &apoll->work, sizeof(req->work));
+ kfree(apoll);
+ }
}
if (do_complete) {
@@ -4459,49 +4583,6 @@ static int io_poll_remove(struct io_kiocb *req)
return 0;
}
-static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error)
-{
- struct io_ring_ctx *ctx = req->ctx;
-
- req->poll.done = true;
- io_cqring_fill_event(req, error ? error : mangle_poll(mask));
- io_commit_cqring(ctx);
-}
-
-static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_poll_iocb *poll = &req->poll;
-
- if (io_poll_rewait(req, poll)) {
- spin_unlock_irq(&ctx->completion_lock);
- return;
- }
-
- hash_del(&req->hash_node);
- io_poll_complete(req, req->result, 0);
- req->flags |= REQ_F_COMP_LOCKED;
- io_put_req_find_next(req, nxt);
- spin_unlock_irq(&ctx->completion_lock);
-
- io_cqring_ev_posted(ctx);
-}
-
-static void io_poll_task_func(struct callback_head *cb)
-{
- struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
- struct io_kiocb *nxt = NULL;
-
- io_poll_task_handler(req, &nxt);
- if (nxt) {
- struct io_ring_ctx *ctx = nxt->ctx;
-
- mutex_lock(&ctx->uring_lock);
- __io_queue_sqe(nxt, NULL);
- mutex_unlock(&ctx->uring_lock);
- }
-}
-
static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
void *key)
{
@@ -4581,20 +4662,8 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
* We could be racing with timeout deletion. If the list is empty,
* then timeout lookup already found it and will be handling it.
*/
- if (!list_empty(&req->list)) {
- struct io_kiocb *prev;
-
- /*
- * Adjust the reqs sequence before the current one because it
- * will consume a slot in the cq_ring and the cq_tail
- * pointer will be increased, otherwise other timeout reqs may
- * return in advance without waiting for enough wait_nr.
- */
- prev = req;
- list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
- prev->sequence++;
+ if (!list_empty(&req->list))
list_del_init(&req->list);
- }
io_cqring_fill_event(req, -ETIME);
io_commit_cqring(ctx);
@@ -4674,18 +4743,19 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
{
struct io_timeout_data *data;
unsigned flags;
+ u32 off = READ_ONCE(sqe->off);
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
if (sqe->ioprio || sqe->buf_index || sqe->len != 1)
return -EINVAL;
- if (sqe->off && is_timeout_link)
+ if (off && is_timeout_link)
return -EINVAL;
flags = READ_ONCE(sqe->timeout_flags);
if (flags & ~IORING_TIMEOUT_ABS)
return -EINVAL;
- req->timeout.count = READ_ONCE(sqe->off);
+ req->timeout.off = off;
if (!req->io && io_alloc_async_ctx(req))
return -ENOMEM;
@@ -4709,68 +4779,39 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
static int io_timeout(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
- struct io_timeout_data *data;
+ struct io_timeout_data *data = &req->io->timeout;
struct list_head *entry;
- unsigned span = 0;
- u32 count = req->timeout.count;
- u32 seq = req->sequence;
+ u32 tail, off = req->timeout.off;
- data = &req->io->timeout;
+ spin_lock_irq(&ctx->completion_lock);
/*
* sqe->off holds how many events that need to occur for this
* timeout event to be satisfied. If it isn't set, then this is
* a pure timeout request, sequence isn't used.
*/
- if (!count) {
+ if (!off) {
req->flags |= REQ_F_TIMEOUT_NOSEQ;
- spin_lock_irq(&ctx->completion_lock);
entry = ctx->timeout_list.prev;
goto add;
}
- req->sequence = seq + count;
+ tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+ req->timeout.target_seq = tail + off;
/*
* Insertion sort, ensuring the first entry in the list is always
* the one we need first.
*/
- spin_lock_irq(&ctx->completion_lock);
list_for_each_prev(entry, &ctx->timeout_list) {
struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list);
- unsigned nxt_seq;
- long long tmp, tmp_nxt;
- u32 nxt_offset = nxt->timeout.count;
if (nxt->flags & REQ_F_TIMEOUT_NOSEQ)
continue;
-
- /*
- * Since seq + count can overflow, use type long
- * long to store it.
- */
- tmp = (long long)seq + count;
- nxt_seq = nxt->sequence - nxt_offset;
- tmp_nxt = (long long)nxt_seq + nxt_offset;
-
- /*
- * cached_sq_head may overflow, and it will never overflow twice
- * once there is some timeout req still be valid.
- */
- if (seq < nxt_seq)
- tmp += UINT_MAX;
-
- if (tmp > tmp_nxt)
+ /* nxt.seq is behind @tail, otherwise would've been completed */
+ if (off >= nxt->timeout.target_seq - tail)
break;
-
- /*
- * Sequence of reqs after the insert one and itself should
- * be adjusted because each timeout req consumes a slot.
- */
- span++;
- nxt->sequence++;
}
- req->sequence -= span;
add:
list_add(&req->list, entry);
data->timer.function = io_timeout_fn;
@@ -4999,6 +5040,9 @@ static int io_req_defer_prep(struct io_kiocb *req,
case IORING_OP_REMOVE_BUFFERS:
ret = io_remove_buffers_prep(req, sqe);
break;
+ case IORING_OP_TEE:
+ ret = io_tee_prep(req, sqe);
+ break;
default:
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
@@ -5015,15 +5059,16 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe)
int ret;
/* Still need defer if there is pending req in defer list. */
- if (!req_need_defer(req) && list_empty(&ctx->defer_list))
+ if (!req_need_defer(req) && list_empty_careful(&ctx->defer_list))
return 0;
- if (!req->io && io_alloc_async_ctx(req))
- return -EAGAIN;
-
- ret = io_req_defer_prep(req, sqe);
- if (ret < 0)
- return ret;
+ if (!req->io) {
+ if (io_alloc_async_ctx(req))
+ return -EAGAIN;
+ ret = io_req_defer_prep(req, sqe);
+ if (ret < 0)
+ return ret;
+ }
spin_lock_irq(&ctx->completion_lock);
if (!req_need_defer(req) && list_empty(&ctx->defer_list)) {
@@ -5068,10 +5113,9 @@ static void io_cleanup_req(struct io_kiocb *req)
break;
case IORING_OP_OPENAT:
case IORING_OP_OPENAT2:
- case IORING_OP_STATX:
- putname(req->open.filename);
break;
case IORING_OP_SPLICE:
+ case IORING_OP_TEE:
io_put_file(req, req->splice.file_in,
(req->splice.flags & SPLICE_F_FD_IN_FIXED));
break;
@@ -5302,6 +5346,14 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
ret = io_remove_buffers(req, force_nonblock);
break;
+ case IORING_OP_TEE:
+ if (sqe) {
+ ret = io_tee_prep(req, sqe);
+ if (ret < 0)
+ break;
+ }
+ ret = io_tee(req, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;
@@ -5310,7 +5362,8 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (ret)
return ret;
- if (ctx->flags & IORING_SETUP_IOPOLL) {
+ /* If the op doesn't have a file, we're not polling for it */
+ if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) {
const bool in_async = io_wq_current_is_worker();
if (req->result == -EAGAIN)
@@ -5364,22 +5417,13 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
io_steal_work(req, workptr);
}
-static int io_req_needs_file(struct io_kiocb *req, int fd)
-{
- if (!io_op_defs[req->opcode].needs_file)
- return 0;
- if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
- return 0;
- return 1;
-}
-
static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
int index)
{
struct fixed_file_table *table;
table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT];
- return table->files[index & IORING_FILE_TABLE_MASK];;
+ return table->files[index & IORING_FILE_TABLE_MASK];
}
static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
@@ -5410,15 +5454,12 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
}
static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
- int fd, unsigned int flags)
+ int fd)
{
bool fixed;
- if (!io_req_needs_file(req, fd))
- return 0;
-
- fixed = (flags & IOSQE_FIXED_FILE);
- if (unlikely(!fixed && req->needs_fixed_file))
+ fixed = (req->flags & REQ_F_FIXED_FILE) != 0;
+ if (unlikely(!fixed && io_async_submit(req->ctx)))
return -EBADF;
return io_file_get(state, req, fd, &req->file, fixed);
@@ -5429,7 +5470,7 @@ static int io_grab_files(struct io_kiocb *req)
int ret = -EBADF;
struct io_ring_ctx *ctx = req->ctx;
- if (req->work.files)
+ if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
return 0;
if (!ctx->ring_file)
return -EBADF;
@@ -5623,9 +5664,15 @@ fail_req:
io_double_put_req(req);
}
} else if (req->flags & REQ_F_FORCE_ASYNC) {
- ret = io_req_defer_prep(req, sqe);
- if (unlikely(ret < 0))
- goto fail_req;
+ if (!req->io) {
+ ret = -EAGAIN;
+ if (io_alloc_async_ctx(req))
+ goto fail_req;
+ ret = io_req_defer_prep(req, sqe);
+ if (unlikely(ret < 0))
+ goto fail_req;
+ }
+
/*
* Never try inline submit of IOSQE_ASYNC is set, go straight
* to async execution.
@@ -5647,7 +5694,7 @@ static inline void io_queue_link_head(struct io_kiocb *req)
}
static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- struct io_submit_state *state, struct io_kiocb **link)
+ struct io_kiocb **link)
{
struct io_ring_ctx *ctx = req->ctx;
int ret;
@@ -5720,7 +5767,7 @@ static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
static void io_submit_state_end(struct io_submit_state *state)
{
blk_finish_plug(&state->plug);
- io_file_put(state);
+ io_state_file_put(state);
if (state->free_reqs)
kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs);
}
@@ -5791,10 +5838,10 @@ static inline void io_consume_sqe(struct io_ring_ctx *ctx)
static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe,
- struct io_submit_state *state, bool async)
+ struct io_submit_state *state)
{
unsigned int sqe_flags;
- int id, fd;
+ int id;
/*
* All io need record the previous position, if LINK vs DARIN,
@@ -5812,7 +5859,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
refcount_set(&req->refs, 2);
req->task = NULL;
req->result = 0;
- req->needs_fixed_file = async;
INIT_IO_WORK(&req->work, io_wq_submit_work);
if (unlikely(req->opcode >= IORING_OP_LAST))
@@ -5842,16 +5888,16 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
}
/* same numerical values with corresponding REQ_F_*, safe to copy */
- req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK |
- IOSQE_ASYNC | IOSQE_FIXED_FILE |
- IOSQE_BUFFER_SELECT | IOSQE_IO_LINK);
+ req->flags |= sqe_flags;
- fd = READ_ONCE(sqe->fd);
- return io_req_set_file(state, req, fd, sqe_flags);
+ if (!io_op_defs[req->opcode].needs_file)
+ return 0;
+
+ return io_req_set_file(state, req, READ_ONCE(sqe->fd));
}
static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
- struct file *ring_file, int ring_fd, bool async)
+ struct file *ring_file, int ring_fd)
{
struct io_submit_state state, *statep = NULL;
struct io_kiocb *link = NULL;
@@ -5895,7 +5941,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
break;
}
- err = io_init_req(ctx, req, sqe, statep, async);
+ err = io_init_req(ctx, req, sqe, statep);
io_consume_sqe(ctx);
/* will complete beyond this point, count as submitted */
submitted++;
@@ -5908,8 +5954,8 @@ fail_req:
}
trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
- true, async);
- err = io_submit_sqe(req, sqe, statep, &link);
+ true, io_async_submit(ctx));
+ err = io_submit_sqe(req, sqe, &link);
if (err)
goto fail_req;
}
@@ -5949,7 +5995,7 @@ static int io_sq_thread(void *data)
unsigned long timeout;
int ret = 0;
- complete(&ctx->completions[1]);
+ complete(&ctx->sq_thread_comp);
old_fs = get_fs();
set_fs(USER_DS);
@@ -6039,6 +6085,7 @@ static int io_sq_thread(void *data)
finish_wait(&ctx->sqo_wait, &wait);
ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+ ret = 0;
continue;
}
finish_wait(&ctx->sqo_wait, &wait);
@@ -6047,7 +6094,8 @@ static int io_sq_thread(void *data)
}
mutex_lock(&ctx->uring_lock);
- ret = io_submit_sqes(ctx, to_submit, NULL, -1, true);
+ if (likely(!percpu_ref_is_dying(&ctx->refs)))
+ ret = io_submit_sqes(ctx, to_submit, NULL, -1);
mutex_unlock(&ctx->uring_lock);
timeout = jiffies + ctx->sq_thread_idle;
}
@@ -6195,22 +6243,22 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
struct fixed_file_data *data = ctx->file_data;
struct fixed_file_ref_node *ref_node = NULL;
unsigned nr_tables, i;
- unsigned long flags;
if (!data)
return -ENXIO;
- spin_lock_irqsave(&data->lock, flags);
+ spin_lock(&data->lock);
if (!list_empty(&data->ref_list))
ref_node = list_first_entry(&data->ref_list,
struct fixed_file_ref_node, node);
- spin_unlock_irqrestore(&data->lock, flags);
+ spin_unlock(&data->lock);
if (ref_node)
percpu_ref_kill(&ref_node->refs);
percpu_ref_kill(&data->refs);
/* wait for all refs nodes to complete */
+ flush_delayed_work(&ctx->file_put_work);
wait_for_completion(&data->done);
__io_sqe_files_unregister(ctx);
@@ -6228,7 +6276,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
static void io_sq_thread_stop(struct io_ring_ctx *ctx)
{
if (ctx->sqo_thread) {
- wait_for_completion(&ctx->completions[1]);
+ wait_for_completion(&ctx->sq_thread_comp);
/*
* The park is a bit of a work-around, without it we get
* warning spews on shutdown with SQPOLL set and affinity
@@ -6441,40 +6489,63 @@ struct io_file_put {
struct file *file;
};
-static void io_file_put_work(struct work_struct *work)
+static void __io_file_put_work(struct fixed_file_ref_node *ref_node)
{
- struct fixed_file_ref_node *ref_node;
- struct fixed_file_data *file_data;
- struct io_ring_ctx *ctx;
+ struct fixed_file_data *file_data = ref_node->file_data;
+ struct io_ring_ctx *ctx = file_data->ctx;
struct io_file_put *pfile, *tmp;
- unsigned long flags;
-
- ref_node = container_of(work, struct fixed_file_ref_node, work);
- file_data = ref_node->file_data;
- ctx = file_data->ctx;
list_for_each_entry_safe(pfile, tmp, &ref_node->file_list, list) {
- list_del_init(&pfile->list);
+ list_del(&pfile->list);
io_ring_file_put(ctx, pfile->file);
kfree(pfile);
}
- spin_lock_irqsave(&file_data->lock, flags);
- list_del_init(&ref_node->node);
- spin_unlock_irqrestore(&file_data->lock, flags);
+ spin_lock(&file_data->lock);
+ list_del(&ref_node->node);
+ spin_unlock(&file_data->lock);
percpu_ref_exit(&ref_node->refs);
kfree(ref_node);
percpu_ref_put(&file_data->refs);
}
+static void io_file_put_work(struct work_struct *work)
+{
+ struct io_ring_ctx *ctx;
+ struct llist_node *node;
+
+ ctx = container_of(work, struct io_ring_ctx, file_put_work.work);
+ node = llist_del_all(&ctx->file_put_llist);
+
+ while (node) {
+ struct fixed_file_ref_node *ref_node;
+ struct llist_node *next = node->next;
+
+ ref_node = llist_entry(node, struct fixed_file_ref_node, llist);
+ __io_file_put_work(ref_node);
+ node = next;
+ }
+}
+
static void io_file_data_ref_zero(struct percpu_ref *ref)
{
struct fixed_file_ref_node *ref_node;
+ struct io_ring_ctx *ctx;
+ bool first_add;
+ int delay = HZ;
ref_node = container_of(ref, struct fixed_file_ref_node, refs);
+ ctx = ref_node->file_data->ctx;
- queue_work(system_wq, &ref_node->work);
+ if (percpu_ref_is_dying(&ctx->file_data->refs))
+ delay = 0;
+
+ first_add = llist_add(&ref_node->llist, &ctx->file_put_llist);
+ if (!delay)
+ mod_delayed_work(system_wq, &ctx->file_put_work, 0);
+ else if (first_add)
+ queue_delayed_work(system_wq, &ctx->file_put_work, delay);
}
static struct fixed_file_ref_node *alloc_fixed_file_ref_node(
@@ -6493,10 +6564,8 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node(
}
INIT_LIST_HEAD(&ref_node->node);
INIT_LIST_HEAD(&ref_node->file_list);
- INIT_WORK(&ref_node->work, io_file_put_work);
ref_node->file_data = ctx->file_data;
return ref_node;
-
}
static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node)
@@ -6514,7 +6583,6 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
int fd, ret = 0;
unsigned i;
struct fixed_file_ref_node *ref_node;
- unsigned long flags;
if (ctx->file_data)
return -EBUSY;
@@ -6622,9 +6690,9 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
}
ctx->file_data->cur_refs = &ref_node->refs;
- spin_lock_irqsave(&ctx->file_data->lock, flags);
+ spin_lock(&ctx->file_data->lock);
list_add(&ref_node->node, &ctx->file_data->ref_list);
- spin_unlock_irqrestore(&ctx->file_data->lock, flags);
+ spin_unlock(&ctx->file_data->lock);
percpu_ref_get(&ctx->file_data->refs);
return ret;
}
@@ -6700,7 +6768,6 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
__s32 __user *fds;
int fd, i, err;
__u32 done;
- unsigned long flags;
bool needs_switch = false;
if (check_add_overflow(up->offset, nr_args, &done))
@@ -6765,10 +6832,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
if (needs_switch) {
percpu_ref_kill(data->cur_refs);
- spin_lock_irqsave(&data->lock, flags);
+ spin_lock(&data->lock);
list_add(&ref_node->node, &data->ref_list);
data->cur_refs = &ref_node->refs;
- spin_unlock_irqrestore(&data->lock, flags);
+ spin_unlock(&data->lock);
percpu_ref_get(&ctx->file_data->refs);
} else
destroy_fixed_file_ref_node(ref_node);
@@ -6852,7 +6919,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
{
int ret;
- init_waitqueue_head(&ctx->sqo_wait);
mmgrab(current->mm);
ctx->sqo_mm = current->mm;
@@ -7120,7 +7186,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
}
ret = 0;
- down_read(&current->mm->mmap_sem);
+ mmap_read_lock(current->mm);
pret = pin_user_pages(ubuf, nr_pages,
FOLL_WRITE | FOLL_LONGTERM,
pages, vmas);
@@ -7138,7 +7204,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
} else {
ret = pret < 0 ? pret : -EFAULT;
}
- up_read(&current->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
if (ret) {
/*
* if we did partial map, or found file backed vmas,
@@ -7257,7 +7323,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
ring_pages(ctx->sq_entries, ctx->cq_entries));
free_uid(ctx->user);
put_cred(ctx->creds);
- kfree(ctx->completions);
kfree(ctx->cancel_hash);
kmem_cache_free(req_cachep, ctx->fallback_req);
kfree(ctx);
@@ -7309,7 +7374,7 @@ static void io_ring_exit_work(struct work_struct *work)
if (ctx->rings)
io_cqring_overflow_flush(ctx, true);
- wait_for_completion(&ctx->completions[0]);
+ wait_for_completion(&ctx->ref_comp);
io_ring_ctx_free(ctx);
}
@@ -7319,16 +7384,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
percpu_ref_kill(&ctx->refs);
mutex_unlock(&ctx->uring_lock);
- /*
- * Wait for sq thread to idle, if we have one. It won't spin on new
- * work after we've killed the ctx ref above. This is important to do
- * before we cancel existing commands, as the thread could otherwise
- * be queueing new work post that. If that's work we need to cancel,
- * it could cause shutdown to hang.
- */
- while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait))
- cpu_relax();
-
io_kill_timeouts(ctx);
io_poll_remove_all(ctx);
@@ -7356,11 +7411,9 @@ static int io_uring_release(struct inode *inode, struct file *file)
static void io_uring_cancel_files(struct io_ring_ctx *ctx,
struct files_struct *files)
{
- struct io_kiocb *req;
- DEFINE_WAIT(wait);
-
while (!list_empty_careful(&ctx->inflight_list)) {
- struct io_kiocb *cancel_req = NULL;
+ struct io_kiocb *cancel_req = NULL, *req;
+ DEFINE_WAIT(wait);
spin_lock_irq(&ctx->inflight_lock);
list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
@@ -7399,16 +7452,18 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
* all we had, then we're done with this request.
*/
if (refcount_sub_and_test(2, &cancel_req->refs)) {
- io_put_req(cancel_req);
+ io_free_req(cancel_req);
+ finish_wait(&ctx->inflight_wait, &wait);
continue;
}
+ } else {
+ io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
+ io_put_req(cancel_req);
}
- io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
- io_put_req(cancel_req);
schedule();
+ finish_wait(&ctx->inflight_wait, &wait);
}
- finish_wait(&ctx->inflight_wait, &wait);
}
static int io_uring_flush(struct file *file, void *data)
@@ -7538,7 +7593,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
submitted = to_submit;
} else if (to_submit) {
mutex_lock(&ctx->uring_lock);
- submitted = io_submit_sqes(ctx, to_submit, f.file, fd, false);
+ submitted = io_submit_sqes(ctx, to_submit, f.file, fd);
mutex_unlock(&ctx->uring_lock);
if (submitted != to_submit)
@@ -7757,7 +7812,8 @@ err:
return ret;
}
-static int io_uring_create(unsigned entries, struct io_uring_params *p)
+static int io_uring_create(unsigned entries, struct io_uring_params *p,
+ struct io_uring_params __user *params)
{
struct user_struct *user = NULL;
struct io_ring_ctx *ctx;
@@ -7848,7 +7904,16 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries);
p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
p->cq_off.cqes = offsetof(struct io_rings, cqes);
+ p->cq_off.flags = offsetof(struct io_rings, cq_flags);
+
+ p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+ IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+ IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+ if (copy_to_user(params, p, sizeof(*p))) {
+ ret = -EFAULT;
+ goto err;
+ }
/*
* Install ring fd as the very last thing, so we don't risk someone
* having closed it before we finish setup
@@ -7857,9 +7922,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
if (ret < 0)
goto err;
- p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
- IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
- IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
@@ -7875,7 +7937,6 @@ err:
static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
{
struct io_uring_params p;
- long ret;
int i;
if (copy_from_user(&p, params, sizeof(p)))
@@ -7890,14 +7951,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
return -EINVAL;
- ret = io_uring_create(entries, &p);
- if (ret < 0)
- return ret;
-
- if (copy_to_user(params, &p, sizeof(p)))
- return -EFAULT;
-
- return ret;
+ return io_uring_create(entries, &p, params);
}
SYSCALL_DEFINE2(io_uring_setup, u32, entries,
@@ -8011,7 +8065,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
* after we've killed the percpu ref.
*/
mutex_unlock(&ctx->uring_lock);
- ret = wait_for_completion_interruptible(&ctx->completions[0]);
+ ret = wait_for_completion_interruptible(&ctx->ref_comp);
mutex_lock(&ctx->uring_lock);
if (ret) {
percpu_ref_resurrect(&ctx->refs);
@@ -8088,7 +8142,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
/* bring the ctx back to life */
percpu_ref_reinit(&ctx->refs);
out:
- reinit_completion(&ctx->completions[0]);
+ reinit_completion(&ctx->ref_comp);
}
return ret;
}
Powered by cgit, Gruvboxed by Blaster4385.