summaryrefslogtreecommitdiff
path: root/io_uring
diff options
context:
space:
mode:
Diffstat (limited to 'io_uring')
-rw-r--r--io_uring/io-wq.c4
-rw-r--r--io_uring/io_uring.c2
-rw-r--r--io_uring/kbuf.c8
-rw-r--r--io_uring/kbuf.h1
-rw-r--r--io_uring/net.c58
-rw-r--r--io_uring/opdef.c1
-rw-r--r--io_uring/poll.c2
-rw-r--r--io_uring/rsrc.c23
-rw-r--r--io_uring/rsrc.h1
-rw-r--r--io_uring/rw.c2
-rw-r--r--io_uring/sqpoll.c5
11 files changed, 78 insertions, 29 deletions
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index a2d577b09930..8f555c1d7185 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1204,8 +1204,10 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
atomic_set(&wq->worker_refs, 1);
init_completion(&wq->worker_done);
ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node);
- if (ret)
+ if (ret) {
+ put_task_struct(wq->task);
goto err;
+ }
return wq;
err:
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 64870f51b678..52ada466bf98 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1681,7 +1681,7 @@ queue:
spin_unlock(&ctx->completion_lock);
io_prep_async_link(req);
- de = kmalloc(sizeof(*de), GFP_KERNEL);
+ de = kmalloc(sizeof(*de), GFP_KERNEL_ACCOUNT);
if (!de) {
ret = -ENOMEM;
io_req_defer_failed(req, ret);
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 7a8c3a004800..9bd27deeee6f 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -262,8 +262,12 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
/* truncate end piece, if needed, for non partial buffers */
if (len > arg->max_len) {
len = arg->max_len;
- if (!(bl->flags & IOBL_INC))
+ if (!(bl->flags & IOBL_INC)) {
+ arg->partial_map = 1;
+ if (iov != arg->iovs)
+ break;
buf->len = len;
+ }
}
iov->iov_base = u64_to_user_ptr(buf->addr);
@@ -728,7 +732,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
io_destroy_bl(ctx, bl);
}
- free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL);
+ free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT);
if (!bl)
return -ENOMEM;
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 36aadfe5ac00..2586a292dfb9 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -61,6 +61,7 @@ struct buf_sel_arg {
size_t max_len;
unsigned short nr_iovs;
unsigned short mode;
+ unsigned short partial_map;
};
void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
diff --git a/io_uring/net.c b/io_uring/net.c
index 384915d931b7..356f95c33aa2 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -76,12 +76,18 @@ struct io_sr_msg {
/* initialised and used only by !msg send variants */
u16 addr_len;
u16 buf_group;
+ unsigned short retry_flags;
void __user *addr;
void __user *msg_control;
/* used only for send zerocopy */
struct io_kiocb *notif;
};
+enum sr_retry_flags {
+ IO_SR_MSG_RETRY = 1,
+ IO_SR_MSG_PARTIAL_MAP = 2,
+};
+
/*
* Number of times we'll try and do receives if there's more data. If we
* exceed this limit, then add us to the back of the queue and retry from
@@ -203,6 +209,7 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req,
req->flags &= ~REQ_F_BL_EMPTY;
sr->done_io = 0;
+ sr->retry_flags = 0;
sr->len = 0; /* get from the provided buffer */
req->buf_index = sr->buf_group;
}
@@ -409,6 +416,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
sr->done_io = 0;
+ sr->retry_flags = 0;
if (req->opcode == IORING_OP_SEND) {
if (READ_ONCE(sqe->__pad3[0]))
@@ -780,6 +788,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
sr->done_io = 0;
+ sr->retry_flags = 0;
if (unlikely(sqe->file_index || sqe->addr2))
return -EINVAL;
@@ -828,6 +837,9 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return io_recvmsg_prep_setup(req);
}
+/* bits to clear in old and inherit in new cflags on bundle retry */
+#define CQE_F_MASK (IORING_CQE_F_SOCK_NONEMPTY|IORING_CQE_F_MORE)
+
/*
* Finishes io_recv and io_recvmsg.
*
@@ -845,11 +857,27 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
cflags |= IORING_CQE_F_SOCK_NONEMPTY;
if (sr->flags & IORING_RECVSEND_BUNDLE) {
- cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, *ret),
+ size_t this_ret = *ret - sr->done_io;
+
+ cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret),
issue_flags);
+ if (sr->retry_flags & IO_SR_MSG_RETRY)
+ cflags = req->cqe.flags | (cflags & CQE_F_MASK);
/* bundle with no more immediate buffers, we're done */
if (req->flags & REQ_F_BL_EMPTY)
goto finish;
+ /*
+ * If more is available AND it was a full transfer, retry and
+ * append to this one
+ */
+ if (!sr->retry_flags && kmsg->msg.msg_inq > 1 && this_ret > 0 &&
+ !iov_iter_count(&kmsg->msg.msg_iter)) {
+ req->cqe.flags = cflags & ~CQE_F_MASK;
+ sr->len = kmsg->msg.msg_inq;
+ sr->done_io += this_ret;
+ sr->retry_flags |= IO_SR_MSG_RETRY;
+ return false;
+ }
} else {
cflags |= io_put_kbuf(req, *ret, issue_flags);
}
@@ -1088,13 +1116,21 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
arg.mode |= KBUF_MODE_FREE;
}
- if (kmsg->msg.msg_inq > 0)
+ if (kmsg->msg.msg_inq > 1)
arg.max_len = min_not_zero(sr->len, kmsg->msg.msg_inq);
ret = io_buffers_peek(req, &arg);
if (unlikely(ret < 0))
return ret;
+ if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
+ kmsg->free_iov_nr = ret;
+ kmsg->free_iov = arg.iovs;
+ req->flags |= REQ_F_NEED_CLEANUP;
+ }
+ if (arg.partial_map)
+ sr->retry_flags |= IO_SR_MSG_PARTIAL_MAP;
+
/* special case 1 vec, can be a fast path */
if (ret == 1) {
sr->buf = arg.iovs[0].iov_base;
@@ -1103,11 +1139,6 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
}
iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret,
arg.out_len);
- if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
- kmsg->free_iov_nr = ret;
- kmsg->free_iov = arg.iovs;
- req->flags |= REQ_F_NEED_CLEANUP;
- }
} else {
void __user *buf;
@@ -1228,6 +1259,7 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
struct io_kiocb *notif;
zc->done_io = 0;
+ zc->retry_flags = 0;
req->flags |= REQ_F_POLL_NO_LAZY;
if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)))
@@ -1703,9 +1735,11 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags)
int ret;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- if (unlikely(req->flags & REQ_F_FAIL)) {
- ret = -ECONNRESET;
- goto out;
+ if (connect->in_progress) {
+ struct poll_table_struct pt = { ._key = EPOLLERR };
+
+ if (vfs_poll(req->file, &pt) & EPOLLERR)
+ goto get_sock_err;
}
file_flags = force_nonblock ? O_NONBLOCK : 0;
@@ -1730,8 +1764,10 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags)
* which means the previous result is good. For both of these,
* grab the sock_error() and use that for the completion.
*/
- if (ret == -EBADFD || ret == -EISCONN)
+ if (ret == -EBADFD || ret == -EISCONN) {
+get_sock_err:
ret = sock_error(sock_from_file(req->file)->sk);
+ }
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index a2be3bbca5ff..5dc1cba158a0 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -214,6 +214,7 @@ const struct io_issue_def io_issue_defs[] = {
},
[IORING_OP_FALLOCATE] = {
.needs_file = 1,
+ .hash_reg_file = 1,
.prep = io_fallocate_prep,
.issue = io_fallocate,
},
diff --git a/io_uring/poll.c b/io_uring/poll.c
index b93e9ebdd87c..17dea8aa09c9 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -315,8 +315,6 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
return IOU_POLL_REISSUE;
}
}
- if (unlikely(req->cqe.res & EPOLLERR))
- req_set_fail(req);
if (req->apoll_events & EPOLLONESHOT)
return IOU_POLL_DONE;
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index a67bae350416..1687e35e21c9 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -119,8 +119,11 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slo
if (imu != &dummy_ubuf) {
if (!refcount_dec_and_test(&imu->refs))
return;
- for (i = 0; i < imu->nr_bvecs; i++)
- unpin_user_page(imu->bvec[i].bv_page);
+ for (i = 0; i < imu->nr_bvecs; i++) {
+ struct folio *folio = page_folio(imu->bvec[i].bv_page);
+
+ unpin_user_folio(folio, 1);
+ }
if (imu->acct_pages)
io_unaccount_mem(ctx, imu->acct_pages);
kvfree(imu);
@@ -915,6 +918,7 @@ static bool io_try_coalesce_buffer(struct page ***pages, int *nr_pages,
return false;
data->folio_shift = folio_shift(folio);
+ data->first_folio_page_idx = folio_page_idx(folio, page_array[0]);
/*
* Check if pages are contiguous inside a folio, and all folios have
* the same page count except for the head and tail.
@@ -983,10 +987,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
goto done;
ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage);
- if (ret) {
- unpin_user_pages(pages, nr_pages);
+ if (ret)
goto done;
- }
size = iov->iov_len;
/* store original address for later verification */
@@ -997,7 +999,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
if (coalesced)
imu->folio_shift = data.folio_shift;
refcount_set(&imu->refs, 1);
- off = (unsigned long) iov->iov_base & ((1UL << imu->folio_shift) - 1);
+ off = (unsigned long)iov->iov_base & ~PAGE_MASK;
+ if (coalesced)
+ off += data.first_folio_page_idx << PAGE_SHIFT;
*pimu = imu;
ret = 0;
@@ -1010,8 +1014,13 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
size -= vec_len;
}
done:
- if (ret)
+ if (ret) {
kvfree(imu);
+ if (pages) {
+ for (i = 0; i < nr_pages; i++)
+ unpin_user_folio(page_folio(pages[i]), 1);
+ }
+ }
kvfree(pages);
return ret;
}
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 8ed588036210..459cf4c6e856 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -56,6 +56,7 @@ struct io_imu_folio_data {
/* For non-head/tail folios, has to be fully included */
unsigned int nr_pages_mid;
unsigned int folio_shift;
+ unsigned long first_folio_page_idx;
};
void io_rsrc_node_ref_zero(struct io_rsrc_node *node);
diff --git a/io_uring/rw.c b/io_uring/rw.c
index a1ed64760eba..3ad104cf1e7d 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -282,7 +282,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
rw->addr = READ_ONCE(sqe->addr);
rw->len = READ_ONCE(sqe->len);
- rw->flags = READ_ONCE(sqe->rw_flags);
+ rw->flags = (__force rwf_t) READ_ONCE(sqe->rw_flags);
return io_prep_rw_setup(req, ddir, do_import);
}
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 9a6306894895..2faa3058b2d0 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -426,7 +426,6 @@ void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
__cold int io_sq_offload_create(struct io_ring_ctx *ctx,
struct io_uring_params *p)
{
- struct task_struct *task_to_put = NULL;
int ret;
/* Retain compatibility with failing for an invalid attach attempt */
@@ -510,7 +509,7 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
rcu_assign_pointer(sqd->thread, tsk);
mutex_unlock(&sqd->lock);
- task_to_put = get_task_struct(tsk);
+ get_task_struct(tsk);
ret = io_uring_alloc_task_context(tsk, ctx);
wake_up_new_task(tsk);
if (ret)
@@ -525,8 +524,6 @@ err_sqpoll:
complete(&ctx->sq_data->exited);
err:
io_sq_thread_finish(ctx);
- if (task_to_put)
- put_task_struct(task_to_put);
return ret;
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-25 10:07:37 +0300