summaryrefslogtreecommitdiff
path: root/io_uring
diff options
context:
space:
mode:
Diffstat (limited to 'io_uring')
-rw-r--r--io_uring/Kconfig10
-rw-r--r--io_uring/Makefile10
-rw-r--r--io_uring/alloc_cache.h15
-rw-r--r--io_uring/cancel.c42
-rw-r--r--io_uring/cancel.h8
-rw-r--r--io_uring/epoll.c35
-rw-r--r--io_uring/epoll.h2
-rw-r--r--io_uring/filetable.c2
-rw-r--r--io_uring/futex.c62
-rw-r--r--io_uring/io-wq.c230
-rw-r--r--io_uring/io-wq.h7
-rw-r--r--io_uring/io_uring.c332
-rw-r--r--io_uring/io_uring.h44
-rw-r--r--io_uring/kbuf.c200
-rw-r--r--io_uring/kbuf.h100
-rw-r--r--io_uring/memmap.c2
-rw-r--r--io_uring/memmap.h1
-rw-r--r--io_uring/msg_ring.c2
-rw-r--r--io_uring/napi.c4
-rw-r--r--io_uring/net.c511
-rw-r--r--io_uring/net.h6
-rw-r--r--io_uring/nop.c18
-rw-r--r--io_uring/notif.c4
-rw-r--r--io_uring/opdef.c76
-rw-r--r--io_uring/opdef.h12
-rw-r--r--io_uring/poll.c23
-rw-r--r--io_uring/poll.h4
-rw-r--r--io_uring/register.c7
-rw-r--r--io_uring/rsrc.c411
-rw-r--r--io_uring/rsrc.h49
-rw-r--r--io_uring/rw.c294
-rw-r--r--io_uring/rw.h11
-rw-r--r--io_uring/splice.c3
-rw-r--r--io_uring/timeout.c29
-rw-r--r--io_uring/uring_cmd.c92
-rw-r--r--io_uring/uring_cmd.h17
-rw-r--r--io_uring/waitid.c56
-rw-r--r--io_uring/zcrx.c960
-rw-r--r--io_uring/zcrx.h73
39 files changed, 2717 insertions, 1047 deletions
diff --git a/io_uring/Kconfig b/io_uring/Kconfig
new file mode 100644
index 000000000000..9e2a4beba1ef
--- /dev/null
+++ b/io_uring/Kconfig
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# io_uring configuration
+#
+
+config IO_URING_ZCRX
+ def_bool y
+ depends on PAGE_POOL
+ depends on INET
+ depends on NET_RX_BUSY_POLL
diff --git a/io_uring/Makefile b/io_uring/Makefile
index d695b60dba4f..3e28a741ca15 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -11,9 +11,11 @@ obj-$(CONFIG_IO_URING) += io_uring.o opdef.o kbuf.o rsrc.o notif.o \
eventfd.o uring_cmd.o openclose.o \
sqpoll.o xattr.o nop.o fs.o splice.o \
sync.o msg_ring.o advise.o openclose.o \
- epoll.o statx.o timeout.o fdinfo.o \
- cancel.o waitid.o register.o \
- truncate.o memmap.o alloc_cache.o
+ statx.o timeout.o fdinfo.o cancel.o \
+ waitid.o register.o truncate.o \
+ memmap.o alloc_cache.o
+obj-$(CONFIG_IO_URING_ZCRX) += zcrx.o
obj-$(CONFIG_IO_WQ) += io-wq.o
obj-$(CONFIG_FUTEX) += futex.o
-obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
+obj-$(CONFIG_EPOLL) += epoll.o
+obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
index 0dd17d8ba93a..d33ce159ef33 100644
--- a/io_uring/alloc_cache.h
+++ b/io_uring/alloc_cache.h
@@ -16,15 +16,6 @@ bool io_alloc_cache_init(struct io_alloc_cache *cache,
void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp);
-static inline void io_alloc_cache_kasan(struct iovec **iov, int *nr)
-{
- if (IS_ENABLED(CONFIG_KASAN)) {
- kfree(*iov);
- *iov = NULL;
- *nr = 0;
- }
-}
-
static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
void *entry)
{
@@ -68,4 +59,10 @@ static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp)
return io_cache_alloc_new(cache, gfp);
}
+static inline void io_cache_free(struct io_alloc_cache *cache, void *obj)
+{
+ if (!io_alloc_cache_put(cache, obj))
+ kfree(obj);
+}
+
#endif
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 484193567839..0870060bac7c 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -341,3 +341,45 @@ out:
fput(file);
return ret;
}
+
+bool io_cancel_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+ struct hlist_head *list, bool cancel_all,
+ bool (*cancel)(struct io_kiocb *))
+{
+ struct hlist_node *tmp;
+ struct io_kiocb *req;
+ bool found = false;
+
+ lockdep_assert_held(&ctx->uring_lock);
+
+ hlist_for_each_entry_safe(req, tmp, list, hash_node) {
+ if (!io_match_task_safe(req, tctx, cancel_all))
+ continue;
+ hlist_del_init(&req->hash_node);
+ if (cancel(req))
+ found = true;
+ }
+
+ return found;
+}
+
+int io_cancel_remove(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+ unsigned int issue_flags, struct hlist_head *list,
+ bool (*cancel)(struct io_kiocb *))
+{
+ struct hlist_node *tmp;
+ struct io_kiocb *req;
+ int nr = 0;
+
+ io_ring_submit_lock(ctx, issue_flags);
+ hlist_for_each_entry_safe(req, tmp, list, hash_node) {
+ if (!io_cancel_req_match(req, cd))
+ continue;
+ if (cancel(req))
+ nr++;
+ if (!(cd->flags & IORING_ASYNC_CANCEL_ALL))
+ break;
+ }
+ io_ring_submit_unlock(ctx, issue_flags);
+ return nr ?: -ENOENT;
+}
diff --git a/io_uring/cancel.h b/io_uring/cancel.h
index bbfea2cd00ea..43e9bb74e9d1 100644
--- a/io_uring/cancel.h
+++ b/io_uring/cancel.h
@@ -24,6 +24,14 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,
int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg);
bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd);
+bool io_cancel_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+ struct hlist_head *list, bool cancel_all,
+ bool (*cancel)(struct io_kiocb *));
+
+int io_cancel_remove(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+ unsigned int issue_flags, struct hlist_head *list,
+ bool (*cancel)(struct io_kiocb *));
+
static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence)
{
if (req->cancel_seq_set && sequence == req->work.cancel_seq)
diff --git a/io_uring/epoll.c b/io_uring/epoll.c
index 89bff2068a19..6d2c48ba1923 100644
--- a/io_uring/epoll.c
+++ b/io_uring/epoll.c
@@ -12,7 +12,6 @@
#include "io_uring.h"
#include "epoll.h"
-#if defined(CONFIG_EPOLL)
struct io_epoll {
struct file *file;
int epfd;
@@ -21,6 +20,12 @@ struct io_epoll {
struct epoll_event event;
};
+struct io_epoll_wait {
+ struct file *file;
+ int maxevents;
+ struct epoll_event __user *events;
+};
+
int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll);
@@ -58,4 +63,30 @@ int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
io_req_set_res(req, ret, 0);
return IOU_OK;
}
-#endif
+
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+ if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+ return -EINVAL;
+
+ iew->maxevents = READ_ONCE(sqe->len);
+ iew->events = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ return 0;
+}
+
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+ int ret;
+
+ ret = epoll_sendevents(req->file, iew->events, iew->maxevents);
+ if (ret == 0)
+ return -EAGAIN;
+ if (ret < 0)
+ req_set_fail(req);
+
+ io_req_set_res(req, ret, 0);
+ return IOU_OK;
+}
diff --git a/io_uring/epoll.h b/io_uring/epoll.h
index 870cce11ba98..4111997c360b 100644
--- a/io_uring/epoll.h
+++ b/io_uring/epoll.h
@@ -3,4 +3,6 @@
#if defined(CONFIG_EPOLL)
int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags);
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags);
#endif
diff --git a/io_uring/filetable.c b/io_uring/filetable.c
index dd8eeec97acf..a21660e3145a 100644
--- a/io_uring/filetable.c
+++ b/io_uring/filetable.c
@@ -68,7 +68,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
if (slot_index >= ctx->file_table.data.nr)
return -EINVAL;
- node = io_rsrc_node_alloc(IORING_RSRC_FILE);
+ node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
if (!node)
return -ENOMEM;
diff --git a/io_uring/futex.c b/io_uring/futex.c
index 43e2143255f5..0ea4820cd8ff 100644
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -44,30 +44,28 @@ void io_futex_cache_free(struct io_ring_ctx *ctx)
io_alloc_cache_free(&ctx->futex_cache, kfree);
}
-static void __io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts)
+static void __io_futex_complete(struct io_kiocb *req, io_tw_token_t tw)
{
req->async_data = NULL;
hlist_del_init(&req->hash_node);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
}
-static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_futex_complete(struct io_kiocb *req, io_tw_token_t tw)
{
- struct io_futex_data *ifd = req->async_data;
struct io_ring_ctx *ctx = req->ctx;
- io_tw_lock(ctx, ts);
- if (!io_alloc_cache_put(&ctx->futex_cache, ifd))
- kfree(ifd);
- __io_futex_complete(req, ts);
+ io_tw_lock(ctx, tw);
+ io_cache_free(&ctx->futex_cache, req->async_data);
+ __io_futex_complete(req, tw);
}
-static void io_futexv_complete(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_futexv_complete(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
struct futex_vector *futexv = req->async_data;
- io_tw_lock(req->ctx, ts);
+ io_tw_lock(req->ctx, tw);
if (!iof->futexv_unqueued) {
int res;
@@ -79,7 +77,7 @@ static void io_futexv_complete(struct io_kiocb *req, struct io_tw_state *ts)
kfree(req->async_data);
req->flags &= ~REQ_F_ASYNC_DATA;
- __io_futex_complete(req, ts);
+ __io_futex_complete(req, tw);
}
static bool io_futexv_claim(struct io_futex *iof)
@@ -90,7 +88,7 @@ static bool io_futexv_claim(struct io_futex *iof)
return true;
}
-static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
+static bool __io_futex_cancel(struct io_kiocb *req)
{
/* futex wake already done or in progress */
if (req->opcode == IORING_OP_FUTEX_WAIT) {
@@ -116,49 +114,13 @@ static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
unsigned int issue_flags)
{
- struct hlist_node *tmp;
- struct io_kiocb *req;
- int nr = 0;
-
- if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED))
- return -ENOENT;
-
- io_ring_submit_lock(ctx, issue_flags);
- hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) {
- if (req->cqe.user_data != cd->data &&
- !(cd->flags & IORING_ASYNC_CANCEL_ANY))
- continue;
- if (__io_futex_cancel(ctx, req))
- nr++;
- if (!(cd->flags & IORING_ASYNC_CANCEL_ALL))
- break;
- }
- io_ring_submit_unlock(ctx, issue_flags);
-
- if (nr)
- return nr;
-
- return -ENOENT;
+ return io_cancel_remove(ctx, cd, issue_flags, &ctx->futex_list, __io_futex_cancel);
}
bool io_futex_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
bool cancel_all)
{
- struct hlist_node *tmp;
- struct io_kiocb *req;
- bool found = false;
-
- lockdep_assert_held(&ctx->uring_lock);
-
- hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) {
- if (!io_match_task_safe(req, tctx, cancel_all))
- continue;
- hlist_del_init(&req->hash_node);
- __io_futex_cancel(ctx, req);
- found = true;
- }
-
- return found;
+ return io_cancel_remove_all(ctx, tctx, &ctx->futex_list, cancel_all, __io_futex_cancel);
}
int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 91019b4d0308..04a75d666195 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -30,7 +30,6 @@ enum {
IO_WORKER_F_UP = 0, /* up and active */
IO_WORKER_F_RUNNING = 1, /* account as running */
IO_WORKER_F_FREE = 2, /* worker on free list */
- IO_WORKER_F_BOUND = 3, /* is doing bounded work */
};
enum {
@@ -46,12 +45,12 @@ enum {
*/
struct io_worker {
refcount_t ref;
- int create_index;
unsigned long flags;
struct hlist_nulls_node nulls_node;
struct list_head all_list;
struct task_struct *task;
struct io_wq *wq;
+ struct io_wq_acct *acct;
struct io_wq_work *cur_work;
raw_spinlock_t lock;
@@ -77,10 +76,27 @@ struct io_worker {
#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER)
struct io_wq_acct {
+ /**
+ * Protects access to the worker lists.
+ */
+ raw_spinlock_t workers_lock;
+
unsigned nr_workers;
unsigned max_workers;
- int index;
atomic_t nr_running;
+
+ /**
+ * The list of free workers. Protected by #workers_lock
+ * (write) and RCU (read).
+ */
+ struct hlist_nulls_head free_list;
+
+ /**
+ * The list of all workers. Protected by #workers_lock
+ * (write) and RCU (read).
+ */
+ struct list_head all_list;
+
raw_spinlock_t lock;
struct io_wq_work_list work_list;
unsigned long flags;
@@ -112,12 +128,6 @@ struct io_wq {
struct io_wq_acct acct[IO_WQ_ACCT_NR];
- /* lock protects access to elements below */
- raw_spinlock_t lock;
-
- struct hlist_nulls_head free_list;
- struct list_head all_list;
-
struct wait_queue_entry wait;
struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS];
@@ -135,7 +145,7 @@ struct io_cb_cancel_data {
bool cancel_all;
};
-static bool create_io_worker(struct io_wq *wq, int index);
+static bool create_io_worker(struct io_wq *wq, struct io_wq_acct *acct);
static void io_wq_dec_running(struct io_worker *worker);
static bool io_acct_cancel_pending_work(struct io_wq *wq,
struct io_wq_acct *acct,
@@ -160,14 +170,14 @@ static inline struct io_wq_acct *io_get_acct(struct io_wq *wq, bool bound)
}
static inline struct io_wq_acct *io_work_get_acct(struct io_wq *wq,
- struct io_wq_work *work)
+ unsigned int work_flags)
{
- return io_get_acct(wq, !(atomic_read(&work->flags) & IO_WQ_WORK_UNBOUND));
+ return io_get_acct(wq, !(work_flags & IO_WQ_WORK_UNBOUND));
}
static inline struct io_wq_acct *io_wq_get_acct(struct io_worker *worker)
{
- return io_get_acct(worker->wq, test_bit(IO_WORKER_F_BOUND, &worker->flags));
+ return worker->acct;
}
static void io_worker_ref_put(struct io_wq *wq)
@@ -192,9 +202,9 @@ static void io_worker_cancel_cb(struct io_worker *worker)
struct io_wq *wq = worker->wq;
atomic_dec(&acct->nr_running);
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
acct->nr_workers--;
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
io_worker_ref_put(wq);
clear_bit_unlock(0, &worker->create_state);
io_worker_release(worker);
@@ -213,6 +223,7 @@ static bool io_task_worker_match(struct callback_head *cb, void *data)
static void io_worker_exit(struct io_worker *worker)
{
struct io_wq *wq = worker->wq;
+ struct io_wq_acct *acct = io_wq_get_acct(worker);
while (1) {
struct callback_head *cb = task_work_cancel_match(wq->task,
@@ -226,11 +237,11 @@ static void io_worker_exit(struct io_worker *worker)
io_worker_release(worker);
wait_for_completion(&worker->ref_done);
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
if (test_bit(IO_WORKER_F_FREE, &worker->flags))
hlist_nulls_del_rcu(&worker->nulls_node);
list_del_rcu(&worker->all_list);
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
io_wq_dec_running(worker);
/*
* this worker is a goner, clear ->worker_private to avoid any
@@ -269,8 +280,7 @@ static inline bool io_acct_run_queue(struct io_wq_acct *acct)
* Check head of free list for an available worker. If one isn't available,
* caller must create one.
*/
-static bool io_wq_activate_free_worker(struct io_wq *wq,
- struct io_wq_acct *acct)
+static bool io_acct_activate_free_worker(struct io_wq_acct *acct)
__must_hold(RCU)
{
struct hlist_nulls_node *n;
@@ -281,13 +291,9 @@ static bool io_wq_activate_free_worker(struct io_wq *wq,
* activate. If a given worker is on the free_list but in the process
* of exiting, keep trying.
*/
- hlist_nulls_for_each_entry_rcu(worker, n, &wq->free_list, nulls_node) {
+ hlist_nulls_for_each_entry_rcu(worker, n, &acct->free_list, nulls_node) {
if (!io_worker_get(worker))
continue;
- if (io_wq_get_acct(worker) != acct) {
- io_worker_release(worker);
- continue;
- }
/*
* If the worker is already running, it's either already
* starting work or finishing work. In either case, if it does
@@ -314,16 +320,16 @@ static bool io_wq_create_worker(struct io_wq *wq, struct io_wq_acct *acct)
if (unlikely(!acct->max_workers))
pr_warn_once("io-wq is not configured for unbound workers");
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
if (acct->nr_workers >= acct->max_workers) {
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
return true;
}
acct->nr_workers++;
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
atomic_inc(&acct->nr_running);
atomic_inc(&wq->worker_refs);
- return create_io_worker(wq, acct->index);
+ return create_io_worker(wq, acct);
}
static void io_wq_inc_running(struct io_worker *worker)
@@ -343,16 +349,16 @@ static void create_worker_cb(struct callback_head *cb)
worker = container_of(cb, struct io_worker, create_work);
wq = worker->wq;
- acct = &wq->acct[worker->create_index];
- raw_spin_lock(&wq->lock);
+ acct = worker->acct;
+ raw_spin_lock(&acct->workers_lock);
if (acct->nr_workers < acct->max_workers) {
acct->nr_workers++;
do_create = true;
}
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
if (do_create) {
- create_io_worker(wq, worker->create_index);
+ create_io_worker(wq, acct);
} else {
atomic_dec(&acct->nr_running);
io_worker_ref_put(wq);
@@ -384,7 +390,6 @@ static bool io_queue_worker_create(struct io_worker *worker,
atomic_inc(&wq->worker_refs);
init_task_work(&worker->create_work, func);
- worker->create_index = acct->index;
if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
/*
* EXIT may have been set after checking it above, check after
@@ -430,31 +435,36 @@ static void io_wq_dec_running(struct io_worker *worker)
* Worker will start processing some work. Move it to the busy list, if
* it's currently on the freelist
*/
-static void __io_worker_busy(struct io_wq *wq, struct io_worker *worker)
+static void __io_worker_busy(struct io_wq_acct *acct, struct io_worker *worker)
{
if (test_bit(IO_WORKER_F_FREE, &worker->flags)) {
clear_bit(IO_WORKER_F_FREE, &worker->flags);
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
hlist_nulls_del_init_rcu(&worker->nulls_node);
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
}
}
/*
* No work, worker going to sleep. Move to freelist.
*/
-static void __io_worker_idle(struct io_wq *wq, struct io_worker *worker)
- __must_hold(wq->lock)
+static void __io_worker_idle(struct io_wq_acct *acct, struct io_worker *worker)
+ __must_hold(acct->workers_lock)
{
if (!test_bit(IO_WORKER_F_FREE, &worker->flags)) {
set_bit(IO_WORKER_F_FREE, &worker->flags);
- hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list);
+ hlist_nulls_add_head_rcu(&worker->nulls_node, &acct->free_list);
}
}
+static inline unsigned int __io_get_work_hash(unsigned int work_flags)
+{
+ return work_flags >> IO_WQ_HASH_SHIFT;
+}
+
static inline unsigned int io_get_work_hash(struct io_wq_work *work)
{
- return atomic_read(&work->flags) >> IO_WQ_HASH_SHIFT;
+ return __io_get_work_hash(atomic_read(&work->flags));
}
static bool io_wait_on_hash(struct io_wq *wq, unsigned int hash)
@@ -475,26 +485,27 @@ static bool io_wait_on_hash(struct io_wq *wq, unsigned int hash)
}
static struct io_wq_work *io_get_next_work(struct io_wq_acct *acct,
- struct io_worker *worker)
+ struct io_wq *wq)
__must_hold(acct->lock)
{
struct io_wq_work_node *node, *prev;
struct io_wq_work *work, *tail;
unsigned int stall_hash = -1U;
- struct io_wq *wq = worker->wq;
wq_list_for_each(node, prev, &acct->work_list) {
+ unsigned int work_flags;
unsigned int hash;
work = container_of(node, struct io_wq_work, list);
/* not hashed, can run anytime */
- if (!io_wq_is_hashed(work)) {
+ work_flags = atomic_read(&work->flags);
+ if (!__io_wq_is_hashed(work_flags)) {
wq_list_del(&acct->work_list, node, prev);
return work;
}
- hash = io_get_work_hash(work);
+ hash = __io_get_work_hash(work_flags);
/* all items with this hash lie in [work, tail] */
tail = wq->hash_tail[hash];
@@ -564,7 +575,7 @@ static void io_worker_handle_work(struct io_wq_acct *acct,
* can't make progress, any work completion or insertion will
* clear the stalled flag.
*/
- work = io_get_next_work(acct, worker);
+ work = io_get_next_work(acct, wq);
if (work) {
/*
* Make sure cancelation can find this, even before
@@ -583,7 +594,7 @@ static void io_worker_handle_work(struct io_wq_acct *acct,
if (!work)
break;
- __io_worker_busy(wq, worker);
+ __io_worker_busy(acct, worker);
io_assign_current_work(worker, work);
__set_current_state(TASK_RUNNING);
@@ -591,12 +602,15 @@ static void io_worker_handle_work(struct io_wq_acct *acct,
/* handle a whole dependent link */
do {
struct io_wq_work *next_hashed, *linked;
- unsigned int hash = io_get_work_hash(work);
+ unsigned int work_flags = atomic_read(&work->flags);
+ unsigned int hash = __io_wq_is_hashed(work_flags)
+ ? __io_get_work_hash(work_flags)
+ : -1U;
next_hashed = wq_next_work(work);
if (do_kill &&
- (atomic_read(&work->flags) & IO_WQ_WORK_UNBOUND))
+ (work_flags & IO_WQ_WORK_UNBOUND))
atomic_or(IO_WQ_WORK_CANCEL, &work->flags);
wq->do_work(work);
io_assign_current_work(worker, NULL);
@@ -654,20 +668,20 @@ static int io_wq_worker(void *data)
while (io_acct_run_queue(acct))
io_worker_handle_work(acct, worker);
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
/*
* Last sleep timed out. Exit if we're not the last worker,
* or if someone modified our affinity.
*/
if (last_timeout && (exit_mask || acct->nr_workers > 1)) {
acct->nr_workers--;
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
__set_current_state(TASK_RUNNING);
break;
}
last_timeout = false;
- __io_worker_idle(wq, worker);
- raw_spin_unlock(&wq->lock);
+ __io_worker_idle(acct, worker);
+ raw_spin_unlock(&acct->workers_lock);
if (io_run_task_work())
continue;
ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
@@ -728,18 +742,18 @@ void io_wq_worker_sleeping(struct task_struct *tsk)
io_wq_dec_running(worker);
}
-static void io_init_new_worker(struct io_wq *wq, struct io_worker *worker,
+static void io_init_new_worker(struct io_wq *wq, struct io_wq_acct *acct, struct io_worker *worker,
struct task_struct *tsk)
{
tsk->worker_private = worker;
worker->task = tsk;
set_cpus_allowed_ptr(tsk, wq->cpu_mask);
- raw_spin_lock(&wq->lock);
- hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list);
- list_add_tail_rcu(&worker->all_list, &wq->all_list);
+ raw_spin_lock(&acct->workers_lock);
+ hlist_nulls_add_head_rcu(&worker->nulls_node, &acct->free_list);
+ list_add_tail_rcu(&worker->all_list, &acct->all_list);
set_bit(IO_WORKER_F_FREE, &worker->flags);
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
wake_up_new_task(tsk);
}
@@ -787,20 +801,20 @@ static void create_worker_cont(struct callback_head *cb)
struct io_worker *worker;
struct task_struct *tsk;
struct io_wq *wq;
+ struct io_wq_acct *acct;
worker = container_of(cb, struct io_worker, create_work);
clear_bit_unlock(0, &worker->create_state);
wq = worker->wq;
+ acct = io_wq_get_acct(worker);
tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE);
if (!IS_ERR(tsk)) {
- io_init_new_worker(wq, worker, tsk);
+ io_init_new_worker(wq, acct, worker, tsk);
io_worker_release(worker);
return;
} else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) {
- struct io_wq_acct *acct = io_wq_get_acct(worker);
-
atomic_dec(&acct->nr_running);
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
acct->nr_workers--;
if (!acct->nr_workers) {
struct io_cb_cancel_data match = {
@@ -808,11 +822,11 @@ static void create_worker_cont(struct callback_head *cb)
.cancel_all = true,
};
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
while (io_acct_cancel_pending_work(wq, acct, &match))
;
} else {
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
}
io_worker_ref_put(wq);
kfree(worker);
@@ -834,9 +848,8 @@ static void io_workqueue_create(struct work_struct *work)
kfree(worker);
}
-static bool create_io_worker(struct io_wq *wq, int index)
+static bool create_io_worker(struct io_wq *wq, struct io_wq_acct *acct)
{
- struct io_wq_acct *acct = &wq->acct[index];
struct io_worker *worker;
struct task_struct *tsk;
@@ -846,24 +859,22 @@ static bool create_io_worker(struct io_wq *wq, int index)
if (!worker) {
fail:
atomic_dec(&acct->nr_running);
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
acct->nr_workers--;
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
io_worker_ref_put(wq);
return false;
}
refcount_set(&worker->ref, 1);
worker->wq = wq;
+ worker->acct = acct;
raw_spin_lock_init(&worker->lock);
init_completion(&worker->ref_done);
- if (index == IO_WQ_ACCT_BOUND)
- set_bit(IO_WORKER_F_BOUND, &worker->flags);
-
tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE);
if (!IS_ERR(tsk)) {
- io_init_new_worker(wq, worker, tsk);
+ io_init_new_worker(wq, acct, worker, tsk);
} else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) {
kfree(worker);
goto fail;
@@ -879,14 +890,14 @@ fail:
* Iterate the passed in list and call the specific function for each
* worker that isn't exiting
*/
-static bool io_wq_for_each_worker(struct io_wq *wq,
- bool (*func)(struct io_worker *, void *),
- void *data)
+static bool io_acct_for_each_worker(struct io_wq_acct *acct,
+ bool (*func)(struct io_worker *, void *),
+ void *data)
{
struct io_worker *worker;
bool ret = false;
- list_for_each_entry_rcu(worker, &wq->all_list, all_list) {
+ list_for_each_entry_rcu(worker, &acct->all_list, all_list) {
if (io_worker_get(worker)) {
/* no task if node is/was offline */
if (worker->task)
@@ -900,6 +911,18 @@ static bool io_wq_for_each_worker(struct io_wq *wq,
return ret;
}
+static bool io_wq_for_each_worker(struct io_wq *wq,
+ bool (*func)(struct io_worker *, void *),
+ void *data)
+{
+ for (int i = 0; i < IO_WQ_ACCT_NR; i++) {
+ if (!io_acct_for_each_worker(&wq->acct[i], func, data))
+ return false;
+ }
+
+ return true;
+}
+
static bool io_wq_worker_wake(struct io_worker *worker, void *data)
{
__set_notify_signal(worker->task);
@@ -916,19 +939,19 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq)
} while (work);
}
-static void io_wq_insert_work(struct io_wq *wq, struct io_wq_work *work)
+static void io_wq_insert_work(struct io_wq *wq, struct io_wq_acct *acct,
+ struct io_wq_work *work, unsigned int work_flags)
{
- struct io_wq_acct *acct = io_work_get_acct(wq, work);
unsigned int hash;
struct io_wq_work *tail;
- if (!io_wq_is_hashed(work)) {
+ if (!__io_wq_is_hashed(work_flags)) {
append:
wq_list_add_tail(&work->list, &acct->work_list);
return;
}
- hash = io_get_work_hash(work);
+ hash = __io_get_work_hash(work_flags);
tail = wq->hash_tail[hash];
wq->hash_tail[hash] = work;
if (!tail)
@@ -944,8 +967,8 @@ static bool io_wq_work_match_item(struct io_wq_work *work, void *data)
void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
{
- struct io_wq_acct *acct = io_work_get_acct(wq, work);
unsigned int work_flags = atomic_read(&work->flags);
+ struct io_wq_acct *acct = io_work_get_acct(wq, work_flags);
struct io_cb_cancel_data match = {
.fn = io_wq_work_match_item,
.data = work,
@@ -964,12 +987,12 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
}
raw_spin_lock(&acct->lock);
- io_wq_insert_work(wq, work);
+ io_wq_insert_work(wq, acct, work, work_flags);
clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
raw_spin_unlock(&acct->lock);
rcu_read_lock();
- do_create = !io_wq_activate_free_worker(wq, acct);
+ do_create = !io_acct_activate_free_worker(acct);
rcu_read_unlock();
if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) ||
@@ -980,12 +1003,12 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
if (likely(did_create))
return;
- raw_spin_lock(&wq->lock);
+ raw_spin_lock(&acct->workers_lock);
if (acct->nr_workers) {
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
return;
}
- raw_spin_unlock(&wq->lock);
+ raw_spin_unlock(&acct->workers_lock);
/* fatal condition, failed to create the first worker */
io_acct_cancel_pending_work(wq, acct, &match);
@@ -1034,10 +1057,10 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
}
static inline void io_wq_remove_pending(struct io_wq *wq,
+ struct io_wq_acct *acct,
struct io_wq_work *work,
struct io_wq_work_node *prev)
{
- struct io_wq_acct *acct = io_work_get_acct(wq, work);
unsigned int hash = io_get_work_hash(work);
struct io_wq_work *prev_work = NULL;
@@ -1064,7 +1087,7 @@ static bool io_acct_cancel_pending_work(struct io_wq *wq,
work = container_of(node, struct io_wq_work, list);
if (!match->fn(work, match->data))
continue;
- io_wq_remove_pending(wq, work, prev);
+ io_wq_remove_pending(wq, acct, work, prev);
raw_spin_unlock(&acct->lock);
io_run_cancel(work, wq);
match->nr_pending++;
@@ -1092,11 +1115,22 @@ retry:
}
}
+static void io_acct_cancel_running_work(struct io_wq_acct *acct,
+ struct io_cb_cancel_data *match)
+{
+ raw_spin_lock(&acct->workers_lock);
+ io_acct_for_each_worker(acct, io_wq_worker_cancel, match);
+ raw_spin_unlock(&acct->workers_lock);
+}
+
static void io_wq_cancel_running_work(struct io_wq *wq,
struct io_cb_cancel_data *match)
{
rcu_read_lock();
- io_wq_for_each_worker(wq, io_wq_worker_cancel, match);
+
+ for (int i = 0; i < IO_WQ_ACCT_NR; i++)
+ io_acct_cancel_running_work(&wq->acct[i], match);
+
rcu_read_unlock();
}
@@ -1119,16 +1153,14 @@ enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
* as an indication that we attempt to signal cancellation. The
* completion will run normally in this case.
*
- * Do both of these while holding the wq->lock, to ensure that
+ * Do both of these while holding the acct->workers_lock, to ensure that
* we'll find a work item regardless of state.
*/
io_wq_cancel_pending_work(wq, &match);
if (match.nr_pending && !match.cancel_all)
return IO_WQ_CANCEL_OK;
- raw_spin_lock(&wq->lock);
io_wq_cancel_running_work(wq, &match);
- raw_spin_unlock(&wq->lock);
if (match.nr_running && !match.cancel_all)
return IO_WQ_CANCEL_RUNNING;
@@ -1152,7 +1184,7 @@ static int io_wq_hash_wake(struct wait_queue_entry *wait, unsigned mode,
struct io_wq_acct *acct = &wq->acct[i];
if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags))
- io_wq_activate_free_worker(wq, acct);
+ io_acct_activate_free_worker(acct);
}
rcu_read_unlock();
return 1;
@@ -1190,16 +1222,16 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
for (i = 0; i < IO_WQ_ACCT_NR; i++) {
struct io_wq_acct *acct = &wq->acct[i];
- acct->index = i;
atomic_set(&acct->nr_running, 0);
+
+ raw_spin_lock_init(&acct->workers_lock);
+ INIT_HLIST_NULLS_HEAD(&acct->free_list, 0);
+ INIT_LIST_HEAD(&acct->all_list);
+
INIT_WQ_LIST(&acct->work_list);
raw_spin_lock_init(&acct->lock);
}
- raw_spin_lock_init(&wq->lock);
- INIT_HLIST_NULLS_HEAD(&wq->free_list, 0);
- INIT_LIST_HEAD(&wq->all_list);
-
wq->task = get_task_struct(data->task);
atomic_set(&wq->worker_refs, 1);
init_completion(&wq->worker_done);
@@ -1385,14 +1417,14 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count)
rcu_read_lock();
- raw_spin_lock(&wq->lock);
for (i = 0; i < IO_WQ_ACCT_NR; i++) {
acct = &wq->acct[i];
+ raw_spin_lock(&acct->workers_lock);
prev[i] = max_t(int, acct->max_workers, prev[i]);
if (new_count[i])
acct->max_workers = new_count[i];
+ raw_spin_unlock(&acct->workers_lock);
}
- raw_spin_unlock(&wq->lock);
rcu_read_unlock();
for (i = 0; i < IO_WQ_ACCT_NR; i++)
diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h
index b3b004a7b625..d4fb2940e435 100644
--- a/io_uring/io-wq.h
+++ b/io_uring/io-wq.h
@@ -54,9 +54,14 @@ int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask);
int io_wq_max_workers(struct io_wq *wq, int *new_count);
bool io_wq_worker_stopped(void);
+static inline bool __io_wq_is_hashed(unsigned int work_flags)
+{
+ return work_flags & IO_WQ_WORK_HASHED;
+}
+
static inline bool io_wq_is_hashed(struct io_wq_work *work)
{
- return atomic_read(&work->flags) & IO_WQ_WORK_HASHED;
+ return __io_wq_is_hashed(atomic_read(&work->flags));
}
typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index f7acae5f7e1d..3ba49c628337 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -97,6 +97,7 @@
#include "uring_cmd.h"
#include "msg_ring.h"
#include "memmap.h"
+#include "zcrx.h"
#include "timeout.h"
#include "poll.h"
@@ -110,11 +111,13 @@
#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
+#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
+
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
REQ_F_ASYNC_DATA)
-#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
+#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | IO_REQ_LINK_FLAGS | \
REQ_F_REISSUE | IO_REQ_CLEAN_FLAGS)
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
@@ -131,7 +134,6 @@ struct io_defer_entry {
/* requests with any of those set should undergo io_disarm_next() */
#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
-#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
/*
* No waiters. It's larger than any valid value of the tw counter
@@ -254,7 +256,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
percpu_ref_get(&ctx->refs);
mutex_lock(&ctx->uring_lock);
llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
- req->io_task_work.func(req, &ts);
+ req->io_task_work.func(req, ts);
io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
percpu_ref_put(&ctx->refs);
@@ -282,6 +284,17 @@ static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
return 0;
}
+static void io_free_alloc_caches(struct io_ring_ctx *ctx)
+{
+ io_alloc_cache_free(&ctx->apoll_cache, kfree);
+ io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
+ io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free);
+ io_alloc_cache_free(&ctx->cmd_cache, io_cmd_cache_free);
+ io_alloc_cache_free(&ctx->msg_cache, kfree);
+ io_futex_cache_free(ctx);
+ io_rsrc_cache_free(ctx);
+}
+
static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
@@ -313,7 +326,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
init_waitqueue_head(&ctx->sqo_sq_wait);
INIT_LIST_HEAD(&ctx->sqd_list);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
- INIT_LIST_HEAD(&ctx->io_buffers_cache);
ret = io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX,
sizeof(struct async_poll), 0);
ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX,
@@ -322,12 +334,14 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct io_async_rw),
offsetof(struct io_async_rw, clear));
- ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX,
- sizeof(struct io_uring_cmd_data), 0);
+ ret |= io_alloc_cache_init(&ctx->cmd_cache, IO_ALLOC_CACHE_MAX,
+ sizeof(struct io_async_cmd),
+ sizeof(struct io_async_cmd));
spin_lock_init(&ctx->msg_lock);
ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct io_kiocb), 0);
ret |= io_futex_cache_init(ctx);
+ ret |= io_rsrc_cache_init(ctx);
if (ret)
goto free_ref;
init_completion(&ctx->ref_comp);
@@ -338,7 +352,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
spin_lock_init(&ctx->completion_lock);
raw_spin_lock_init(&ctx->timeout_lock);
INIT_WQ_LIST(&ctx->iopoll_list);
- INIT_LIST_HEAD(&ctx->io_buffers_comp);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
INIT_LIST_HEAD(&ctx->ltimeout_list);
@@ -360,12 +373,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
free_ref:
percpu_ref_exit(&ctx->refs);
err:
- io_alloc_cache_free(&ctx->apoll_cache, kfree);
- io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
- io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free);
- io_alloc_cache_free(&ctx->uring_cache, kfree);
- io_alloc_cache_free(&ctx->msg_cache, kfree);
- io_futex_cache_free(ctx);
+ io_free_alloc_caches(ctx);
kvfree(ctx->cancel_table.hbs);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
@@ -393,11 +401,8 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
static void io_clean_op(struct io_kiocb *req)
{
- if (req->flags & REQ_F_BUFFER_SELECTED) {
- spin_lock(&req->ctx->completion_lock);
- io_kbuf_drop(req);
- spin_unlock(&req->ctx->completion_lock);
- }
+ if (unlikely(req->flags & REQ_F_BUFFER_SELECTED))
+ io_kbuf_drop_legacy(req);
if (req->flags & REQ_F_NEED_CLEANUP) {
const struct io_cold_def *def = &io_cold_defs[req->opcode];
@@ -542,7 +547,7 @@ static void io_queue_iowq(struct io_kiocb *req)
io_queue_linked_timeout(link);
}
-static void io_req_queue_iowq_tw(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_req_queue_iowq_tw(struct io_kiocb *req, io_tw_token_t tw)
{
io_queue_iowq(req);
}
@@ -829,24 +834,14 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
return false;
}
-static bool __io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res,
- u32 cflags)
+bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
{
bool filled;
+ io_cq_lock(ctx);
filled = io_fill_cqe_aux(ctx, user_data, res, cflags);
if (!filled)
filled = io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
-
- return filled;
-}
-
-bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
-{
- bool filled;
-
- io_cq_lock(ctx);
- filled = __io_post_aux_cqe(ctx, user_data, res, cflags);
io_cq_unlock_post(ctx);
return filled;
}
@@ -887,6 +882,7 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
static void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
+ bool completed = true;
/*
* All execution paths but io-wq use the deferred completions by
@@ -899,19 +895,21 @@ static void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
* Handle special CQ sync cases via task_work. DEFER_TASKRUN requires
* the submitter task context, IOPOLL protects with uring_lock.
*/
- if (ctx->task_complete || (ctx->flags & IORING_SETUP_IOPOLL)) {
+ if (ctx->lockless_cq || (req->flags & REQ_F_REISSUE)) {
+defer_complete:
req->io_task_work.func = io_req_task_complete;
io_req_task_work_add(req);
return;
}
io_cq_lock(ctx);
- if (!(req->flags & REQ_F_CQE_SKIP)) {
- if (!io_fill_cqe_req(ctx, req))
- io_req_cqe_overflow(req);
- }
+ if (!(req->flags & REQ_F_CQE_SKIP))
+ completed = io_fill_cqe_req(ctx, req);
io_cq_unlock_post(ctx);
+ if (!completed)
+ goto defer_complete;
+
/*
* We don't free the request here because we know it's called from
* io-wq only, which holds a reference, so it cannot be the last put.
@@ -1021,7 +1019,7 @@ static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
return nxt;
}
-static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts)
+static void ctx_flush_and_put(struct io_ring_ctx *ctx, io_tw_token_t tw)
{
if (!ctx)
return;
@@ -1051,24 +1049,24 @@ struct llist_node *io_handle_tw_list(struct llist_node *node,
io_task_work.node);
if (req->ctx != ctx) {
- ctx_flush_and_put(ctx, &ts);
+ ctx_flush_and_put(ctx, ts);
ctx = req->ctx;
mutex_lock(&ctx->uring_lock);
percpu_ref_get(&ctx->refs);
}
INDIRECT_CALL_2(req->io_task_work.func,
io_poll_task_func, io_req_rw_complete,
- req, &ts);
+ req, ts);
node = next;
(*count)++;
if (unlikely(need_resched())) {
- ctx_flush_and_put(ctx, &ts);
+ ctx_flush_and_put(ctx, ts);
ctx = NULL;
cond_resched();
}
} while (node && *count < max_entries);
- ctx_flush_and_put(ctx, &ts);
+ ctx_flush_and_put(ctx, ts);
return node;
}
@@ -1157,7 +1155,7 @@ static inline void io_req_local_work_add(struct io_kiocb *req,
* We don't know how many reuqests is there in the link and whether
* they can even be queued lazily, fall back to non-lazy.
*/
- if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
+ if (req->flags & IO_REQ_LINK_FLAGS)
flags &= ~IOU_F_TWQ_LAZY_WAKE;
guard(rcu)();
@@ -1276,7 +1274,7 @@ static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events,
}
static int __io_run_local_work_loop(struct llist_node **node,
- struct io_tw_state *ts,
+ io_tw_token_t tw,
int events)
{
int ret = 0;
@@ -1287,7 +1285,7 @@ static int __io_run_local_work_loop(struct llist_node **node,
io_task_work.node);
INDIRECT_CALL_2(req->io_task_work.func,
io_poll_task_func, io_req_rw_complete,
- req, ts);
+ req, tw);
*node = next;
if (++ret >= events)
break;
@@ -1296,7 +1294,7 @@ static int __io_run_local_work_loop(struct llist_node **node,
return ret;
}
-static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
+static int __io_run_local_work(struct io_ring_ctx *ctx, io_tw_token_t tw,
int min_events, int max_events)
{
struct llist_node *node;
@@ -1309,7 +1307,7 @@ static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
again:
min_events -= ret;
- ret = __io_run_local_work_loop(&ctx->retry_llist.first, ts, max_events);
+ ret = __io_run_local_work_loop(&ctx->retry_llist.first, tw, max_events);
if (ctx->retry_llist.first)
goto retry_done;
@@ -1318,7 +1316,7 @@ again:
* running the pending items.
*/
node = llist_reverse_order(llist_del_all(&ctx->work_llist));
- ret += __io_run_local_work_loop(&node, ts, max_events - ret);
+ ret += __io_run_local_work_loop(&node, tw, max_events - ret);
ctx->retry_llist.first = node;
loops++;
@@ -1340,7 +1338,7 @@ static inline int io_run_local_work_locked(struct io_ring_ctx *ctx,
if (!io_local_work_pending(ctx))
return 0;
- return __io_run_local_work(ctx, &ts, min_events,
+ return __io_run_local_work(ctx, ts, min_events,
max(IO_LOCAL_TW_DEFAULT_MAX, min_events));
}
@@ -1351,20 +1349,20 @@ static int io_run_local_work(struct io_ring_ctx *ctx, int min_events,
int ret;
mutex_lock(&ctx->uring_lock);
- ret = __io_run_local_work(ctx, &ts, min_events, max_events);
+ ret = __io_run_local_work(ctx, ts, min_events, max_events);
mutex_unlock(&ctx->uring_lock);
return ret;
}
-static void io_req_task_cancel(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_req_task_cancel(struct io_kiocb *req, io_tw_token_t tw)
{
- io_tw_lock(req->ctx, ts);
+ io_tw_lock(req->ctx, tw);
io_req_defer_failed(req, req->cqe.res);
}
-void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts)
+void io_req_task_submit(struct io_kiocb *req, io_tw_token_t tw)
{
- io_tw_lock(req->ctx, ts);
+ io_tw_lock(req->ctx, tw);
if (unlikely(io_should_terminate_tw()))
io_req_defer_failed(req, -EFAULT);
else if (req->flags & REQ_F_FORCE_ASYNC)
@@ -1419,8 +1417,7 @@ static void io_free_batch_list(struct io_ring_ctx *ctx,
if (apoll->double_poll)
kfree(apoll->double_poll);
- if (!io_alloc_cache_put(&ctx->apoll_cache, apoll))
- kfree(apoll);
+ io_cache_free(&ctx->apoll_cache, apoll);
req->flags &= ~REQ_F_POLLED;
}
if (req->flags & IO_REQ_LINK_FLAGS)
@@ -1508,11 +1505,13 @@ static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
mutex_unlock(&ctx->uring_lock);
}
-static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned int min_events)
{
unsigned int nr_events = 0;
unsigned long check_cq;
+ min_events = min(min_events, ctx->cq_entries);
+
lockdep_assert_held(&ctx->uring_lock);
if (!io_allowed_run_tw(ctx))
@@ -1554,7 +1553,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
io_task_work_pending(ctx)) {
u32 tail = ctx->cached_cq_tail;
- (void) io_run_local_work_locked(ctx, min);
+ (void) io_run_local_work_locked(ctx, min_events);
if (task_work_pending(current) ||
wq_list_empty(&ctx->iopoll_list)) {
@@ -1567,7 +1566,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
wq_list_empty(&ctx->iopoll_list))
break;
}
- ret = io_do_iopoll(ctx, !min);
+ ret = io_do_iopoll(ctx, !min_events);
if (unlikely(ret < 0))
return ret;
@@ -1577,12 +1576,12 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
break;
nr_events += ret;
- } while (nr_events < min);
+ } while (nr_events < min_events);
return 0;
}
-void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts)
+void io_req_task_complete(struct io_kiocb *req, io_tw_token_t tw)
{
io_req_complete_defer(req);
}
@@ -1719,15 +1718,13 @@ static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def,
return !!req->file;
}
-static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
+static inline int __io_issue_sqe(struct io_kiocb *req,
+ unsigned int issue_flags,
+ const struct io_issue_def *def)
{
- const struct io_issue_def *def = &io_issue_defs[req->opcode];
const struct cred *creds = NULL;
int ret;
- if (unlikely(!io_assign_file(req, def, issue_flags)))
- return -EBADF;
-
if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
creds = override_creds(req->creds);
@@ -1742,6 +1739,19 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (creds)
revert_creds(creds);
+ return ret;
+}
+
+static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
+{
+ const struct io_issue_def *def = &io_issue_defs[req->opcode];
+ int ret;
+
+ if (unlikely(!io_assign_file(req, def, issue_flags)))
+ return -EBADF;
+
+ ret = __io_issue_sqe(req, issue_flags, def);
+
if (ret == IOU_OK) {
if (issue_flags & IO_URING_F_COMPLETE_DEFER)
io_req_complete_defer(req);
@@ -1762,11 +1772,23 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
return ret;
}
-int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts)
+int io_poll_issue(struct io_kiocb *req, io_tw_token_t tw)
{
- io_tw_lock(req->ctx, ts);
- return io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_MULTISHOT|
- IO_URING_F_COMPLETE_DEFER);
+ const unsigned int issue_flags = IO_URING_F_NONBLOCK |
+ IO_URING_F_MULTISHOT |
+ IO_URING_F_COMPLETE_DEFER;
+ int ret;
+
+ io_tw_lock(req->ctx, tw);
+
+ WARN_ON_ONCE(!req->file);
+ if (WARN_ON_ONCE(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EFAULT;
+
+ ret = __io_issue_sqe(req, issue_flags, &io_issue_defs[req->opcode]);
+
+ WARN_ON_ONCE(ret == IOU_ISSUE_SKIP_COMPLETE);
+ return ret;
}
struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
@@ -1818,7 +1840,7 @@ fail:
* Don't allow any multishot execution from io-wq. It's more restrictive
* than necessary and also cleaner.
*/
- if (req->flags & REQ_F_APOLL_MULTISHOT) {
+ if (req->flags & (REQ_F_MULTISHOT|REQ_F_APOLL_MULTISHOT)) {
err = -EBADFD;
if (!io_file_can_poll(req))
goto fail;
@@ -1829,7 +1851,7 @@ fail:
goto fail;
return;
} else {
- req->flags &= ~REQ_F_APOLL_MULTISHOT;
+ req->flags &= ~(REQ_F_APOLL_MULTISHOT|REQ_F_MULTISHOT);
}
}
@@ -1996,9 +2018,8 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
return true;
}
-static void io_init_req_drain(struct io_kiocb *req)
+static void io_init_drain(struct io_ring_ctx *ctx)
{
- struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *head = ctx->submit_state.link.head;
ctx->drain_active = true;
@@ -2062,7 +2083,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
if (sqe_flags & IOSQE_IO_DRAIN) {
if (ctx->drain_disabled)
return io_init_fail_req(req, -EOPNOTSUPP);
- io_init_req_drain(req);
+ io_init_drain(ctx);
}
}
if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
@@ -2423,7 +2444,7 @@ static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer)
goto out_wake;
}
- iowq->t.function = io_cqring_timer_wakeup;
+ hrtimer_update_function(&iowq->t, io_cqring_timer_wakeup);
hrtimer_set_expires(timer, iowq->timeout);
return HRTIMER_RESTART;
out_wake:
@@ -2458,8 +2479,18 @@ static int io_cqring_schedule_timeout(struct io_wait_queue *iowq,
return READ_ONCE(iowq->hit_timeout) ? -ETIME : 0;
}
+struct ext_arg {
+ size_t argsz;
+ struct timespec64 ts;
+ const sigset_t __user *sig;
+ ktime_t min_time;
+ bool ts_set;
+ bool iowait;
+};
+
static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
+ struct ext_arg *ext_arg,
ktime_t start_time)
{
int ret = 0;
@@ -2469,7 +2500,7 @@ static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx,
* can take into account that the task is waiting for IO - turns out
* to be important for low QD IO.
*/
- if (current_pending_io())
+ if (ext_arg->iowait && current_pending_io())
current->in_iowait = 1;
if (iowq->timeout != KTIME_MAX || iowq->min_timeout)
ret = io_cqring_schedule_timeout(iowq, ctx->clockid, start_time);
@@ -2482,6 +2513,7 @@ static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx,
/* If this returns > 0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
+ struct ext_arg *ext_arg,
ktime_t start_time)
{
if (unlikely(READ_ONCE(ctx->check_cq)))
@@ -2495,17 +2527,9 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
if (unlikely(io_should_wake(iowq)))
return 0;
- return __io_cqring_wait_schedule(ctx, iowq, start_time);
+ return __io_cqring_wait_schedule(ctx, iowq, ext_arg, start_time);
}
-struct ext_arg {
- size_t argsz;
- struct timespec64 ts;
- const sigset_t __user *sig;
- ktime_t min_time;
- bool ts_set;
-};
-
/*
* Wait until events become available, if we don't already have some. The
* application must reap them itself, as they reside on the shared cq ring.
@@ -2518,6 +2542,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
ktime_t start_time;
int ret;
+ min_events = min_t(int, min_events, ctx->cq_entries);
+
if (!io_allowed_run_tw(ctx))
return -EEXIST;
if (io_local_work_pending(ctx))
@@ -2583,7 +2609,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
TASK_INTERRUPTIBLE);
}
- ret = io_cqring_wait_schedule(ctx, &iowq, start_time);
+ ret = io_cqring_wait_schedule(ctx, &iowq, ext_arg, start_time);
__set_current_state(TASK_RUNNING);
atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
@@ -2702,14 +2728,10 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
mutex_lock(&ctx->uring_lock);
io_sqe_buffers_unregister(ctx);
io_sqe_files_unregister(ctx);
+ io_unregister_zcrx_ifqs(ctx);
io_cqring_overflow_kill(ctx);
io_eventfd_unregister(ctx);
- io_alloc_cache_free(&ctx->apoll_cache, kfree);
- io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
- io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free);
- io_alloc_cache_free(&ctx->uring_cache, kfree);
- io_alloc_cache_free(&ctx->msg_cache, kfree);
- io_futex_cache_free(ctx);
+ io_free_alloc_caches(ctx);
io_destroy_buffers(ctx);
io_free_region(ctx, &ctx->param_region);
mutex_unlock(&ctx->uring_lock);
@@ -2866,6 +2888,11 @@ static __cold void io_ring_exit_work(struct work_struct *work)
io_cqring_overflow_kill(ctx);
mutex_unlock(&ctx->uring_lock);
}
+ if (ctx->ifq) {
+ mutex_lock(&ctx->uring_lock);
+ io_shutdown_zcrx_ifqs(ctx);
+ mutex_unlock(&ctx->uring_lock);
+ }
if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
io_move_task_work_from_local(ctx);
@@ -3239,6 +3266,8 @@ static int io_get_ext_arg(struct io_ring_ctx *ctx, unsigned flags,
const struct io_uring_getevents_arg __user *uarg = argp;
struct io_uring_getevents_arg arg;
+ ext_arg->iowait = !(flags & IORING_ENTER_NO_IOWAIT);
+
/*
* If EXT_ARG isn't set, then we have no timespec and the argp pointer
* is just a pointer to the sigset_t.
@@ -3316,7 +3345,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG |
IORING_ENTER_REGISTERED_RING |
IORING_ENTER_ABS_TIMER |
- IORING_ENTER_EXT_ARG_REG)))
+ IORING_ENTER_EXT_ARG_REG |
+ IORING_ENTER_NO_IOWAIT)))
return -EINVAL;
/*
@@ -3400,22 +3430,16 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
mutex_lock(&ctx->uring_lock);
iopoll_locked:
ret2 = io_validate_ext_arg(ctx, flags, argp, argsz);
- if (likely(!ret2)) {
- min_complete = min(min_complete,
- ctx->cq_entries);
+ if (likely(!ret2))
ret2 = io_iopoll_check(ctx, min_complete);
- }
mutex_unlock(&ctx->uring_lock);
} else {
struct ext_arg ext_arg = { .argsz = argsz };
ret2 = io_get_ext_arg(ctx, flags, argp, &ext_arg);
- if (likely(!ret2)) {
- min_complete = min(min_complete,
- ctx->cq_entries);
+ if (likely(!ret2))
ret2 = io_cqring_wait(ctx, min_complete, flags,
&ext_arg);
- }
}
if (!ret) {
@@ -3537,6 +3561,44 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
O_RDWR | O_CLOEXEC, NULL);
}
+static int io_uring_sanitise_params(struct io_uring_params *p)
+{
+ unsigned flags = p->flags;
+
+ /* There is no way to mmap rings without a real fd */
+ if ((flags & IORING_SETUP_REGISTERED_FD_ONLY) &&
+ !(flags & IORING_SETUP_NO_MMAP))
+ return -EINVAL;
+
+ if (flags & IORING_SETUP_SQPOLL) {
+ /* IPI related flags don't make sense with SQPOLL */
+ if (flags & (IORING_SETUP_COOP_TASKRUN |
+ IORING_SETUP_TASKRUN_FLAG |
+ IORING_SETUP_DEFER_TASKRUN))
+ return -EINVAL;
+ }
+
+ if (flags & IORING_SETUP_TASKRUN_FLAG) {
+ if (!(flags & (IORING_SETUP_COOP_TASKRUN |
+ IORING_SETUP_DEFER_TASKRUN)))
+ return -EINVAL;
+ }
+
+ /* HYBRID_IOPOLL only valid with IOPOLL */
+ if ((flags & IORING_SETUP_HYBRID_IOPOLL) && !(flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
+ /*
+ * For DEFER_TASKRUN we require the completion task to be the same as
+ * the submission task. This implies that there is only one submitter.
+ */
+ if ((flags & IORING_SETUP_DEFER_TASKRUN) &&
+ !(flags & IORING_SETUP_SINGLE_ISSUER))
+ return -EINVAL;
+
+ return 0;
+}
+
int io_uring_fill_params(unsigned entries, struct io_uring_params *p)
{
if (!entries)
@@ -3547,10 +3609,6 @@ int io_uring_fill_params(unsigned entries, struct io_uring_params *p)
entries = IORING_MAX_ENTRIES;
}
- if ((p->flags & IORING_SETUP_REGISTERED_FD_ONLY)
- && !(p->flags & IORING_SETUP_NO_MMAP))
- return -EINVAL;
-
/*
* Use twice as many entries for the CQ ring. It's possible for the
* application to drive a higher depth than the size of the SQ ring,
@@ -3612,6 +3670,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
struct file *file;
int ret;
+ ret = io_uring_sanitise_params(p);
+ if (ret)
+ return ret;
+
ret = io_uring_fill_params(entries, p);
if (unlikely(ret))
return ret;
@@ -3659,37 +3721,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
* For SQPOLL, we just need a wakeup, always. For !SQPOLL, if
* COOP_TASKRUN is set, then IPIs are never needed by the app.
*/
- ret = -EINVAL;
- if (ctx->flags & IORING_SETUP_SQPOLL) {
- /* IPI related flags don't make sense with SQPOLL */
- if (ctx->flags & (IORING_SETUP_COOP_TASKRUN |
- IORING_SETUP_TASKRUN_FLAG |
- IORING_SETUP_DEFER_TASKRUN))
- goto err;
- ctx->notify_method = TWA_SIGNAL_NO_IPI;
- } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) {
+ if (ctx->flags & (IORING_SETUP_SQPOLL|IORING_SETUP_COOP_TASKRUN))
ctx->notify_method = TWA_SIGNAL_NO_IPI;
- } else {
- if (ctx->flags & IORING_SETUP_TASKRUN_FLAG &&
- !(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
- goto err;
+ else
ctx->notify_method = TWA_SIGNAL;
- }
-
- /* HYBRID_IOPOLL only valid with IOPOLL */
- if ((ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_HYBRID_IOPOLL)) ==
- IORING_SETUP_HYBRID_IOPOLL)
- goto err;
-
- /*
- * For DEFER_TASKRUN we require the completion task to be the same as the
- * submission task. This implies that there is only one submitter, so enforce
- * that.
- */
- if (ctx->flags & IORING_SETUP_DEFER_TASKRUN &&
- !(ctx->flags & IORING_SETUP_SINGLE_ISSUER)) {
- goto err;
- }
/*
* This is just grabbed for accounting purposes. When a process exits,
@@ -3719,7 +3754,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP |
IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING |
IORING_FEAT_RECVSEND_BUNDLE | IORING_FEAT_MIN_TIMEOUT |
- IORING_FEAT_RW_ATTR;
+ IORING_FEAT_RW_ATTR | IORING_FEAT_NO_IOWAIT;
if (copy_to_user(params, p, sizeof(*p))) {
ret = -EFAULT;
@@ -3793,29 +3828,36 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
return io_uring_create(entries, &p, params);
}
-static inline bool io_uring_allowed(void)
+static inline int io_uring_allowed(void)
{
int disabled = READ_ONCE(sysctl_io_uring_disabled);
kgid_t io_uring_group;
if (disabled == 2)
- return false;
+ return -EPERM;
if (disabled == 0 || capable(CAP_SYS_ADMIN))
- return true;
+ goto allowed_lsm;
io_uring_group = make_kgid(&init_user_ns, sysctl_io_uring_group);
if (!gid_valid(io_uring_group))
- return false;
+ return -EPERM;
- return in_group_p(io_uring_group);
+ if (!in_group_p(io_uring_group))
+ return -EPERM;
+
+allowed_lsm:
+ return security_uring_allowed();
}
SYSCALL_DEFINE2(io_uring_setup, u32, entries,
struct io_uring_params __user *, params)
{
- if (!io_uring_allowed())
- return -EPERM;
+ int ret;
+
+ ret = io_uring_allowed();
+ if (ret)
+ return ret;
return io_uring_setup(entries, params);
}
@@ -3908,6 +3950,9 @@ static int __init io_uring_init(void)
io_uring_optable_init();
+ /* imu->dir is u8 */
+ BUILD_BUG_ON((IO_IMU_DEST | IO_IMU_SOURCE) > U8_MAX);
+
/*
* Allow user copy in the per-command field, which starts after the
* file in io_kiocb and until the opcode field. The openat2 handling
@@ -3918,10 +3963,9 @@ static int __init io_uring_init(void)
req_cachep = kmem_cache_create("io_kiocb", sizeof(struct io_kiocb), &kmem_args,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT |
SLAB_TYPESAFE_BY_RCU);
- io_buf_cachep = KMEM_CACHE(io_buffer,
- SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64);
+ BUG_ON(!iou_wq);
#ifdef CONFIG_SYSCTL
register_sysctl_init("kernel", kernel_io_uring_disabled_table);
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index ab619e63ef39..87f883130286 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -19,22 +19,25 @@
#endif
enum {
- IOU_OK = 0,
+ IOU_OK = 0, /* deprecated, use IOU_COMPLETE */
+ IOU_COMPLETE = 0,
+
IOU_ISSUE_SKIP_COMPLETE = -EIOCBQUEUED,
/*
+ * The request has more work to do and should be retried. io_uring will
+ * attempt to wait on the file for eligible opcodes, but otherwise
+ * it'll be handed to iowq for blocking execution. It works for normal
+ * requests as well as for the multi shot mode.
+ */
+ IOU_RETRY = -EAGAIN,
+
+ /*
* Requeue the task_work to restart operations on this request. The
* actual value isn't important, should just be not an otherwise
* valid error code, yet less than -MAX_ERRNO and valid internally.
*/
IOU_REQUEUE = -3072,
-
- /*
- * Intended only when both IO_URING_F_MULTISHOT is passed
- * to indicate to the poll runner that multishot should be
- * removed and the result is set on req->cqe.res.
- */
- IOU_STOP_MULTISHOT = -ECANCELED,
};
struct io_wait_queue {
@@ -88,11 +91,10 @@ struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
void __io_req_task_work_add(struct io_kiocb *req, unsigned flags);
void io_req_task_work_add_remote(struct io_kiocb *req, struct io_ring_ctx *ctx,
unsigned flags);
-bool io_alloc_async_data(struct io_kiocb *req);
void io_req_task_queue(struct io_kiocb *req);
-void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts);
+void io_req_task_complete(struct io_kiocb *req, io_tw_token_t tw);
void io_req_task_queue_fail(struct io_kiocb *req, int ret);
-void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts);
+void io_req_task_submit(struct io_kiocb *req, io_tw_token_t tw);
struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries);
struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
void tctx_task_work(struct callback_head *cb);
@@ -104,7 +106,7 @@ int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
int start, int end);
void io_req_queue_iowq(struct io_kiocb *req);
-int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts);
+int io_poll_issue(struct io_kiocb *req, io_tw_token_t tw);
int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr);
int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin);
void __io_submit_flush_completions(struct io_ring_ctx *ctx);
@@ -147,6 +149,11 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
#endif
}
+static inline bool io_is_compat(struct io_ring_ctx *ctx)
+{
+ return IS_ENABLED(CONFIG_COMPAT) && unlikely(ctx->compat);
+}
+
static inline void io_req_task_work_add(struct io_kiocb *req)
{
__io_req_task_work_add(req, 0);
@@ -185,6 +192,16 @@ static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret
return io_get_cqe_overflow(ctx, ret, false);
}
+static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx,
+ struct io_uring_cqe **cqe_ret)
+{
+ io_lockdep_assert_cq_locked(ctx);
+
+ ctx->cq_extra++;
+ ctx->submit_state.cq_flush = true;
+ return io_get_cqe(ctx, cqe_ret);
+}
+
static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
struct io_kiocb *req)
{
@@ -376,7 +393,7 @@ static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
return task_work_pending(current) || io_local_work_pending(ctx);
}
-static inline void io_tw_lock(struct io_ring_ctx *ctx, struct io_tw_state *ts)
+static inline void io_tw_lock(struct io_ring_ctx *ctx, io_tw_token_t tw)
{
lockdep_assert_held(&ctx->uring_lock);
}
@@ -418,7 +435,6 @@ static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
}
extern struct kmem_cache *req_cachep;
-extern struct kmem_cache *io_buf_cachep;
static inline struct io_kiocb *io_extract_req(struct io_ring_ctx *ctx)
{
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 8e72de7712ac..098109259671 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -20,7 +20,8 @@
/* BIDs are addressed by a 16-bit field in a CQE */
#define MAX_BIDS_PER_BGID (1 << 16)
-struct kmem_cache *io_buf_cachep;
+/* Mapped buffer ring, return io_uring_buf from head */
+#define io_ring_head_to_buf(br, head, mask) &(br)->bufs[(head) & (mask)]
struct io_provide_buf {
struct file *file;
@@ -31,6 +32,41 @@ struct io_provide_buf {
__u16 bid;
};
+static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
+{
+ while (len) {
+ struct io_uring_buf *buf;
+ u32 this_len;
+
+ buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask);
+ this_len = min_t(int, len, buf->len);
+ buf->len -= this_len;
+ if (buf->len) {
+ buf->addr += this_len;
+ return false;
+ }
+ bl->head++;
+ len -= this_len;
+ }
+ return true;
+}
+
+bool io_kbuf_commit(struct io_kiocb *req,
+ struct io_buffer_list *bl, int len, int nr)
+{
+ if (unlikely(!(req->flags & REQ_F_BUFFERS_COMMIT)))
+ return true;
+
+ req->flags &= ~REQ_F_BUFFERS_COMMIT;
+
+ if (unlikely(len < 0))
+ return true;
+ if (bl->flags & IOBL_INC)
+ return io_kbuf_inc_commit(bl, len);
+ bl->head += nr;
+ return true;
+}
+
static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
unsigned int bgid)
{
@@ -52,6 +88,16 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx,
return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
}
+void io_kbuf_drop_legacy(struct io_kiocb *req)
+{
+ if (WARN_ON_ONCE(!(req->flags & REQ_F_BUFFER_SELECTED)))
+ return;
+ req->buf_index = req->kbuf->bgid;
+ req->flags &= ~REQ_F_BUFFER_SELECTED;
+ kfree(req->kbuf);
+ req->kbuf = NULL;
+}
+
bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -70,33 +116,6 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
return true;
}
-void __io_put_kbuf(struct io_kiocb *req, int len, unsigned issue_flags)
-{
- /*
- * We can add this buffer back to two lists:
- *
- * 1) The io_buffers_cache list. This one is protected by the
- * ctx->uring_lock. If we already hold this lock, add back to this
- * list as we can grab it from issue as well.
- * 2) The io_buffers_comp list. This one is protected by the
- * ctx->completion_lock.
- *
- * We migrate buffers from the comp_list to the issue cache list
- * when we need one.
- */
- if (issue_flags & IO_URING_F_UNLOCKED) {
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock(&ctx->completion_lock);
- __io_put_kbuf_list(req, len, &ctx->io_buffers_comp);
- spin_unlock(&ctx->completion_lock);
- } else {
- lockdep_assert_held(&req->ctx->uring_lock);
-
- __io_put_kbuf_list(req, len, &req->ctx->io_buffers_cache);
- }
-}
-
static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
struct io_buffer_list *bl)
{
@@ -214,25 +233,14 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
buf = io_ring_head_to_buf(br, head, bl->mask);
if (arg->max_len) {
u32 len = READ_ONCE(buf->len);
+ size_t needed;
if (unlikely(!len))
return -ENOBUFS;
- /*
- * Limit incremental buffers to 1 segment. No point trying
- * to peek ahead and map more than we need, when the buffers
- * themselves should be large when setup with
- * IOU_PBUF_RING_INC.
- */
- if (bl->flags & IOBL_INC) {
- nr_avail = 1;
- } else {
- size_t needed;
-
- needed = (arg->max_len + len - 1) / len;
- needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT);
- if (nr_avail > needed)
- nr_avail = needed;
- }
+ needed = (arg->max_len + len - 1) / len;
+ needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT);
+ if (nr_avail > needed)
+ nr_avail = needed;
}
/*
@@ -342,6 +350,35 @@ int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg)
return io_provided_buffers_select(req, &arg->max_len, bl, arg->iovs);
}
+static inline bool __io_put_kbuf_ring(struct io_kiocb *req, int len, int nr)
+{
+ struct io_buffer_list *bl = req->buf_list;
+ bool ret = true;
+
+ if (bl) {
+ ret = io_kbuf_commit(req, bl, len, nr);
+ req->buf_index = bl->bgid;
+ }
+ req->flags &= ~REQ_F_BUFFER_RING;
+ return ret;
+}
+
+unsigned int __io_put_kbufs(struct io_kiocb *req, int len, int nbufs)
+{
+ unsigned int ret;
+
+ ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+
+ if (unlikely(!(req->flags & REQ_F_BUFFER_RING))) {
+ io_kbuf_drop_legacy(req);
+ return ret;
+ }
+
+ if (!__io_put_kbuf_ring(req, len, nbufs))
+ ret |= IORING_CQE_F_BUF_MORE;
+ return ret;
+}
+
static int __io_remove_buffers(struct io_ring_ctx *ctx,
struct io_buffer_list *bl, unsigned nbufs)
{
@@ -367,7 +404,9 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
struct io_buffer *nxt;
nxt = list_first_entry(&bl->buf_list, struct io_buffer, list);
- list_move(&nxt->list, &ctx->io_buffers_cache);
+ list_del(&nxt->list);
+ kfree(nxt);
+
if (++i == nbufs)
return i;
cond_resched();
@@ -385,8 +424,6 @@ static void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
void io_destroy_buffers(struct io_ring_ctx *ctx)
{
struct io_buffer_list *bl;
- struct list_head *item, *tmp;
- struct io_buffer *buf;
while (1) {
unsigned long index = 0;
@@ -400,19 +437,6 @@ void io_destroy_buffers(struct io_ring_ctx *ctx)
break;
io_put_bl(ctx, bl);
}
-
- /*
- * Move deferred locked entries to cache before pruning
- */
- spin_lock(&ctx->completion_lock);
- if (!list_empty(&ctx->io_buffers_comp))
- list_splice_init(&ctx->io_buffers_comp, &ctx->io_buffers_cache);
- spin_unlock(&ctx->completion_lock);
-
- list_for_each_safe(item, tmp, &ctx->io_buffers_cache) {
- buf = list_entry(item, struct io_buffer, list);
- kmem_cache_free(io_buf_cachep, buf);
- }
}
static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
@@ -501,53 +525,6 @@ int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
return 0;
}
-#define IO_BUFFER_ALLOC_BATCH 64
-
-static int io_refill_buffer_cache(struct io_ring_ctx *ctx)
-{
- struct io_buffer *bufs[IO_BUFFER_ALLOC_BATCH];
- int allocated;
-
- /*
- * Completions that don't happen inline (eg not under uring_lock) will
- * add to ->io_buffers_comp. If we don't have any free buffers, check
- * the completion list and splice those entries first.
- */
- if (!list_empty_careful(&ctx->io_buffers_comp)) {
- spin_lock(&ctx->completion_lock);
- if (!list_empty(&ctx->io_buffers_comp)) {
- list_splice_init(&ctx->io_buffers_comp,
- &ctx->io_buffers_cache);
- spin_unlock(&ctx->completion_lock);
- return 0;
- }
- spin_unlock(&ctx->completion_lock);
- }
-
- /*
- * No free buffers and no completion entries either. Allocate a new
- * batch of buffer entries and add those to our freelist.
- */
-
- allocated = kmem_cache_alloc_bulk(io_buf_cachep, GFP_KERNEL_ACCOUNT,
- ARRAY_SIZE(bufs), (void **) bufs);
- if (unlikely(!allocated)) {
- /*
- * Bulk alloc is all-or-nothing. If we fail to get a batch,
- * retry single alloc to be on the safe side.
- */
- bufs[0] = kmem_cache_alloc(io_buf_cachep, GFP_KERNEL);
- if (!bufs[0])
- return -ENOMEM;
- allocated = 1;
- }
-
- while (allocated)
- list_add_tail(&bufs[--allocated]->list, &ctx->io_buffers_cache);
-
- return 0;
-}
-
static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf,
struct io_buffer_list *bl)
{
@@ -556,12 +533,11 @@ static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf,
int i, bid = pbuf->bid;
for (i = 0; i < pbuf->nbufs; i++) {
- if (list_empty(&ctx->io_buffers_cache) &&
- io_refill_buffer_cache(ctx))
+ buf = kmalloc(sizeof(*buf), GFP_KERNEL_ACCOUNT);
+ if (!buf)
break;
- buf = list_first_entry(&ctx->io_buffers_cache, struct io_buffer,
- list);
- list_move_tail(&buf->list, &bl->buf_list);
+
+ list_add_tail(&buf->list, &bl->buf_list);
buf->addr = addr;
buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT);
buf->bid = bid;
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index bd80c44c5af1..2ec0b983ce24 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -74,9 +74,12 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
-void __io_put_kbuf(struct io_kiocb *req, int len, unsigned issue_flags);
-
bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
+void io_kbuf_drop_legacy(struct io_kiocb *req);
+
+unsigned int __io_put_kbufs(struct io_kiocb *req, int len, int nbufs);
+bool io_kbuf_commit(struct io_kiocb *req,
+ struct io_buffer_list *bl, int len, int nr);
struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx,
unsigned int bgid);
@@ -116,100 +119,19 @@ static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
return false;
}
-/* Mapped buffer ring, return io_uring_buf from head */
-#define io_ring_head_to_buf(br, head, mask) &(br)->bufs[(head) & (mask)]
-
-static inline bool io_kbuf_commit(struct io_kiocb *req,
- struct io_buffer_list *bl, int len, int nr)
-{
- if (unlikely(!(req->flags & REQ_F_BUFFERS_COMMIT)))
- return true;
-
- req->flags &= ~REQ_F_BUFFERS_COMMIT;
-
- if (unlikely(len < 0))
- return true;
-
- if (bl->flags & IOBL_INC) {
- struct io_uring_buf *buf;
-
- buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask);
- if (WARN_ON_ONCE(len > buf->len))
- len = buf->len;
- buf->len -= len;
- if (buf->len) {
- buf->addr += len;
- return false;
- }
- }
-
- bl->head += nr;
- return true;
-}
-
-static inline bool __io_put_kbuf_ring(struct io_kiocb *req, int len, int nr)
-{
- struct io_buffer_list *bl = req->buf_list;
- bool ret = true;
-
- if (bl) {
- ret = io_kbuf_commit(req, bl, len, nr);
- req->buf_index = bl->bgid;
- }
- req->flags &= ~REQ_F_BUFFER_RING;
- return ret;
-}
-
-static inline void __io_put_kbuf_list(struct io_kiocb *req, int len,
- struct list_head *list)
-{
- if (req->flags & REQ_F_BUFFER_RING) {
- __io_put_kbuf_ring(req, len, 1);
- } else {
- req->buf_index = req->kbuf->bgid;
- list_add(&req->kbuf->list, list);
- req->flags &= ~REQ_F_BUFFER_SELECTED;
- }
-}
-
-static inline void io_kbuf_drop(struct io_kiocb *req)
-{
- lockdep_assert_held(&req->ctx->completion_lock);
-
- if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
- return;
-
- /* len == 0 is fine here, non-ring will always drop all of it */
- __io_put_kbuf_list(req, 0, &req->ctx->io_buffers_comp);
-}
-
-static inline unsigned int __io_put_kbufs(struct io_kiocb *req, int len,
- int nbufs, unsigned issue_flags)
-{
- unsigned int ret;
-
- if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
- return 0;
-
- ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
- if (req->flags & REQ_F_BUFFER_RING) {
- if (!__io_put_kbuf_ring(req, len, nbufs))
- ret |= IORING_CQE_F_BUF_MORE;
- } else {
- __io_put_kbuf(req, len, issue_flags);
- }
- return ret;
-}
-
static inline unsigned int io_put_kbuf(struct io_kiocb *req, int len,
unsigned issue_flags)
{
- return __io_put_kbufs(req, len, 1, issue_flags);
+ if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
+ return 0;
+ return __io_put_kbufs(req, len, 1);
}
static inline unsigned int io_put_kbufs(struct io_kiocb *req, int len,
int nbufs, unsigned issue_flags)
{
- return __io_put_kbufs(req, len, nbufs, issue_flags);
+ if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
+ return 0;
+ return __io_put_kbufs(req, len, nbufs);
}
#endif
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 361134544427..76fcc79656b0 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -271,6 +271,8 @@ static struct io_mapped_region *io_mmap_get_region(struct io_ring_ctx *ctx,
return io_pbuf_get_region(ctx, bgid);
case IORING_MAP_OFF_PARAM_REGION:
return &ctx->param_region;
+ case IORING_MAP_OFF_ZCRX_REGION:
+ return &ctx->zcrx_region;
}
return NULL;
}
diff --git a/io_uring/memmap.h b/io_uring/memmap.h
index c898dcba2b4e..dad0aa5b1b45 100644
--- a/io_uring/memmap.h
+++ b/io_uring/memmap.h
@@ -2,6 +2,7 @@
#define IO_URING_MEMMAP_H
#define IORING_MAP_OFF_PARAM_REGION 0x20000000ULL
+#define IORING_MAP_OFF_ZCRX_REGION 0x30000000ULL
struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages);
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 7e6f68e911f1..0bbcbbcdebfd 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -71,7 +71,7 @@ static inline bool io_msg_need_remote(struct io_ring_ctx *target_ctx)
return target_ctx->task_complete;
}
-static void io_msg_tw_complete(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_ring_ctx *ctx = req->ctx;
diff --git a/io_uring/napi.c b/io_uring/napi.c
index b1ade3fda30f..4a10de03e426 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -44,7 +44,7 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id)
struct io_napi_entry *e;
/* Non-NAPI IDs can be rejected. */
- if (napi_id < MIN_NAPI_ID)
+ if (!napi_id_valid(napi_id))
return -EINVAL;
hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
@@ -87,7 +87,7 @@ static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id)
struct io_napi_entry *e;
/* Non-NAPI IDs can be rejected. */
- if (napi_id < MIN_NAPI_ID)
+ if (!napi_id_valid(napi_id))
return -EINVAL;
hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
diff --git a/io_uring/net.c b/io_uring/net.c
index 5d0b56ff50ee..8944eb679024 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -16,6 +16,7 @@
#include "net.h"
#include "notif.h"
#include "rsrc.h"
+#include "zcrx.h"
#if defined(CONFIG_NET)
struct io_shutdown {
@@ -75,7 +76,7 @@ struct io_sr_msg {
u16 flags;
/* initialised and used only by !msg send variants */
u16 buf_group;
- u16 buf_index;
+ bool retry;
void __user *msg_control;
/* used only for send zerocopy */
struct io_kiocb *notif;
@@ -88,6 +89,14 @@ struct io_sr_msg {
*/
#define MULTISHOT_MAX_RETRY 32
+struct io_recvzc {
+ struct file *file;
+ unsigned msg_flags;
+ u16 flags;
+ u32 len;
+ struct io_zcrx_ifq *ifq;
+};
+
int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
@@ -127,11 +136,8 @@ static bool io_net_retry(struct socket *sock, int flags)
static void io_netmsg_iovec_free(struct io_async_msghdr *kmsg)
{
- if (kmsg->free_iov) {
- kfree(kmsg->free_iov);
- kmsg->free_iov_nr = 0;
- kmsg->free_iov = NULL;
- }
+ if (kmsg->vec.iovec)
+ io_vec_free(&kmsg->vec);
}
static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags)
@@ -145,10 +151,13 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags)
}
/* Let normal cleanup path reap it if we fail adding to the cache */
- io_alloc_cache_kasan(&hdr->free_iov, &hdr->free_iov_nr);
+ io_alloc_cache_vec_kasan(&hdr->vec);
+ if (hdr->vec.nr > IO_VEC_CACHE_SOFT_CAP)
+ io_vec_free(&hdr->vec);
+
if (io_alloc_cache_put(&req->ctx->netmsg_cache, hdr)) {
req->async_data = NULL;
- req->flags &= ~REQ_F_ASYNC_DATA;
+ req->flags &= ~(REQ_F_ASYNC_DATA|REQ_F_NEED_CLEANUP);
}
}
@@ -162,7 +171,7 @@ static struct io_async_msghdr *io_msg_alloc_async(struct io_kiocb *req)
return NULL;
/* If the async data was cached, we might have an iov cached inside. */
- if (hdr->free_iov)
+ if (hdr->vec.iovec)
req->flags |= REQ_F_NEED_CLEANUP;
return hdr;
}
@@ -173,10 +182,7 @@ static void io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg
{
if (iov) {
req->flags |= REQ_F_NEED_CLEANUP;
- kmsg->free_iov_nr = kmsg->msg.msg_iter.nr_segs;
- if (kmsg->free_iov)
- kfree(kmsg->free_iov);
- kmsg->free_iov = iov;
+ io_vec_reset_iovec(&kmsg->vec, iov, kmsg->msg.msg_iter.nr_segs);
}
}
@@ -187,120 +193,135 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req,
req->flags &= ~REQ_F_BL_EMPTY;
sr->done_io = 0;
+ sr->retry = false;
sr->len = 0; /* get from the provided buffer */
req->buf_index = sr->buf_group;
}
-#ifdef CONFIG_COMPAT
-static int io_compat_msg_copy_hdr(struct io_kiocb *req,
- struct io_async_msghdr *iomsg,
- struct compat_msghdr *msg, int ddir)
+static int io_net_import_vec(struct io_kiocb *req, struct io_async_msghdr *iomsg,
+ const struct iovec __user *uiov, unsigned uvec_seg,
+ int ddir)
{
- struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
- struct compat_iovec __user *uiov;
struct iovec *iov;
int ret, nr_segs;
- if (iomsg->free_iov) {
- nr_segs = iomsg->free_iov_nr;
- iov = iomsg->free_iov;
+ if (iomsg->vec.iovec) {
+ nr_segs = iomsg->vec.nr;
+ iov = iomsg->vec.iovec;
} else {
- iov = &iomsg->fast_iov;
nr_segs = 1;
+ iov = &iomsg->fast_iov;
}
+ ret = __import_iovec(ddir, uiov, uvec_seg, nr_segs, &iov,
+ &iomsg->msg.msg_iter, io_is_compat(req->ctx));
+ if (unlikely(ret < 0))
+ return ret;
+ io_net_vec_assign(req, iomsg, iov);
+ return 0;
+}
+
+static int io_compat_msg_copy_hdr(struct io_kiocb *req,
+ struct io_async_msghdr *iomsg,
+ struct compat_msghdr *msg, int ddir,
+ struct sockaddr __user **save_addr)
+{
+ struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+ struct compat_iovec __user *uiov;
+ int ret;
+
if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg)))
return -EFAULT;
+ ret = __get_compat_msghdr(&iomsg->msg, msg, save_addr);
+ if (ret)
+ return ret;
+
uiov = compat_ptr(msg->msg_iov);
if (req->flags & REQ_F_BUFFER_SELECT) {
- compat_ssize_t clen;
-
if (msg->msg_iovlen == 0) {
- sr->len = iov->iov_len = 0;
- iov->iov_base = NULL;
+ sr->len = 0;
} else if (msg->msg_iovlen > 1) {
return -EINVAL;
} else {
- if (!access_ok(uiov, sizeof(*uiov)))
- return -EFAULT;
- if (__get_user(clen, &uiov->iov_len))
+ struct compat_iovec tmp_iov;
+
+ if (copy_from_user(&tmp_iov, uiov, sizeof(tmp_iov)))
return -EFAULT;
- if (clen < 0)
- return -EINVAL;
- sr->len = clen;
+ sr->len = tmp_iov.iov_len;
}
-
- return 0;
}
-
- ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen,
- nr_segs, &iov, &iomsg->msg.msg_iter, true);
- if (unlikely(ret < 0))
- return ret;
-
- io_net_vec_assign(req, iomsg, iov);
return 0;
}
-#endif
-static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
- struct user_msghdr *msg, int ddir)
+static int io_copy_msghdr_from_user(struct user_msghdr *msg,
+ struct user_msghdr __user *umsg)
{
- struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
- struct user_msghdr __user *umsg = sr->umsg;
- struct iovec *iov;
- int ret, nr_segs;
-
- if (iomsg->free_iov) {
- nr_segs = iomsg->free_iov_nr;
- iov = iomsg->free_iov;
- } else {
- iov = &iomsg->fast_iov;
- nr_segs = 1;
- }
-
if (!user_access_begin(umsg, sizeof(*umsg)))
return -EFAULT;
-
- ret = -EFAULT;
unsafe_get_user(msg->msg_name, &umsg->msg_name, ua_end);
unsafe_get_user(msg->msg_namelen, &umsg->msg_namelen, ua_end);
unsafe_get_user(msg->msg_iov, &umsg->msg_iov, ua_end);
unsafe_get_user(msg->msg_iovlen, &umsg->msg_iovlen, ua_end);
unsafe_get_user(msg->msg_control, &umsg->msg_control, ua_end);
unsafe_get_user(msg->msg_controllen, &umsg->msg_controllen, ua_end);
+ user_access_end();
+ return 0;
+ua_end:
+ user_access_end();
+ return -EFAULT;
+}
+
+static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
+ struct user_msghdr *msg, int ddir,
+ struct sockaddr __user **save_addr)
+{
+ struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+ struct user_msghdr __user *umsg = sr->umsg;
+ int ret;
+
+ iomsg->msg.msg_name = &iomsg->addr;
+ iomsg->msg.msg_iter.nr_segs = 0;
+
+ if (io_is_compat(req->ctx)) {
+ struct compat_msghdr cmsg;
+
+ ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ddir, save_addr);
+ if (ret)
+ return ret;
+
+ memset(msg, 0, sizeof(*msg));
+ msg->msg_namelen = cmsg.msg_namelen;
+ msg->msg_controllen = cmsg.msg_controllen;
+ msg->msg_iov = compat_ptr(cmsg.msg_iov);
+ msg->msg_iovlen = cmsg.msg_iovlen;
+ return 0;
+ }
+
+ ret = io_copy_msghdr_from_user(msg, umsg);
+ if (unlikely(ret))
+ return ret;
+
msg->msg_flags = 0;
+ ret = __copy_msghdr(&iomsg->msg, msg, save_addr);
+ if (ret)
+ return ret;
+
if (req->flags & REQ_F_BUFFER_SELECT) {
if (msg->msg_iovlen == 0) {
- sr->len = iov->iov_len = 0;
- iov->iov_base = NULL;
+ sr->len = 0;
} else if (msg->msg_iovlen > 1) {
- ret = -EINVAL;
- goto ua_end;
+ return -EINVAL;
} else {
struct iovec __user *uiov = msg->msg_iov;
+ struct iovec tmp_iov;
- /* we only need the length for provided buffers */
- if (!access_ok(&uiov->iov_len, sizeof(uiov->iov_len)))
- goto ua_end;
- unsafe_get_user(iov->iov_len, &uiov->iov_len, ua_end);
- sr->len = iov->iov_len;
+ if (copy_from_user(&tmp_iov, uiov, sizeof(tmp_iov)))
+ return -EFAULT;
+ sr->len = tmp_iov.iov_len;
}
- ret = 0;
-ua_end:
- user_access_end();
- return ret;
}
-
- user_access_end();
- ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, nr_segs,
- &iov, &iomsg->msg.msg_iter, false);
- if (unlikely(ret < 0))
- return ret;
-
- io_net_vec_assign(req, iomsg, iov);
return 0;
}
@@ -311,29 +332,13 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req,
struct user_msghdr msg;
int ret;
- iomsg->msg.msg_name = &iomsg->addr;
- iomsg->msg.msg_iter.nr_segs = 0;
-
-#ifdef CONFIG_COMPAT
- if (unlikely(req->ctx->compat)) {
- struct compat_msghdr cmsg;
-
- ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE);
- if (unlikely(ret))
- return ret;
-
- ret = __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
- sr->msg_control = iomsg->msg.msg_control_user;
- return ret;
- }
-#endif
-
- ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE);
+ ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE, NULL);
if (unlikely(ret))
return ret;
- ret = __copy_msghdr(&iomsg->msg, &msg, NULL);
-
+ if (!(req->flags & REQ_F_BUFFER_SELECT))
+ ret = io_net_import_vec(req, iomsg, msg.msg_iov, msg.msg_iovlen,
+ ITER_SOURCE);
/* save msg_control as sys_sendmsg() overwrites it */
sr->msg_control = iomsg->msg.msg_control_user;
return ret;
@@ -387,14 +392,31 @@ static int io_sendmsg_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
+
+ sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
+
+ return io_sendmsg_copy_hdr(req, kmsg);
+}
+
+static int io_sendmsg_zc_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+ struct io_async_msghdr *kmsg = req->async_data;
+ struct user_msghdr msg;
int ret;
+ if (!(sr->flags & IORING_RECVSEND_FIXED_BUF))
+ return io_sendmsg_setup(req, sqe);
+
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
- ret = io_sendmsg_copy_hdr(req, kmsg);
- if (!ret)
- req->flags |= REQ_F_NEED_CLEANUP;
- return ret;
+ ret = io_msg_copy_hdr(req, kmsg, &msg, ITER_SOURCE, NULL);
+ if (unlikely(ret))
+ return ret;
+ sr->msg_control = kmsg->msg.msg_control_user;
+ kmsg->msg.msg_iter.nr_segs = msg.msg_iovlen;
+
+ return io_prep_reg_iovec(req, &kmsg->vec, msg.msg_iov, msg.msg_iovlen);
}
#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE)
@@ -404,6 +426,7 @@ 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 = false;
if (req->opcode != IORING_OP_SEND) {
if (sqe->addr2 || sqe->file_index)
@@ -425,12 +448,12 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
sr->msg_flags |= MSG_WAITALL;
sr->buf_group = req->buf_index;
req->buf_list = NULL;
+ req->flags |= REQ_F_MULTISHOT;
}
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
+ if (io_is_compat(req->ctx))
sr->msg_flags |= MSG_CMSG_COMPAT;
-#endif
+
if (unlikely(!io_msg_alloc_async(req)))
return -ENOMEM;
if (req->opcode != IORING_OP_SENDMSG)
@@ -441,7 +464,6 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
static void io_req_msg_cleanup(struct io_kiocb *req,
unsigned int issue_flags)
{
- req->flags &= ~REQ_F_NEED_CLEANUP;
io_netmsg_recycle(req, issue_flags);
}
@@ -464,7 +486,7 @@ static int io_bundle_nbufs(struct io_async_msghdr *kmsg, int ret)
if (iter_is_ubuf(&kmsg->msg.msg_iter))
return 1;
- iov = kmsg->free_iov;
+ iov = kmsg->vec.iovec;
if (!iov)
iov = &kmsg->fast_iov;
@@ -580,9 +602,9 @@ static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags,
.nr_iovs = 1,
};
- if (kmsg->free_iov) {
- arg.nr_iovs = kmsg->free_iov_nr;
- arg.iovs = kmsg->free_iov;
+ if (kmsg->vec.iovec) {
+ arg.nr_iovs = kmsg->vec.nr;
+ arg.iovs = kmsg->vec.iovec;
arg.mode = KBUF_MODE_FREE;
}
@@ -595,9 +617,9 @@ static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags,
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;
+ if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) {
+ kmsg->vec.nr = ret;
+ kmsg->vec.iovec = arg.iovs;
req->flags |= REQ_F_NEED_CLEANUP;
}
sr->len = arg.out_len;
@@ -712,34 +734,16 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req,
struct user_msghdr msg;
int ret;
- iomsg->msg.msg_name = &iomsg->addr;
- iomsg->msg.msg_iter.nr_segs = 0;
-
-#ifdef CONFIG_COMPAT
- if (unlikely(req->ctx->compat)) {
- struct compat_msghdr cmsg;
-
- ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST);
- if (unlikely(ret))
- return ret;
+ ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST, &iomsg->uaddr);
+ if (unlikely(ret))
+ return ret;
- ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr);
+ if (!(req->flags & REQ_F_BUFFER_SELECT)) {
+ ret = io_net_import_vec(req, iomsg, msg.msg_iov, msg.msg_iovlen,
+ ITER_DEST);
if (unlikely(ret))
return ret;
-
- return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen,
- cmsg.msg_controllen);
}
-#endif
-
- ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST);
- if (unlikely(ret))
- return ret;
-
- ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
- if (unlikely(ret))
- return ret;
-
return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen,
msg.msg_controllen);
}
@@ -773,10 +777,7 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req)
return 0;
}
- ret = io_recvmsg_copy_hdr(req, kmsg);
- if (!ret)
- req->flags |= REQ_F_NEED_CLEANUP;
- return ret;
+ return io_recvmsg_copy_hdr(req, kmsg);
}
#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT | \
@@ -787,6 +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 = false;
if (unlikely(sqe->file_index || sqe->addr2))
return -EINVAL;
@@ -827,14 +829,16 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return -EINVAL;
}
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
+ if (io_is_compat(req->ctx))
sr->msg_flags |= MSG_CMSG_COMPAT;
-#endif
+
sr->nr_multishot_loops = 0;
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.
*
@@ -854,9 +858,19 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
if (sr->flags & IORING_RECVSEND_BUNDLE) {
cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, *ret),
issue_flags);
+ if (sr->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, retry and append to this one */
+ if (!sr->retry && kmsg->msg.msg_inq > 0 && *ret > 0) {
+ req->cqe.flags = cflags & ~CQE_F_MASK;
+ sr->len = kmsg->msg.msg_inq;
+ sr->done_io += *ret;
+ sr->retry = true;
+ return false;
+ }
} else {
cflags |= io_put_kbuf(req, *ret, issue_flags);
}
@@ -867,8 +881,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
*/
if ((req->flags & REQ_F_APOLL_MULTISHOT) && !mshot_finished &&
io_req_post_cqe(req, *ret, cflags | IORING_CQE_F_MORE)) {
- int mshot_retry_ret = IOU_ISSUE_SKIP_COMPLETE;
-
+ *ret = IOU_RETRY;
io_mshot_prep_retry(req, kmsg);
/* Known not-empty or unknown state, retry */
if (cflags & IORING_CQE_F_SOCK_NONEMPTY || kmsg->msg.msg_inq < 0) {
@@ -876,23 +889,16 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
return false;
/* mshot retries exceeded, force a requeue */
sr->nr_multishot_loops = 0;
- mshot_retry_ret = IOU_REQUEUE;
+ if (issue_flags & IO_URING_F_MULTISHOT)
+ *ret = IOU_REQUEUE;
}
- if (issue_flags & IO_URING_F_MULTISHOT)
- *ret = mshot_retry_ret;
- else
- *ret = -EAGAIN;
return true;
}
/* Finish the request / stop multishot. */
finish:
io_req_set_res(req, *ret, cflags);
-
- if (issue_flags & IO_URING_F_MULTISHOT)
- *ret = IOU_STOP_MULTISHOT;
- else
- *ret = IOU_OK;
+ *ret = IOU_COMPLETE;
io_req_msg_cleanup(req, issue_flags);
return true;
}
@@ -1039,16 +1045,15 @@ retry_multishot:
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock) {
- if (issue_flags & IO_URING_F_MULTISHOT) {
+ if (issue_flags & IO_URING_F_MULTISHOT)
io_kbuf_recycle(req, issue_flags);
- return IOU_ISSUE_SKIP_COMPLETE;
- }
- return -EAGAIN;
+
+ return IOU_RETRY;
}
if (ret > 0 && io_net_retry(sock, flags)) {
sr->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
- return -EAGAIN;
+ return IOU_RETRY;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
@@ -1089,9 +1094,9 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
.mode = KBUF_MODE_EXPAND,
};
- if (kmsg->free_iov) {
- arg.nr_iovs = kmsg->free_iov_nr;
- arg.iovs = kmsg->free_iov;
+ if (kmsg->vec.iovec) {
+ arg.nr_iovs = kmsg->vec.nr;
+ arg.iovs = kmsg->vec.iovec;
arg.mode |= KBUF_MODE_FREE;
}
@@ -1110,9 +1115,9 @@ 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;
+ if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) {
+ kmsg->vec.nr = ret;
+ kmsg->vec.iovec = arg.iovs;
req->flags |= REQ_F_NEED_CLEANUP;
}
} else {
@@ -1176,12 +1181,10 @@ retry_multishot:
ret = sock_recvmsg(sock, &kmsg->msg, flags);
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock) {
- if (issue_flags & IO_URING_F_MULTISHOT) {
+ if (issue_flags & IO_URING_F_MULTISHOT)
io_kbuf_recycle(req, issue_flags);
- return IOU_ISSUE_SKIP_COMPLETE;
- }
- return -EAGAIN;
+ return IOU_RETRY;
}
if (ret > 0 && io_net_retry(sock, flags)) {
sr->len -= ret;
@@ -1212,6 +1215,73 @@ out_free:
return ret;
}
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+ unsigned ifq_idx;
+
+ if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr ||
+ sqe->addr3))
+ return -EINVAL;
+
+ ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx);
+ if (ifq_idx != 0)
+ return -EINVAL;
+ zc->ifq = req->ctx->ifq;
+ if (!zc->ifq)
+ return -EINVAL;
+ zc->len = READ_ONCE(sqe->len);
+ zc->flags = READ_ONCE(sqe->ioprio);
+ zc->msg_flags = READ_ONCE(sqe->msg_flags);
+ if (zc->msg_flags)
+ return -EINVAL;
+ if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT))
+ return -EINVAL;
+ /* multishot required */
+ if (!(zc->flags & IORING_RECV_MULTISHOT))
+ return -EINVAL;
+ /* All data completions are posted as aux CQEs. */
+ req->flags |= REQ_F_APOLL_MULTISHOT;
+
+ return 0;
+}
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+ struct socket *sock;
+ unsigned int len;
+ int ret;
+
+ if (!(req->flags & REQ_F_POLLED) &&
+ (zc->flags & IORING_RECVSEND_POLL_FIRST))
+ return -EAGAIN;
+
+ sock = sock_from_file(req->file);
+ if (unlikely(!sock))
+ return -ENOTSOCK;
+
+ len = zc->len;
+ ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT,
+ issue_flags, &zc->len);
+ if (len && zc->len == 0) {
+ io_req_set_res(req, 0, 0);
+
+ return IOU_COMPLETE;
+ }
+ if (unlikely(ret <= 0) && ret != -EAGAIN) {
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
+ if (ret == IOU_REQUEUE)
+ return IOU_REQUEUE;
+
+ req_set_fail(req);
+ io_req_set_res(req, ret, 0);
+ return IOU_COMPLETE;
+ }
+ return IOU_RETRY;
+}
+
void io_send_zc_cleanup(struct io_kiocb *req)
{
struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
@@ -1235,6 +1305,7 @@ 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 = false;
req->flags |= REQ_F_POLL_NO_LAZY;
if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)))
@@ -1267,25 +1338,24 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (req->opcode != IORING_OP_SEND_ZC) {
if (unlikely(sqe->addr2 || sqe->file_index))
return -EINVAL;
- if (unlikely(zc->flags & IORING_RECVSEND_FIXED_BUF))
- return -EINVAL;
}
zc->len = READ_ONCE(sqe->len);
zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL | MSG_ZEROCOPY;
- zc->buf_index = READ_ONCE(sqe->buf_index);
+ req->buf_index = READ_ONCE(sqe->buf_index);
if (zc->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
+ if (io_is_compat(req->ctx))
zc->msg_flags |= MSG_CMSG_COMPAT;
-#endif
+
if (unlikely(!io_msg_alloc_async(req)))
return -ENOMEM;
- if (req->opcode != IORING_OP_SENDMSG_ZC)
+ if (req->opcode == IORING_OP_SEND_ZC) {
+ req->flags |= REQ_F_IMPORT_BUFFER;
return io_send_setup(req, sqe);
- return io_sendmsg_setup(req, sqe);
+ }
+ return io_sendmsg_zc_setup(req, sqe);
}
static int io_sg_from_iter_iovec(struct sk_buff *skb,
@@ -1345,24 +1415,10 @@ static int io_send_zc_import(struct io_kiocb *req, unsigned int issue_flags)
int ret;
if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_rsrc_node *node;
-
- ret = -EFAULT;
- io_ring_submit_lock(ctx, issue_flags);
- node = io_rsrc_node_lookup(&ctx->buf_table, sr->buf_index);
- if (node) {
- io_req_assign_buf_node(sr->notif, node);
- ret = 0;
- }
- io_ring_submit_unlock(ctx, issue_flags);
-
- if (unlikely(ret))
- return ret;
-
- ret = io_import_fixed(ITER_SOURCE, &kmsg->msg.msg_iter,
- node->buf, (u64)(uintptr_t)sr->buf,
- sr->len);
+ sr->notif->buf_index = req->buf_index;
+ ret = io_import_reg_buf(sr->notif, &kmsg->msg.msg_iter,
+ (u64)(uintptr_t)sr->buf, sr->len,
+ ITER_SOURCE, issue_flags);
if (unlikely(ret))
return ret;
kmsg->msg.sg_from_iter = io_sg_from_iter;
@@ -1397,7 +1453,8 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
(zc->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
- if (!zc->done_io) {
+ if (req->flags & REQ_F_IMPORT_BUFFER) {
+ req->flags &= ~REQ_F_IMPORT_BUFFER;
ret = io_send_zc_import(req, issue_flags);
if (unlikely(ret))
return ret;
@@ -1441,6 +1498,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
*/
if (!(issue_flags & IO_URING_F_UNLOCKED)) {
io_notif_flush(zc->notif);
+ zc->notif = NULL;
io_req_msg_cleanup(req, 0);
}
io_req_set_res(req, ret, IORING_CQE_F_MORE);
@@ -1455,6 +1513,20 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
unsigned flags;
int ret, min_ret = 0;
+ kmsg->msg.sg_from_iter = io_sg_from_iter_iovec;
+
+ if (req->flags & REQ_F_IMPORT_BUFFER) {
+ unsigned uvec_segs = kmsg->msg.msg_iter.nr_segs;
+ int ret;
+
+ ret = io_import_reg_vec(ITER_SOURCE, &kmsg->msg.msg_iter, req,
+ &kmsg->vec, uvec_segs, issue_flags);
+ if (unlikely(ret))
+ return ret;
+ kmsg->msg.sg_from_iter = io_sg_from_iter;
+ req->flags &= ~REQ_F_IMPORT_BUFFER;
+ }
+
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
@@ -1473,7 +1545,6 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
kmsg->msg.msg_control_user = sr->msg_control;
kmsg->msg.msg_ubuf = &io_notif_to_data(sr->notif)->uarg;
- kmsg->msg.sg_from_iter = io_sg_from_iter_iovec;
ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
if (unlikely(ret < min_ret)) {
@@ -1501,6 +1572,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
*/
if (!(issue_flags & IO_URING_F_UNLOCKED)) {
io_notif_flush(sr->notif);
+ sr->notif = NULL;
io_req_msg_cleanup(req, 0);
}
io_req_set_res(req, ret, IORING_CQE_F_MORE);
@@ -1587,19 +1659,11 @@ retry:
put_unused_fd(fd);
ret = PTR_ERR(file);
if (ret == -EAGAIN && force_nonblock &&
- !(accept->iou_flags & IORING_ACCEPT_DONTWAIT)) {
- /*
- * if it's multishot and polled, we don't need to
- * return EAGAIN to arm the poll infra since it
- * has already been done
- */
- if (issue_flags & IO_URING_F_MULTISHOT)
- return IOU_ISSUE_SKIP_COMPLETE;
- return ret;
- }
+ !(accept->iou_flags & IORING_ACCEPT_DONTWAIT))
+ return IOU_RETRY;
+
if (ret == -ERESTARTSYS)
ret = -EINTR;
- req_set_fail(req);
} else if (!fixed) {
fd_install(fd, file);
ret = fd;
@@ -1612,23 +1676,17 @@ retry:
if (!arg.is_empty)
cflags |= IORING_CQE_F_SOCK_NONEMPTY;
- if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
- io_req_set_res(req, ret, cflags);
- return IOU_OK;
- }
-
- if (ret < 0)
- return ret;
- if (io_req_post_cqe(req, ret, cflags | IORING_CQE_F_MORE)) {
+ if (ret >= 0 && (req->flags & REQ_F_APOLL_MULTISHOT) &&
+ io_req_post_cqe(req, ret, cflags | IORING_CQE_F_MORE)) {
if (cflags & IORING_CQE_F_SOCK_NONEMPTY || arg.is_empty == -1)
goto retry;
- if (issue_flags & IO_URING_F_MULTISHOT)
- return IOU_ISSUE_SKIP_COMPLETE;
- return -EAGAIN;
+ return IOU_RETRY;
}
io_req_set_res(req, ret, cflags);
- return IOU_STOP_MULTISHOT;
+ if (ret < 0)
+ req_set_fail(req);
+ return IOU_COMPLETE;
}
int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -1820,8 +1878,7 @@ void io_netmsg_cache_free(const void *entry)
{
struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry;
- if (kmsg->free_iov)
- io_netmsg_iovec_free(kmsg);
+ io_vec_free(&kmsg->vec);
kfree(kmsg);
}
#endif
diff --git a/io_uring/net.h b/io_uring/net.h
index b804c2b36e60..43e5ce5416b7 100644
--- a/io_uring/net.h
+++ b/io_uring/net.h
@@ -2,12 +2,12 @@
#include <linux/net.h>
#include <linux/uio.h>
+#include <linux/io_uring_types.h>
struct io_async_msghdr {
#if defined(CONFIG_NET)
- struct iovec *free_iov;
- /* points to an allocated iov, if NULL we use fast_iov instead */
- int free_iov_nr;
+ struct iou_vec vec;
+
struct_group(clear,
int namelen;
struct iovec fast_iov;
diff --git a/io_uring/nop.c b/io_uring/nop.c
index 5e5196df650a..28f06285fdc2 100644
--- a/io_uring/nop.c
+++ b/io_uring/nop.c
@@ -16,7 +16,6 @@ struct io_nop {
struct file *file;
int result;
int fd;
- int buffer;
unsigned int flags;
};
@@ -40,9 +39,7 @@ int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
else
nop->fd = -1;
if (nop->flags & IORING_NOP_FIXED_BUFFER)
- nop->buffer = READ_ONCE(sqe->buf_index);
- else
- nop->buffer = -1;
+ req->buf_index = READ_ONCE(sqe->buf_index);
return 0;
}
@@ -64,17 +61,8 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags)
}
}
if (nop->flags & IORING_NOP_FIXED_BUFFER) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_rsrc_node *node;
-
- ret = -EFAULT;
- io_ring_submit_lock(ctx, issue_flags);
- node = io_rsrc_node_lookup(&ctx->buf_table, nop->buffer);
- if (node) {
- io_req_assign_buf_node(req, node);
- ret = 0;
- }
- io_ring_submit_unlock(ctx, issue_flags);
+ if (!io_find_buf_node(req, issue_flags))
+ ret = -EFAULT;
}
done:
if (ret < 0)
diff --git a/io_uring/notif.c b/io_uring/notif.c
index ee3a33510b3c..7bd92538dccb 100644
--- a/io_uring/notif.c
+++ b/io_uring/notif.c
@@ -11,7 +11,7 @@
static const struct ubuf_info_ops io_ubuf_ops;
-static void io_notif_tw_complete(struct io_kiocb *notif, struct io_tw_state *ts)
+static void io_notif_tw_complete(struct io_kiocb *notif, io_tw_token_t tw)
{
struct io_notif_data *nd = io_notif_to_data(notif);
@@ -29,7 +29,7 @@ static void io_notif_tw_complete(struct io_kiocb *notif, struct io_tw_state *ts)
}
nd = nd->next;
- io_req_task_complete(notif, ts);
+ io_req_task_complete(notif, tw);
} while (nd);
}
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index e8baef4e5146..489384c0438b 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -37,6 +37,7 @@
#include "waitid.h"
#include "futex.h"
#include "truncate.h"
+#include "zcrx.h"
static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
{
@@ -104,7 +105,7 @@ const struct io_issue_def io_issue_defs[] = {
.iopoll_queue = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_read_fixed,
- .issue = io_read,
+ .issue = io_read_fixed,
},
[IORING_OP_WRITE_FIXED] = {
.needs_file = 1,
@@ -118,7 +119,7 @@ const struct io_issue_def io_issue_defs[] = {
.iopoll_queue = 1,
.async_size = sizeof(struct io_async_rw),
.prep = io_prep_write_fixed,
- .issue = io_write,
+ .issue = io_write_fixed,
},
[IORING_OP_POLL_ADD] = {
.needs_file = 1,
@@ -415,7 +416,7 @@ const struct io_issue_def io_issue_defs[] = {
.plug = 1,
.iopoll = 1,
.iopoll_queue = 1,
- .async_size = sizeof(struct io_uring_cmd_data),
+ .async_size = sizeof(struct io_async_cmd),
.prep = io_uring_cmd_prep,
.issue = io_uring_cmd,
},
@@ -516,6 +517,58 @@ const struct io_issue_def io_issue_defs[] = {
.prep = io_eopnotsupp_prep,
#endif
},
+ [IORING_OP_RECV_ZC] = {
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ .pollin = 1,
+ .ioprio = 1,
+#if defined(CONFIG_NET)
+ .prep = io_recvzc_prep,
+ .issue = io_recvzc,
+#else
+ .prep = io_eopnotsupp_prep,
+#endif
+ },
+ [IORING_OP_EPOLL_WAIT] = {
+ .needs_file = 1,
+ .audit_skip = 1,
+ .pollin = 1,
+#if defined(CONFIG_EPOLL)
+ .prep = io_epoll_wait_prep,
+ .issue = io_epoll_wait,
+#else
+ .prep = io_eopnotsupp_prep,
+#endif
+ },
+ [IORING_OP_READV_FIXED] = {
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ .pollin = 1,
+ .plug = 1,
+ .audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
+ .iopoll_queue = 1,
+ .vectored = 1,
+ .async_size = sizeof(struct io_async_rw),
+ .prep = io_prep_readv_fixed,
+ .issue = io_read,
+ },
+ [IORING_OP_WRITEV_FIXED] = {
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ .pollout = 1,
+ .plug = 1,
+ .audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
+ .iopoll_queue = 1,
+ .vectored = 1,
+ .async_size = sizeof(struct io_async_rw),
+ .prep = io_prep_writev_fixed,
+ .issue = io_write,
+ },
};
const struct io_cold_def io_cold_defs[] = {
@@ -702,6 +755,7 @@ const struct io_cold_def io_cold_defs[] = {
},
[IORING_OP_URING_CMD] = {
.name = "URING_CMD",
+ .cleanup = io_uring_cmd_cleanup,
},
[IORING_OP_SEND_ZC] = {
.name = "SEND_ZC",
@@ -745,6 +799,22 @@ const struct io_cold_def io_cold_defs[] = {
[IORING_OP_LISTEN] = {
.name = "LISTEN",
},
+ [IORING_OP_RECV_ZC] = {
+ .name = "RECV_ZC",
+ },
+ [IORING_OP_EPOLL_WAIT] = {
+ .name = "EPOLL_WAIT",
+ },
+ [IORING_OP_READV_FIXED] = {
+ .name = "READV_FIXED",
+ .cleanup = io_readv_writev_cleanup,
+ .fail = io_rw_fail,
+ },
+ [IORING_OP_WRITEV_FIXED] = {
+ .name = "WRITEV_FIXED",
+ .cleanup = io_readv_writev_cleanup,
+ .fail = io_rw_fail,
+ },
};
const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/opdef.h b/io_uring/opdef.h
index 14456436ff74..719a52104abe 100644
--- a/io_uring/opdef.h
+++ b/io_uring/opdef.h
@@ -7,6 +7,12 @@ struct io_issue_def {
unsigned needs_file : 1;
/* should block plug */
unsigned plug : 1;
+ /* supports ioprio */
+ unsigned ioprio : 1;
+ /* supports iopoll */
+ unsigned iopoll : 1;
+ /* op supports buffer selection */
+ unsigned buffer_select : 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 */
@@ -15,14 +21,8 @@ struct io_issue_def {
unsigned pollin : 1;
unsigned pollout : 1;
unsigned poll_exclusive : 1;
- /* op supports buffer selection */
- unsigned buffer_select : 1;
/* skip auditing */
unsigned audit_skip : 1;
- /* supports ioprio */
- unsigned ioprio : 1;
- /* supports iopoll */
- unsigned iopoll : 1;
/* have to be put into the iopoll list */
unsigned iopoll_queue : 1;
/* vectored opcode, set if 1) vectored, and 2) handler needs to know */
diff --git a/io_uring/poll.c b/io_uring/poll.c
index bb1c0cd4f809..8eb744eb9f4c 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -220,7 +220,7 @@ static inline void io_poll_execute(struct io_kiocb *req, int res)
* req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
* poll and that the result is stored in req->cqe.
*/
-static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
+static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
{
int v;
@@ -288,12 +288,13 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
return IOU_POLL_REMOVE_POLL_USE_RES;
}
} else {
- int ret = io_poll_issue(req, ts);
- if (ret == IOU_STOP_MULTISHOT)
+ int ret = io_poll_issue(req, tw);
+
+ if (ret == IOU_COMPLETE)
return IOU_POLL_REMOVE_POLL_USE_RES;
else if (ret == IOU_REQUEUE)
return IOU_POLL_REQUEUE;
- if (ret < 0)
+ if (ret != IOU_RETRY && ret < 0)
return ret;
}
@@ -311,11 +312,11 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
return IOU_POLL_NO_ACTION;
}
-void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
+void io_poll_task_func(struct io_kiocb *req, io_tw_token_t tw)
{
int ret;
- ret = io_poll_check_events(req, ts);
+ ret = io_poll_check_events(req, tw);
if (ret == IOU_POLL_NO_ACTION) {
io_kbuf_recycle(req, 0);
return;
@@ -335,7 +336,7 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
poll = io_kiocb_to_cmd(req, struct io_poll);
req->cqe.res = mangle_poll(req->cqe.res & poll->events);
} else if (ret == IOU_POLL_REISSUE) {
- io_req_task_submit(req, ts);
+ io_req_task_submit(req, tw);
return;
} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
req->cqe.res = ret;
@@ -343,14 +344,14 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
}
io_req_set_res(req, req->cqe.res, 0);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
} else {
- io_tw_lock(req->ctx, ts);
+ io_tw_lock(req->ctx, tw);
if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
- io_req_task_submit(req, ts);
+ io_req_task_submit(req, tw);
else
io_req_defer_failed(req, ret);
}
diff --git a/io_uring/poll.h b/io_uring/poll.h
index 04ede93113dc..27e2db2ed4ae 100644
--- a/io_uring/poll.h
+++ b/io_uring/poll.h
@@ -1,5 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/io_uring_types.h>
+
#define IO_POLL_ALLOC_CACHE_MAX 32
enum {
@@ -43,4 +45,4 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags);
bool io_poll_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
bool cancel_all);
-void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts);
+void io_poll_task_func(struct io_kiocb *req, io_tw_token_t tw);
diff --git a/io_uring/register.c b/io_uring/register.c
index 9a4d2fbce4ae..cc23a4c205cd 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -30,6 +30,7 @@
#include "eventfd.h"
#include "msg_ring.h"
#include "memmap.h"
+#include "zcrx.h"
#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \
IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -813,6 +814,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
break;
ret = io_register_clone_buffers(ctx, arg);
break;
+ case IORING_REGISTER_ZCRX_IFQ:
+ ret = -EINVAL;
+ if (!arg || nr_args != 1)
+ break;
+ ret = io_register_zcrx_ifq(ctx, arg);
+ break;
case IORING_REGISTER_RESIZE_RINGS:
ret = -EINVAL;
if (!arg || nr_args != 1)
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index af39b69eb4fd..3f195e24777e 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -9,6 +9,7 @@
#include <linux/hugetlb.h>
#include <linux/compat.h>
#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
#include <uapi/linux/io_uring.h>
@@ -32,6 +33,8 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
#define IORING_MAX_FIXED_FILES (1U << 20)
#define IORING_MAX_REG_BUFFERS (1U << 14)
+#define IO_CACHED_BVECS_SEGS 32
+
int __io_account_mem(struct user_struct *user, unsigned long nr_pages)
{
unsigned long page_limit, cur_pages, new_pages;
@@ -77,7 +80,7 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
return 0;
}
-static int io_buffer_validate(struct iovec *iov)
+int io_buffer_validate(struct iovec *iov)
{
unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);
@@ -101,36 +104,79 @@ static int io_buffer_validate(struct iovec *iov)
return 0;
}
-static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
+static void io_release_ubuf(void *priv)
{
+ struct io_mapped_ubuf *imu = priv;
unsigned int i;
- if (node->buf) {
- struct io_mapped_ubuf *imu = node->buf;
+ for (i = 0; i < imu->nr_bvecs; i++)
+ unpin_user_page(imu->bvec[i].bv_page);
+}
+
+static struct io_mapped_ubuf *io_alloc_imu(struct io_ring_ctx *ctx,
+ int nr_bvecs)
+{
+ if (nr_bvecs <= IO_CACHED_BVECS_SEGS)
+ return io_cache_alloc(&ctx->imu_cache, GFP_KERNEL);
+ return kvmalloc(struct_size_t(struct io_mapped_ubuf, bvec, nr_bvecs),
+ GFP_KERNEL);
+}
- if (!refcount_dec_and_test(&imu->refs))
- return;
- for (i = 0; i < imu->nr_bvecs; i++)
- unpin_user_page(imu->bvec[i].bv_page);
- if (imu->acct_pages)
- io_unaccount_mem(ctx, imu->acct_pages);
+static void io_free_imu(struct io_ring_ctx *ctx, struct io_mapped_ubuf *imu)
+{
+ if (imu->nr_bvecs <= IO_CACHED_BVECS_SEGS)
+ io_cache_free(&ctx->imu_cache, imu);
+ else
kvfree(imu);
- }
}
-struct io_rsrc_node *io_rsrc_node_alloc(int type)
+static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf *imu)
+{
+ if (!refcount_dec_and_test(&imu->refs))
+ return;
+
+ if (imu->acct_pages)
+ io_unaccount_mem(ctx, imu->acct_pages);
+ imu->release(imu->priv);
+ io_free_imu(ctx, imu);
+}
+
+struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type)
{
struct io_rsrc_node *node;
- node = kzalloc(sizeof(*node), GFP_KERNEL);
+ node = io_cache_alloc(&ctx->node_cache, GFP_KERNEL);
if (node) {
node->type = type;
node->refs = 1;
+ node->tag = 0;
+ node->file_ptr = 0;
}
return node;
}
-__cold void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data)
+bool io_rsrc_cache_init(struct io_ring_ctx *ctx)
+{
+ const int imu_cache_size = struct_size_t(struct io_mapped_ubuf, bvec,
+ IO_CACHED_BVECS_SEGS);
+ const int node_size = sizeof(struct io_rsrc_node);
+ bool ret;
+
+ ret = io_alloc_cache_init(&ctx->node_cache, IO_ALLOC_CACHE_MAX,
+ node_size, 0);
+ ret |= io_alloc_cache_init(&ctx->imu_cache, IO_ALLOC_CACHE_MAX,
+ imu_cache_size, 0);
+ return ret;
+}
+
+void io_rsrc_cache_free(struct io_ring_ctx *ctx)
+{
+ io_alloc_cache_free(&ctx->node_cache, kfree);
+ io_alloc_cache_free(&ctx->imu_cache, kfree);
+}
+
+__cold void io_rsrc_data_free(struct io_ring_ctx *ctx,
+ struct io_rsrc_data *data)
{
if (!data->nr)
return;
@@ -203,7 +249,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
err = -EBADF;
break;
}
- node = io_rsrc_node_alloc(IORING_RSRC_FILE);
+ node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
if (!node) {
err = -ENOMEM;
fput(file);
@@ -449,19 +495,17 @@ void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
switch (node->type) {
case IORING_RSRC_FILE:
- if (io_slot_file(node))
- fput(io_slot_file(node));
+ fput(io_slot_file(node));
break;
case IORING_RSRC_BUFFER:
- if (node->buf)
- io_buffer_unmap(ctx, node);
+ io_buffer_unmap(ctx, node->buf);
break;
default:
WARN_ON_ONCE(1);
break;
}
- kfree(node);
+ io_cache_free(&ctx->node_cache, node);
}
int io_sqe_files_unregister(struct io_ring_ctx *ctx)
@@ -523,7 +567,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
goto fail;
}
ret = -ENOMEM;
- node = io_rsrc_node_alloc(IORING_RSRC_FILE);
+ node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
if (!node) {
fput(file);
goto fail;
@@ -728,10 +772,9 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
if (!iov->iov_base)
return NULL;
- node = io_rsrc_node_alloc(IORING_RSRC_BUFFER);
+ node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
if (!node)
return ERR_PTR(-ENOMEM);
- node->buf = NULL;
ret = -ENOMEM;
pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len,
@@ -748,10 +791,11 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
coalesced = io_coalesce_buffer(&pages, &nr_pages, &data);
}
- imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
+ imu = io_alloc_imu(ctx, nr_pages);
if (!imu)
goto done;
+ imu->nr_bvecs = nr_pages;
ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage);
if (ret) {
unpin_user_pages(pages, nr_pages);
@@ -762,8 +806,11 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
/* store original address for later verification */
imu->ubuf = (unsigned long) iov->iov_base;
imu->len = iov->iov_len;
- imu->nr_bvecs = nr_pages;
imu->folio_shift = PAGE_SHIFT;
+ imu->release = io_release_ubuf;
+ imu->priv = imu;
+ imu->is_kbuf = false;
+ imu->dir = IO_IMU_DEST | IO_IMU_SOURCE;
if (coalesced)
imu->folio_shift = data.folio_shift;
refcount_set(&imu->refs, 1);
@@ -781,9 +828,9 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
}
done:
if (ret) {
- kvfree(imu);
- if (node)
- io_put_rsrc_node(ctx, node);
+ if (imu)
+ io_free_imu(ctx, imu);
+ io_cache_free(&ctx->node_cache, node);
node = ERR_PTR(ret);
}
kvfree(pages);
@@ -860,7 +907,102 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
return ret;
}
-int io_import_fixed(int ddir, struct iov_iter *iter,
+int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
+ void (*release)(void *), unsigned int index,
+ unsigned int issue_flags)
+{
+ struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+ struct io_rsrc_data *data = &ctx->buf_table;
+ struct req_iterator rq_iter;
+ struct io_mapped_ubuf *imu;
+ struct io_rsrc_node *node;
+ struct bio_vec bv, *bvec;
+ u16 nr_bvecs;
+ int ret = 0;
+
+ io_ring_submit_lock(ctx, issue_flags);
+ if (index >= data->nr) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+ index = array_index_nospec(index, data->nr);
+
+ if (data->nodes[index]) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
+ if (!node) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
+
+ nr_bvecs = blk_rq_nr_phys_segments(rq);
+ imu = io_alloc_imu(ctx, nr_bvecs);
+ if (!imu) {
+ kfree(node);
+ ret = -ENOMEM;
+ goto unlock;
+ }
+
+ imu->ubuf = 0;
+ imu->len = blk_rq_bytes(rq);
+ imu->acct_pages = 0;
+ imu->folio_shift = PAGE_SHIFT;
+ imu->nr_bvecs = nr_bvecs;
+ refcount_set(&imu->refs, 1);
+ imu->release = release;
+ imu->priv = rq;
+ imu->is_kbuf = true;
+ imu->dir = 1 << rq_data_dir(rq);
+
+ bvec = imu->bvec;
+ rq_for_each_bvec(bv, rq, rq_iter)
+ *bvec++ = bv;
+
+ node->buf = imu;
+ data->nodes[index] = node;
+unlock:
+ io_ring_submit_unlock(ctx, issue_flags);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(io_buffer_register_bvec);
+
+int io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
+ unsigned int issue_flags)
+{
+ struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+ struct io_rsrc_data *data = &ctx->buf_table;
+ struct io_rsrc_node *node;
+ int ret = 0;
+
+ io_ring_submit_lock(ctx, issue_flags);
+ if (index >= data->nr) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+ index = array_index_nospec(index, data->nr);
+
+ node = data->nodes[index];
+ if (!node) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+ if (!node->buf->is_kbuf) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ io_put_rsrc_node(ctx, node);
+ data->nodes[index] = NULL;
+unlock:
+ io_ring_submit_unlock(ctx, issue_flags);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(io_buffer_unregister_bvec);
+
+static int io_import_fixed(int ddir, struct iov_iter *iter,
struct io_mapped_ubuf *imu,
u64 buf_addr, size_t len)
{
@@ -874,20 +1016,22 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
/* not inside the mapped region */
if (unlikely(buf_addr < imu->ubuf || buf_end > (imu->ubuf + imu->len)))
return -EFAULT;
+ if (!(imu->dir & (1 << ddir)))
+ return -EFAULT;
/*
* Might not be a start of buffer, set size appropriately
* and advance us to the beginning.
*/
offset = buf_addr - imu->ubuf;
- iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, len);
+ iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len);
if (offset) {
/*
* Don't use iov_iter_advance() here, as it's really slow for
* using the latter parts of a big fixed buffer - it iterates
- * over each segment manually. We can cheat a bit here, because
- * we know that:
+ * over each segment manually. We can cheat a bit here for user
+ * registered nodes, because we know that:
*
* 1) it's a BVEC iter, we set it up
* 2) all bvecs are the same in size, except potentially the
@@ -901,8 +1045,16 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
*/
const struct bio_vec *bvec = imu->bvec;
+ /*
+ * Kernel buffer bvecs, on the other hand, don't necessarily
+ * have the size property of user registered ones, so we have
+ * to use the slow iter advance.
+ */
if (offset < bvec->bv_len) {
+ iter->count -= offset;
iter->iov_offset = offset;
+ } else if (imu->is_kbuf) {
+ iov_iter_advance(iter, offset);
} else {
unsigned long seg_skip;
@@ -912,6 +1064,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
iter->bvec += seg_skip;
iter->nr_segs -= seg_skip;
+ iter->count -= bvec->bv_len + offset;
iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
}
}
@@ -919,6 +1072,35 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
return 0;
}
+inline struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
+ unsigned issue_flags)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_rsrc_node *node;
+
+ if (req->flags & REQ_F_BUF_NODE)
+ return req->buf_node;
+
+ io_ring_submit_lock(ctx, issue_flags);
+ node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index);
+ if (node)
+ io_req_assign_buf_node(req, node);
+ io_ring_submit_unlock(ctx, issue_flags);
+ return node;
+}
+
+int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
+ u64 buf_addr, size_t len, int ddir,
+ unsigned issue_flags)
+{
+ struct io_rsrc_node *node;
+
+ node = io_find_buf_node(req, issue_flags);
+ if (!node)
+ return -EFAULT;
+ return io_import_fixed(ddir, iter, node->buf, buf_addr, len);
+}
+
/* Lock two rings at once. The rings must be different! */
static void lock_two_rings(struct io_ring_ctx *ctx1, struct io_ring_ctx *ctx2)
{
@@ -1002,7 +1184,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
if (!src_node) {
dst_node = NULL;
} else {
- dst_node = io_rsrc_node_alloc(IORING_RSRC_BUFFER);
+ dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
if (!dst_node) {
ret = -ENOMEM;
goto out_free;
@@ -1080,3 +1262,166 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
fput(file);
return ret;
}
+
+void io_vec_free(struct iou_vec *iv)
+{
+ if (!iv->iovec)
+ return;
+ kfree(iv->iovec);
+ iv->iovec = NULL;
+ iv->nr = 0;
+}
+
+int io_vec_realloc(struct iou_vec *iv, unsigned nr_entries)
+{
+ gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
+ struct iovec *iov;
+
+ iov = kmalloc_array(nr_entries, sizeof(iov[0]), gfp);
+ if (!iov)
+ return -ENOMEM;
+
+ io_vec_free(iv);
+ iv->iovec = iov;
+ iv->nr = nr_entries;
+ return 0;
+}
+
+static int io_vec_fill_bvec(int ddir, struct iov_iter *iter,
+ struct io_mapped_ubuf *imu,
+ struct iovec *iovec, unsigned nr_iovs,
+ struct iou_vec *vec)
+{
+ unsigned long folio_size = 1 << imu->folio_shift;
+ unsigned long folio_mask = folio_size - 1;
+ u64 folio_addr = imu->ubuf & ~folio_mask;
+ struct bio_vec *res_bvec = vec->bvec;
+ size_t total_len = 0;
+ unsigned bvec_idx = 0;
+ unsigned iov_idx;
+
+ for (iov_idx = 0; iov_idx < nr_iovs; iov_idx++) {
+ size_t iov_len = iovec[iov_idx].iov_len;
+ u64 buf_addr = (u64)(uintptr_t)iovec[iov_idx].iov_base;
+ struct bio_vec *src_bvec;
+ size_t offset;
+ u64 buf_end;
+
+ if (unlikely(check_add_overflow(buf_addr, (u64)iov_len, &buf_end)))
+ return -EFAULT;
+ if (unlikely(buf_addr < imu->ubuf || buf_end > (imu->ubuf + imu->len)))
+ return -EFAULT;
+ if (unlikely(!iov_len))
+ return -EFAULT;
+ if (unlikely(check_add_overflow(total_len, iov_len, &total_len)))
+ return -EOVERFLOW;
+
+ /* by using folio address it also accounts for bvec offset */
+ offset = buf_addr - folio_addr;
+ src_bvec = imu->bvec + (offset >> imu->folio_shift);
+ offset &= folio_mask;
+
+ for (; iov_len; offset = 0, bvec_idx++, src_bvec++) {
+ size_t seg_size = min_t(size_t, iov_len,
+ folio_size - offset);
+
+ bvec_set_page(&res_bvec[bvec_idx],
+ src_bvec->bv_page, seg_size, offset);
+ iov_len -= seg_size;
+ }
+ }
+ if (total_len > MAX_RW_COUNT)
+ return -EINVAL;
+
+ iov_iter_bvec(iter, ddir, res_bvec, bvec_idx, total_len);
+ return 0;
+}
+
+static int io_estimate_bvec_size(struct iovec *iov, unsigned nr_iovs,
+ struct io_mapped_ubuf *imu)
+{
+ unsigned shift = imu->folio_shift;
+ size_t max_segs = 0;
+ unsigned i;
+
+ for (i = 0; i < nr_iovs; i++)
+ max_segs += (iov[i].iov_len >> shift) + 2;
+ return max_segs;
+}
+
+int io_import_reg_vec(int ddir, struct iov_iter *iter,
+ struct io_kiocb *req, struct iou_vec *vec,
+ unsigned nr_iovs, unsigned issue_flags)
+{
+ struct io_rsrc_node *node;
+ struct io_mapped_ubuf *imu;
+ unsigned iovec_off;
+ struct iovec *iov;
+ unsigned nr_segs;
+
+ node = io_find_buf_node(req, issue_flags);
+ if (!node)
+ return -EFAULT;
+ imu = node->buf;
+ if (imu->is_kbuf)
+ return -EOPNOTSUPP;
+ if (!(imu->dir & (1 << ddir)))
+ return -EFAULT;
+
+ iovec_off = vec->nr - nr_iovs;
+ iov = vec->iovec + iovec_off;
+ nr_segs = io_estimate_bvec_size(iov, nr_iovs, imu);
+
+ if (sizeof(struct bio_vec) > sizeof(struct iovec)) {
+ size_t bvec_bytes;
+
+ bvec_bytes = nr_segs * sizeof(struct bio_vec);
+ nr_segs = (bvec_bytes + sizeof(*iov) - 1) / sizeof(*iov);
+ nr_segs += nr_iovs;
+ }
+
+ if (nr_segs > vec->nr) {
+ struct iou_vec tmp_vec = {};
+ int ret;
+
+ ret = io_vec_realloc(&tmp_vec, nr_segs);
+ if (ret)
+ return ret;
+
+ iovec_off = tmp_vec.nr - nr_iovs;
+ memcpy(tmp_vec.iovec + iovec_off, iov, sizeof(*iov) * nr_iovs);
+ io_vec_free(vec);
+
+ *vec = tmp_vec;
+ iov = vec->iovec + iovec_off;
+ req->flags |= REQ_F_NEED_CLEANUP;
+ }
+
+ return io_vec_fill_bvec(ddir, iter, imu, iov, nr_iovs, vec);
+}
+
+int io_prep_reg_iovec(struct io_kiocb *req, struct iou_vec *iv,
+ const struct iovec __user *uvec, size_t uvec_segs)
+{
+ struct iovec *iov;
+ int iovec_off, ret;
+ void *res;
+
+ if (uvec_segs > iv->nr) {
+ ret = io_vec_realloc(iv, uvec_segs);
+ if (ret)
+ return ret;
+ req->flags |= REQ_F_NEED_CLEANUP;
+ }
+
+ /* pad iovec to the right */
+ iovec_off = iv->nr - uvec_segs;
+ iov = iv->iovec + iovec_off;
+ res = iovec_from_user(uvec, uvec_segs, uvec_segs, iov,
+ io_is_compat(req->ctx));
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ req->flags |= REQ_F_IMPORT_BUFFER;
+ return 0;
+}
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 89ea0135a1a0..b52242852ff3 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -2,8 +2,11 @@
#ifndef IOU_RSRC_H
#define IOU_RSRC_H
+#include <linux/io_uring_types.h>
#include <linux/lockdep.h>
+#define IO_VEC_CACHE_SOFT_CAP 256
+
enum {
IORING_RSRC_FILE = 0,
IORING_RSRC_BUFFER = 1,
@@ -20,6 +23,11 @@ struct io_rsrc_node {
};
};
+enum {
+ IO_IMU_DEST = 1 << ITER_DEST,
+ IO_IMU_SOURCE = 1 << ITER_SOURCE,
+};
+
struct io_mapped_ubuf {
u64 ubuf;
unsigned int len;
@@ -27,6 +35,10 @@ struct io_mapped_ubuf {
unsigned int folio_shift;
refcount_t refs;
unsigned long acct_pages;
+ void (*release)(void *);
+ void *priv;
+ bool is_kbuf;
+ u8 dir;
struct bio_vec bvec[] __counted_by(nr_bvecs);
};
@@ -39,14 +51,23 @@ struct io_imu_folio_data {
unsigned int nr_folios;
};
-struct io_rsrc_node *io_rsrc_node_alloc(int type);
+bool io_rsrc_cache_init(struct io_ring_ctx *ctx);
+void io_rsrc_cache_free(struct io_ring_ctx *ctx);
+struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type);
void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node);
void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data);
int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr);
-int io_import_fixed(int ddir, struct iov_iter *iter,
- struct io_mapped_ubuf *imu,
- u64 buf_addr, size_t len);
+struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
+ unsigned issue_flags);
+int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
+ u64 buf_addr, size_t len, int ddir,
+ unsigned issue_flags);
+int io_import_reg_vec(int ddir, struct iov_iter *iter,
+ struct io_kiocb *req, struct iou_vec *vec,
+ unsigned nr_iovs, unsigned issue_flags);
+int io_prep_reg_iovec(struct io_kiocb *req, struct iou_vec *iv,
+ const struct iovec __user *uvec, size_t uvec_segs);
int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg);
int io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
@@ -62,6 +83,7 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
unsigned size, unsigned type);
int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
unsigned int size, unsigned int type);
+int io_buffer_validate(struct iovec *iov);
bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
struct io_imu_folio_data *data);
@@ -77,7 +99,7 @@ static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data
static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
{
lockdep_assert_held(&ctx->uring_lock);
- if (node && !--node->refs)
+ if (!--node->refs)
io_free_rsrc_node(ctx, node);
}
@@ -130,4 +152,21 @@ static inline void __io_unaccount_mem(struct user_struct *user,
atomic_long_sub(nr_pages, &user->locked_vm);
}
+void io_vec_free(struct iou_vec *iv);
+int io_vec_realloc(struct iou_vec *iv, unsigned nr_entries);
+
+static inline void io_vec_reset_iovec(struct iou_vec *iv,
+ struct iovec *iovec, unsigned nr)
+{
+ io_vec_free(iv);
+ iv->iovec = iovec;
+ iv->nr = nr;
+}
+
+static inline void io_alloc_cache_vec_kasan(struct iou_vec *iv)
+{
+ if (IS_ENABLED(CONFIG_KASAN))
+ io_vec_free(iv);
+}
+
#endif
diff --git a/io_uring/rw.c b/io_uring/rw.c
index e5528cebcd06..039e063f7091 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -49,24 +49,16 @@ static bool io_file_supports_nowait(struct io_kiocb *req, __poll_t mask)
return false;
}
-#ifdef CONFIG_COMPAT
static int io_iov_compat_buffer_select_prep(struct io_rw *rw)
{
- struct compat_iovec __user *uiov;
- compat_ssize_t clen;
+ struct compat_iovec __user *uiov = u64_to_user_ptr(rw->addr);
+ struct compat_iovec iov;
- uiov = u64_to_user_ptr(rw->addr);
- if (!access_ok(uiov, sizeof(*uiov)))
- return -EFAULT;
- if (__get_user(clen, &uiov->iov_len))
+ if (copy_from_user(&iov, uiov, sizeof(iov)))
return -EFAULT;
- if (clen < 0)
- return -EINVAL;
-
- rw->len = clen;
+ rw->len = iov.iov_len;
return 0;
}
-#endif
static int io_iov_buffer_select_prep(struct io_kiocb *req)
{
@@ -77,10 +69,8 @@ static int io_iov_buffer_select_prep(struct io_kiocb *req)
if (rw->len != 1)
return -EINVAL;
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
+ if (io_is_compat(req->ctx))
return io_iov_compat_buffer_select_prep(rw);
-#endif
uiov = u64_to_user_ptr(rw->addr);
if (copy_from_user(&iov, uiov, sizeof(*uiov)))
@@ -89,59 +79,62 @@ static int io_iov_buffer_select_prep(struct io_kiocb *req)
return 0;
}
-static int __io_import_iovec(int ddir, struct io_kiocb *req,
- struct io_async_rw *io,
- unsigned int issue_flags)
+static int io_import_vec(int ddir, struct io_kiocb *req,
+ struct io_async_rw *io,
+ const struct iovec __user *uvec,
+ size_t uvec_segs)
{
- const struct io_issue_def *def = &io_issue_defs[req->opcode];
- struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+ int ret, nr_segs;
struct iovec *iov;
- void __user *buf;
- int nr_segs, ret;
- size_t sqe_len;
-
- buf = u64_to_user_ptr(rw->addr);
- sqe_len = rw->len;
-
- if (!def->vectored || req->flags & REQ_F_BUFFER_SELECT) {
- if (io_do_buffer_select(req)) {
- buf = io_buffer_select(req, &sqe_len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- rw->addr = (unsigned long) buf;
- rw->len = sqe_len;
- }
-
- return import_ubuf(ddir, buf, sqe_len, &io->iter);
- }
- if (io->free_iovec) {
- nr_segs = io->free_iov_nr;
- iov = io->free_iovec;
+ if (io->vec.iovec) {
+ nr_segs = io->vec.nr;
+ iov = io->vec.iovec;
} else {
- iov = &io->fast_iov;
nr_segs = 1;
+ iov = &io->fast_iov;
}
- ret = __import_iovec(ddir, buf, sqe_len, nr_segs, &iov, &io->iter,
- req->ctx->compat);
+
+ ret = __import_iovec(ddir, uvec, uvec_segs, nr_segs, &iov, &io->iter,
+ io_is_compat(req->ctx));
if (unlikely(ret < 0))
return ret;
if (iov) {
req->flags |= REQ_F_NEED_CLEANUP;
- io->free_iov_nr = io->iter.nr_segs;
- kfree(io->free_iovec);
- io->free_iovec = iov;
+ io_vec_reset_iovec(&io->vec, iov, io->iter.nr_segs);
}
return 0;
}
-static inline int io_import_iovec(int rw, struct io_kiocb *req,
- struct io_async_rw *io,
- unsigned int issue_flags)
+static int __io_import_rw_buffer(int ddir, struct io_kiocb *req,
+ struct io_async_rw *io,
+ unsigned int issue_flags)
+{
+ const struct io_issue_def *def = &io_issue_defs[req->opcode];
+ struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+ void __user *buf = u64_to_user_ptr(rw->addr);
+ size_t sqe_len = rw->len;
+
+ if (def->vectored && !(req->flags & REQ_F_BUFFER_SELECT))
+ return io_import_vec(ddir, req, io, buf, sqe_len);
+
+ if (io_do_buffer_select(req)) {
+ buf = io_buffer_select(req, &sqe_len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ rw->addr = (unsigned long) buf;
+ rw->len = sqe_len;
+ }
+ return import_ubuf(ddir, buf, sqe_len, &io->iter);
+}
+
+static inline int io_import_rw_buffer(int rw, struct io_kiocb *req,
+ struct io_async_rw *io,
+ unsigned int issue_flags)
{
int ret;
- ret = __io_import_iovec(rw, req, io, issue_flags);
+ ret = __io_import_rw_buffer(rw, req, io, issue_flags);
if (unlikely(ret < 0))
return ret;
@@ -156,7 +149,10 @@ static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
return;
- io_alloc_cache_kasan(&rw->free_iovec, &rw->free_iov_nr);
+ io_alloc_cache_vec_kasan(&rw->vec);
+ if (rw->vec.nr > IO_VEC_CACHE_SOFT_CAP)
+ io_vec_free(&rw->vec);
+
if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) {
req->async_data = NULL;
req->flags &= ~REQ_F_ASYNC_DATA;
@@ -206,26 +202,12 @@ static int io_rw_alloc_async(struct io_kiocb *req)
rw = io_uring_alloc_async_data(&ctx->rw_cache, req);
if (!rw)
return -ENOMEM;
- if (rw->free_iovec)
+ if (rw->vec.iovec)
req->flags |= REQ_F_NEED_CLEANUP;
rw->bytes_done = 0;
return 0;
}
-static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import)
-{
- struct io_async_rw *rw;
-
- if (io_rw_alloc_async(req))
- return -ENOMEM;
-
- if (!do_import || io_do_buffer_select(req))
- return 0;
-
- rw = req->async_data;
- return io_import_iovec(ddir, req, rw, 0);
-}
-
static inline void io_meta_save_state(struct io_async_rw *io)
{
io->meta_state.seed = io->meta.seed;
@@ -267,14 +249,17 @@ static int io_prep_rw_pi(struct io_kiocb *req, struct io_rw *rw, int ddir,
return ret;
}
-static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- int ddir, bool do_import)
+static int __io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ int ddir)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
unsigned ioprio;
u64 attr_type_mask;
int ret;
+ if (io_rw_alloc_async(req))
+ return -ENOMEM;
+
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);
@@ -300,10 +285,6 @@ 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);
- ret = io_prep_rw_setup(req, ddir, do_import);
-
- if (unlikely(ret))
- return ret;
attr_type_mask = READ_ONCE(sqe->attr_type_mask);
if (attr_type_mask) {
@@ -314,31 +295,50 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
return -EINVAL;
attr_ptr = READ_ONCE(sqe->attr_ptr);
- ret = io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask);
+ return io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask);
}
- return ret;
+ return 0;
+}
+
+static int io_rw_do_import(struct io_kiocb *req, int ddir)
+{
+ if (io_do_buffer_select(req))
+ return 0;
+
+ return io_import_rw_buffer(ddir, req, req->async_data, 0);
+}
+
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ int ddir)
+{
+ int ret;
+
+ ret = __io_prep_rw(req, sqe, ddir);
+ if (unlikely(ret))
+ return ret;
+
+ return io_rw_do_import(req, ddir);
}
int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw(req, sqe, ITER_DEST, true);
+ return io_prep_rw(req, sqe, ITER_DEST);
}
int io_prep_write(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw(req, sqe, ITER_SOURCE, true);
+ return io_prep_rw(req, sqe, ITER_SOURCE);
}
static int io_prep_rwv(struct io_kiocb *req, const struct io_uring_sqe *sqe,
int ddir)
{
- const bool do_import = !(req->flags & REQ_F_BUFFER_SELECT);
int ret;
- ret = io_prep_rw(req, sqe, ddir, do_import);
+ ret = io_prep_rw(req, sqe, ddir);
if (unlikely(ret))
return ret;
- if (do_import)
+ if (!(req->flags & REQ_F_BUFFER_SELECT))
return 0;
/*
@@ -358,38 +358,77 @@ int io_prep_writev(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return io_prep_rwv(req, sqe, ITER_SOURCE);
}
-static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+static int io_init_rw_fixed(struct io_kiocb *req, unsigned int issue_flags,
int ddir)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
- struct io_ring_ctx *ctx = req->ctx;
- struct io_rsrc_node *node;
- struct io_async_rw *io;
+ struct io_async_rw *io = req->async_data;
int ret;
- ret = io_prep_rw(req, sqe, ddir, false);
- if (unlikely(ret))
- return ret;
-
- node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index);
- if (!node)
- return -EFAULT;
- io_req_assign_buf_node(req, node);
+ if (io->bytes_done)
+ return 0;
- io = req->async_data;
- ret = io_import_fixed(ddir, &io->iter, node->buf, rw->addr, rw->len);
+ ret = io_import_reg_buf(req, &io->iter, rw->addr, rw->len, ddir,
+ issue_flags);
iov_iter_save_state(&io->iter, &io->iter_state);
return ret;
}
int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw_fixed(req, sqe, ITER_DEST);
+ return __io_prep_rw(req, sqe, ITER_DEST);
}
int io_prep_write_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- return io_prep_rw_fixed(req, sqe, ITER_SOURCE);
+ return __io_prep_rw(req, sqe, ITER_SOURCE);
+}
+
+static int io_rw_import_reg_vec(struct io_kiocb *req,
+ struct io_async_rw *io,
+ int ddir, unsigned int issue_flags)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+ unsigned uvec_segs = rw->len;
+ int ret;
+
+ ret = io_import_reg_vec(ddir, &io->iter, req, &io->vec,
+ uvec_segs, issue_flags);
+ if (unlikely(ret))
+ return ret;
+ iov_iter_save_state(&io->iter, &io->iter_state);
+ req->flags &= ~REQ_F_IMPORT_BUFFER;
+ return 0;
+}
+
+static int io_rw_prep_reg_vec(struct io_kiocb *req)
+{
+ struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+ struct io_async_rw *io = req->async_data;
+ const struct iovec __user *uvec;
+
+ uvec = u64_to_user_ptr(rw->addr);
+ return io_prep_reg_iovec(req, &io->vec, uvec, rw->len);
+}
+
+int io_prep_readv_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ int ret;
+
+ ret = __io_prep_rw(req, sqe, ITER_DEST);
+ if (unlikely(ret))
+ return ret;
+ return io_rw_prep_reg_vec(req);
+}
+
+int io_prep_writev_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ int ret;
+
+ ret = __io_prep_rw(req, sqe, ITER_SOURCE);
+ if (unlikely(ret))
+ return ret;
+ return io_rw_prep_reg_vec(req);
}
/*
@@ -405,7 +444,7 @@ int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (!(req->flags & REQ_F_BUFFER_SELECT))
return -EINVAL;
- ret = io_prep_rw(req, sqe, ITER_DEST, false);
+ ret = __io_prep_rw(req, sqe, ITER_DEST);
if (unlikely(ret))
return ret;
@@ -519,7 +558,7 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res)
return res;
}
-void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts)
+void io_req_rw_complete(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
struct kiocb *kiocb = &rw->kiocb;
@@ -536,7 +575,7 @@ void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts)
req->cqe.flags |= io_put_kbuf(req, req->cqe.res, 0);
io_req_rw_cleanup(req, 0);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
}
static void io_complete_rw(struct kiocb *kiocb, long res)
@@ -637,6 +676,7 @@ static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
*/
static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
{
+ struct io_kiocb *req = cmd_to_io_kiocb(rw);
struct kiocb *kiocb = &rw->kiocb;
struct file *file = kiocb->ki_filp;
ssize_t ret = 0;
@@ -652,6 +692,8 @@ static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
if ((kiocb->ki_flags & IOCB_NOWAIT) &&
!(kiocb->ki_filp->f_flags & O_NONBLOCK))
return -EAGAIN;
+ if ((req->flags & REQ_F_BUF_NODE) && req->buf_node->buf->is_kbuf)
+ return -EFAULT;
ppos = io_kiocb_ppos(kiocb);
@@ -862,8 +904,12 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
ssize_t ret;
loff_t *ppos;
- if (io_do_buffer_select(req)) {
- ret = io_import_iovec(ITER_DEST, req, io, issue_flags);
+ if (req->flags & REQ_F_IMPORT_BUFFER) {
+ ret = io_rw_import_reg_vec(req, io, ITER_DEST, issue_flags);
+ if (unlikely(ret))
+ return ret;
+ } else if (io_do_buffer_select(req)) {
+ ret = io_import_rw_buffer(ITER_DEST, req, io, issue_flags);
if (unlikely(ret < 0))
return ret;
}
@@ -1001,9 +1047,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
*/
if (io_kbuf_recycle(req, issue_flags))
rw->len = 0;
- if (issue_flags & IO_URING_F_MULTISHOT)
- return IOU_ISSUE_SKIP_COMPLETE;
- return -EAGAIN;
+ return IOU_RETRY;
} else if (ret <= 0) {
io_kbuf_recycle(req, issue_flags);
if (ret < 0)
@@ -1021,16 +1065,15 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
rw->len = 0; /* similarly to above, reset len to 0 */
if (io_req_post_cqe(req, ret, cflags | IORING_CQE_F_MORE)) {
- if (issue_flags & IO_URING_F_MULTISHOT) {
+ if (issue_flags & IO_URING_F_MULTISHOT)
/*
* Force retry, as we might have more data to
* be read and otherwise it won't get retried
* until (if ever) another poll is triggered.
*/
io_poll_multishot_retry(req);
- return IOU_ISSUE_SKIP_COMPLETE;
- }
- return -EAGAIN;
+
+ return IOU_RETRY;
}
}
@@ -1040,9 +1083,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
*/
io_req_set_res(req, ret, cflags);
io_req_rw_cleanup(req, issue_flags);
- if (issue_flags & IO_URING_F_MULTISHOT)
- return IOU_STOP_MULTISHOT;
- return IOU_OK;
+ return IOU_COMPLETE;
}
static bool io_kiocb_start_write(struct io_kiocb *req, struct kiocb *kiocb)
@@ -1073,6 +1114,12 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
ssize_t ret, ret2;
loff_t *ppos;
+ if (req->flags & REQ_F_IMPORT_BUFFER) {
+ ret = io_rw_import_reg_vec(req, io, ITER_SOURCE, issue_flags);
+ if (unlikely(ret))
+ return ret;
+ }
+
ret = io_rw_init_file(req, FMODE_WRITE, WRITE);
if (unlikely(ret))
return ret;
@@ -1154,6 +1201,28 @@ ret_eagain:
}
}
+int io_read_fixed(struct io_kiocb *req, unsigned int issue_flags)
+{
+ int ret;
+
+ ret = io_init_rw_fixed(req, issue_flags, ITER_DEST);
+ if (unlikely(ret))
+ return ret;
+
+ return io_read(req, issue_flags);
+}
+
+int io_write_fixed(struct io_kiocb *req, unsigned int issue_flags)
+{
+ int ret;
+
+ ret = io_init_rw_fixed(req, issue_flags, ITER_SOURCE);
+ if (unlikely(ret))
+ return ret;
+
+ return io_write(req, issue_flags);
+}
+
void io_rw_fail(struct io_kiocb *req)
{
int res;
@@ -1310,7 +1379,6 @@ void io_rw_cache_free(const void *entry)
{
struct io_async_rw *rw = (struct io_async_rw *) entry;
- if (rw->free_iovec)
- kfree(rw->free_iovec);
+ io_vec_free(&rw->vec);
kfree(rw);
}
diff --git a/io_uring/rw.h b/io_uring/rw.h
index eaa59bd64870..81d6d9a8cf69 100644
--- a/io_uring/rw.h
+++ b/io_uring/rw.h
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/io_uring_types.h>
#include <linux/pagemap.h>
struct io_meta_state {
@@ -8,13 +9,13 @@ struct io_meta_state {
};
struct io_async_rw {
+ struct iou_vec vec;
size_t bytes_done;
- struct iovec *free_iovec;
+
struct_group(clear,
struct iov_iter iter;
struct iov_iter_state iter_state;
struct iovec fast_iov;
- int free_iov_nr;
/*
* wpq is for buffered io, while meta fields are used with
* direct io
@@ -31,15 +32,19 @@ struct io_async_rw {
int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_prep_write_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_readv_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_writev_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_prep_readv(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_prep_writev(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_prep_write(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_read(struct io_kiocb *req, unsigned int issue_flags);
int io_write(struct io_kiocb *req, unsigned int issue_flags);
+int io_read_fixed(struct io_kiocb *req, unsigned int issue_flags);
+int io_write_fixed(struct io_kiocb *req, unsigned int issue_flags);
void io_readv_writev_cleanup(struct io_kiocb *req);
void io_rw_fail(struct io_kiocb *req);
-void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts);
+void io_req_rw_complete(struct io_kiocb *req, io_tw_token_t tw);
int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags);
void io_rw_cache_free(const void *entry);
diff --git a/io_uring/splice.c b/io_uring/splice.c
index 5b84f1630611..7b89bd84d486 100644
--- a/io_uring/splice.c
+++ b/io_uring/splice.c
@@ -51,7 +51,8 @@ void io_splice_cleanup(struct io_kiocb *req)
{
struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice);
- io_put_rsrc_node(req->ctx, sp->rsrc_node);
+ if (sp->rsrc_node)
+ io_put_rsrc_node(req->ctx, sp->rsrc_node);
}
static struct file *io_splice_get_file(struct io_kiocb *req,
diff --git a/io_uring/timeout.c b/io_uring/timeout.c
index 48fc8cf70784..2a107665230b 100644
--- a/io_uring/timeout.c
+++ b/io_uring/timeout.c
@@ -65,7 +65,7 @@ static inline bool io_timeout_finish(struct io_timeout *timeout,
static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer);
-static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_timeout_complete(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
struct io_timeout_data *data = req->async_data;
@@ -82,7 +82,7 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts)
}
}
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
}
static __cold bool io_flush_killed_timeouts(struct list_head *list, int err)
@@ -154,9 +154,9 @@ __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
io_flush_killed_timeouts(&list, 0);
}
-static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts)
+static void io_req_tw_fail_links(struct io_kiocb *link, io_tw_token_t tw)
{
- io_tw_lock(link->ctx, ts);
+ io_tw_lock(link->ctx, tw);
while (link) {
struct io_kiocb *nxt = link->link;
long res = -ECANCELED;
@@ -165,7 +165,7 @@ static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts)
res = link->cqe.res;
link->link = NULL;
io_req_set_res(link, res, 0);
- io_req_task_complete(link, ts);
+ io_req_task_complete(link, tw);
link = nxt;
}
}
@@ -312,7 +312,7 @@ int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd)
return 0;
}
-static void io_req_task_link_timeout(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_req_task_link_timeout(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
struct io_kiocb *prev = timeout->prev;
@@ -330,11 +330,11 @@ static void io_req_task_link_timeout(struct io_kiocb *req, struct io_tw_state *t
ret = -ECANCELED;
}
io_req_set_res(req, ret ?: -ETIME, 0);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
io_put_req(prev);
} else {
io_req_set_res(req, -ETIME, 0);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
}
}
@@ -407,8 +407,7 @@ static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
io = req->async_data;
if (hrtimer_try_to_cancel(&io->timer) == -1)
return -EALREADY;
- hrtimer_init(&io->timer, io_timeout_get_clock(io), mode);
- io->timer.function = io_link_timeout_fn;
+ hrtimer_setup(&io->timer, io_link_timeout_fn, io_timeout_get_clock(io), mode);
hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode);
return 0;
}
@@ -430,8 +429,7 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
data->ts = *ts;
list_add_tail(&timeout->list, &ctx->timeout_list);
- hrtimer_init(&data->timer, io_timeout_get_clock(data), mode);
- data->timer.function = io_timeout_fn;
+ hrtimer_setup(&data->timer, io_timeout_fn, io_timeout_get_clock(data), mode);
hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), mode);
return 0;
}
@@ -557,7 +555,6 @@ static int __io_timeout_prep(struct io_kiocb *req,
return -EINVAL;
data->mode = io_translate_timeout_mode(flags);
- hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
if (is_timeout_link) {
struct io_submit_link *link = &req->ctx->submit_state.link;
@@ -568,6 +565,10 @@ static int __io_timeout_prep(struct io_kiocb *req,
return -EINVAL;
timeout->head = link->last;
link->last->flags |= REQ_F_ARM_LTIMEOUT;
+ hrtimer_setup(&data->timer, io_link_timeout_fn, io_timeout_get_clock(data),
+ data->mode);
+ } else {
+ hrtimer_setup(&data->timer, io_timeout_fn, io_timeout_get_clock(data), data->mode);
}
return 0;
}
@@ -627,7 +628,6 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
}
add:
list_add(&timeout->list, entry);
- data->timer.function = io_timeout_fn;
hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
raw_spin_unlock_irq(&ctx->timeout_lock);
return IOU_ISSUE_SKIP_COMPLETE;
@@ -646,7 +646,6 @@ void io_queue_linked_timeout(struct io_kiocb *req)
if (timeout->head) {
struct io_timeout_data *data = req->async_data;
- data->timer.function = io_link_timeout_fn;
hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
data->mode);
list_add_tail(&timeout->list, &ctx->ltimeout_list);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index e6701b7aa147..f2cfc371f3d0 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -16,10 +16,19 @@
#include "rsrc.h"
#include "uring_cmd.h"
+void io_cmd_cache_free(const void *entry)
+{
+ struct io_async_cmd *ac = (struct io_async_cmd *)entry;
+
+ io_vec_free(&ac->vec);
+ kfree(ac);
+}
+
static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
- struct io_uring_cmd_data *cache = req->async_data;
+ struct io_async_cmd *ac = req->async_data;
+ struct io_uring_cmd_data *cache = &ac->data;
if (cache->op_data) {
kfree(cache->op_data);
@@ -28,13 +37,23 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
if (issue_flags & IO_URING_F_UNLOCKED)
return;
- if (io_alloc_cache_put(&req->ctx->uring_cache, cache)) {
+
+ io_alloc_cache_vec_kasan(&ac->vec);
+ if (ac->vec.nr > IO_VEC_CACHE_SOFT_CAP)
+ io_vec_free(&ac->vec);
+
+ if (io_alloc_cache_put(&req->ctx->cmd_cache, cache)) {
ioucmd->sqe = NULL;
req->async_data = NULL;
- req->flags &= ~REQ_F_ASYNC_DATA;
+ req->flags &= ~(REQ_F_ASYNC_DATA|REQ_F_NEED_CLEANUP);
}
}
+void io_uring_cmd_cleanup(struct io_kiocb *req)
+{
+ io_req_uring_cleanup(req, 0);
+}
+
bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
struct io_uring_task *tctx, bool cancel_all)
{
@@ -102,7 +121,7 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
}
EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable);
-static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_uring_cmd_work(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
unsigned int flags = IO_URING_F_COMPLETE_DEFER;
@@ -169,12 +188,15 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
- struct io_uring_cmd_data *cache;
+ struct io_async_cmd *ac;
- cache = io_uring_alloc_async_data(&req->ctx->uring_cache, req);
- if (!cache)
+ /* see io_uring_cmd_get_async_data() */
+ BUILD_BUG_ON(offsetof(struct io_async_cmd, data) != 0);
+
+ ac = io_uring_alloc_async_data(&req->ctx->cmd_cache, req);
+ if (!ac)
return -ENOMEM;
- cache->op_data = NULL;
+ ac->data.op_data = NULL;
/*
* Unconditionally cache the SQE for now - this is only needed for
@@ -183,8 +205,8 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req,
* that it doesn't read in per-op data, play it safe and ensure that
* any SQE data is stable beyond prep. This can later get relaxed.
*/
- memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx));
- ioucmd->sqe = cache->sqes;
+ memcpy(ac->data.sqes, sqe, uring_sqe_size(req->ctx));
+ ioucmd->sqe = ac->data.sqes;
return 0;
}
@@ -199,21 +221,9 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (ioucmd->flags & ~IORING_URING_CMD_MASK)
return -EINVAL;
- if (ioucmd->flags & IORING_URING_CMD_FIXED) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_rsrc_node *node;
- u16 index = READ_ONCE(sqe->buf_index);
-
- node = io_rsrc_node_lookup(&ctx->buf_table, index);
- if (unlikely(!node))
- return -EFAULT;
- /*
- * Pi node upfront, prior to io_uring_cmd_import_fixed()
- * being called. This prevents destruction of the mapped buffer
- * we'll need at actual import time.
- */
- io_req_assign_buf_node(req, node);
- }
+ if (ioucmd->flags & IORING_URING_CMD_FIXED)
+ req->buf_index = READ_ONCE(sqe->buf_index);
+
ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
return io_uring_cmd_prep_setup(req, sqe);
@@ -237,7 +247,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
issue_flags |= IO_URING_F_SQE128;
if (ctx->flags & IORING_SETUP_CQE32)
issue_flags |= IO_URING_F_CQE32;
- if (ctx->compat)
+ if (io_is_compat(ctx))
issue_flags |= IO_URING_F_COMPAT;
if (ctx->flags & IORING_SETUP_IOPOLL) {
if (!file->f_op->uring_cmd_iopoll)
@@ -257,19 +267,35 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
}
int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
- struct iov_iter *iter, void *ioucmd)
+ struct iov_iter *iter,
+ struct io_uring_cmd *ioucmd,
+ unsigned int issue_flags)
{
struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
- struct io_rsrc_node *node = req->buf_node;
-
- /* Must have had rsrc_node assigned at prep time */
- if (node)
- return io_import_fixed(rw, iter, node->buf, ubuf, len);
- return -EFAULT;
+ return io_import_reg_buf(req, iter, ubuf, len, rw, issue_flags);
}
EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
+int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
+ const struct iovec __user *uvec,
+ size_t uvec_segs,
+ int ddir, struct iov_iter *iter,
+ unsigned issue_flags)
+{
+ struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
+ struct io_async_cmd *ac = req->async_data;
+ int ret;
+
+ ret = io_prep_reg_iovec(req, &ac->vec, uvec, uvec_segs);
+ if (ret)
+ return ret;
+
+ return io_import_reg_vec(ddir, iter, req, &ac->vec, uvec_segs,
+ issue_flags);
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed_vec);
+
void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd)
{
struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h
index f6837ee0955b..14e525255854 100644
--- a/io_uring/uring_cmd.h
+++ b/io_uring/uring_cmd.h
@@ -1,7 +1,24 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/io_uring/cmd.h>
+#include <linux/io_uring_types.h>
+
+struct io_async_cmd {
+ struct io_uring_cmd_data data;
+ struct iou_vec vec;
+};
+
int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags);
int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+void io_uring_cmd_cleanup(struct io_kiocb *req);
bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
struct io_uring_task *tctx, bool cancel_all);
+
+void io_cmd_cache_free(const void *entry);
+
+int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
+ const struct iovec __user *uvec,
+ size_t uvec_segs,
+ int ddir, struct iov_iter *iter,
+ unsigned issue_flags);
diff --git a/io_uring/waitid.c b/io_uring/waitid.c
index 15a7daf3ff4f..54e69984cd8a 100644
--- a/io_uring/waitid.c
+++ b/io_uring/waitid.c
@@ -16,7 +16,7 @@
#include "waitid.h"
#include "../kernel/exit.h"
-static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts);
+static void io_waitid_cb(struct io_kiocb *req, io_tw_token_t tw);
#define IO_WAITID_CANCEL_FLAG BIT(31)
#define IO_WAITID_REF_MASK GENMASK(30, 0)
@@ -42,7 +42,6 @@ static void io_waitid_free(struct io_kiocb *req)
req->flags &= ~REQ_F_ASYNC_DATA;
}
-#ifdef CONFIG_COMPAT
static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo)
{
struct compat_siginfo __user *infop;
@@ -67,7 +66,6 @@ Efault:
ret = false;
goto done;
}
-#endif
static bool io_waitid_copy_si(struct io_kiocb *req, int signo)
{
@@ -77,10 +75,8 @@ static bool io_waitid_copy_si(struct io_kiocb *req, int signo)
if (!iw->infop)
return true;
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
+ if (io_is_compat(req->ctx))
return io_waitid_compat_copy_si(iw, signo);
-#endif
if (!user_write_access_begin(iw->infop, sizeof(*iw->infop)))
return false;
@@ -132,7 +128,7 @@ static void io_waitid_complete(struct io_kiocb *req, int ret)
io_req_set_res(req, ret, 0);
}
-static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
+static bool __io_waitid_cancel(struct io_kiocb *req)
{
struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
struct io_waitid_async *iwa = req->async_data;
@@ -158,49 +154,13 @@ static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
unsigned int issue_flags)
{
- struct hlist_node *tmp;
- struct io_kiocb *req;
- int nr = 0;
-
- if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED))
- return -ENOENT;
-
- io_ring_submit_lock(ctx, issue_flags);
- hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) {
- if (req->cqe.user_data != cd->data &&
- !(cd->flags & IORING_ASYNC_CANCEL_ANY))
- continue;
- if (__io_waitid_cancel(ctx, req))
- nr++;
- if (!(cd->flags & IORING_ASYNC_CANCEL_ALL))
- break;
- }
- io_ring_submit_unlock(ctx, issue_flags);
-
- if (nr)
- return nr;
-
- return -ENOENT;
+ return io_cancel_remove(ctx, cd, issue_flags, &ctx->waitid_list, __io_waitid_cancel);
}
bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
bool cancel_all)
{
- struct hlist_node *tmp;
- struct io_kiocb *req;
- bool found = false;
-
- lockdep_assert_held(&ctx->uring_lock);
-
- hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) {
- if (!io_match_task_safe(req, tctx, cancel_all))
- continue;
- hlist_del_init(&req->hash_node);
- __io_waitid_cancel(ctx, req);
- found = true;
- }
-
- return found;
+ return io_cancel_remove_all(ctx, tctx, &ctx->waitid_list, cancel_all, __io_waitid_cancel);
}
static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req)
@@ -221,13 +181,13 @@ static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req)
return true;
}
-static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts)
+static void io_waitid_cb(struct io_kiocb *req, io_tw_token_t tw)
{
struct io_waitid_async *iwa = req->async_data;
struct io_ring_ctx *ctx = req->ctx;
int ret;
- io_tw_lock(ctx, ts);
+ io_tw_lock(ctx, tw);
ret = __do_wait(&iwa->wo);
@@ -257,7 +217,7 @@ static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts)
}
io_waitid_complete(req, ret);
- io_req_task_complete(req, ts);
+ io_req_task_complete(req, tw);
}
static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode,
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
new file mode 100644
index 000000000000..9c95b5b6ec4e
--- /dev/null
+++ b/io_uring/zcrx.c
@@ -0,0 +1,960 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff_ref.h>
+
+#include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
+#include <net/netlink.h>
+#include <net/netdev_rx_queue.h>
+#include <net/tcp.h>
+#include <net/rps.h>
+
+#include <trace/events/page_pool.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "kbuf.h"
+#include "memmap.h"
+#include "zcrx.h"
+#include "rsrc.h"
+
+#define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
+ struct io_zcrx_area *area, int nr_mapped)
+{
+ int i;
+
+ for (i = 0; i < nr_mapped; i++) {
+ struct net_iov *niov = &area->nia.niovs[i];
+ dma_addr_t dma;
+
+ dma = page_pool_get_dma_addr_netmem(net_iov_to_netmem(niov));
+ dma_unmap_page_attrs(ifq->dev, dma, PAGE_SIZE,
+ DMA_FROM_DEVICE, IO_DMA_ATTR);
+ net_mp_niov_set_dma_addr(niov, 0);
+ }
+}
+
+static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
+{
+ if (area->is_mapped)
+ __io_zcrx_unmap_area(ifq, area, area->nia.num_niovs);
+}
+
+static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
+{
+ int i;
+
+ for (i = 0; i < area->nia.num_niovs; i++) {
+ struct net_iov *niov = &area->nia.niovs[i];
+ dma_addr_t dma;
+
+ dma = dma_map_page_attrs(ifq->dev, area->pages[i], 0, PAGE_SIZE,
+ DMA_FROM_DEVICE, IO_DMA_ATTR);
+ if (dma_mapping_error(ifq->dev, dma))
+ break;
+ if (net_mp_niov_set_dma_addr(niov, dma)) {
+ dma_unmap_page_attrs(ifq->dev, dma, PAGE_SIZE,
+ DMA_FROM_DEVICE, IO_DMA_ATTR);
+ break;
+ }
+ }
+
+ if (i != area->nia.num_niovs) {
+ __io_zcrx_unmap_area(ifq, area, i);
+ return -EINVAL;
+ }
+
+ area->is_mapped = true;
+ return 0;
+}
+
+static void io_zcrx_sync_for_device(const struct page_pool *pool,
+ struct net_iov *niov)
+{
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
+ dma_addr_t dma_addr;
+
+ if (!dma_dev_need_sync(pool->p.dev))
+ return;
+
+ dma_addr = page_pool_get_dma_addr_netmem(net_iov_to_netmem(niov));
+ __dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset,
+ PAGE_SIZE, pool->p.dma_dir);
+#endif
+}
+
+#define IO_RQ_MAX_ENTRIES 32768
+
+#define IO_SKBS_PER_CALL_LIMIT 20
+
+struct io_zcrx_args {
+ struct io_kiocb *req;
+ struct io_zcrx_ifq *ifq;
+ struct socket *sock;
+ unsigned nr_skbs;
+};
+
+static const struct memory_provider_ops io_uring_pp_zc_ops;
+
+static inline struct io_zcrx_area *io_zcrx_iov_to_area(const struct net_iov *niov)
+{
+ struct net_iov_area *owner = net_iov_owner(niov);
+
+ return container_of(owner, struct io_zcrx_area, nia);
+}
+
+static inline atomic_t *io_get_user_counter(struct net_iov *niov)
+{
+ struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+ return &area->user_refs[net_iov_idx(niov)];
+}
+
+static bool io_zcrx_put_niov_uref(struct net_iov *niov)
+{
+ atomic_t *uref = io_get_user_counter(niov);
+
+ if (unlikely(!atomic_read(uref)))
+ return false;
+ atomic_dec(uref);
+ return true;
+}
+
+static void io_zcrx_get_niov_uref(struct net_iov *niov)
+{
+ atomic_inc(io_get_user_counter(niov));
+}
+
+static inline struct page *io_zcrx_iov_page(const struct net_iov *niov)
+{
+ struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+ return area->pages[net_iov_idx(niov)];
+}
+
+static int io_allocate_rbuf_ring(struct io_zcrx_ifq *ifq,
+ struct io_uring_zcrx_ifq_reg *reg,
+ struct io_uring_region_desc *rd)
+{
+ size_t off, size;
+ void *ptr;
+ int ret;
+
+ off = sizeof(struct io_uring);
+ size = off + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries;
+ if (size > rd->size)
+ return -EINVAL;
+
+ ret = io_create_region_mmap_safe(ifq->ctx, &ifq->ctx->zcrx_region, rd,
+ IORING_MAP_OFF_ZCRX_REGION);
+ if (ret < 0)
+ return ret;
+
+ ptr = io_region_get_ptr(&ifq->ctx->zcrx_region);
+ ifq->rq_ring = (struct io_uring *)ptr;
+ ifq->rqes = (struct io_uring_zcrx_rqe *)(ptr + off);
+ return 0;
+}
+
+static void io_free_rbuf_ring(struct io_zcrx_ifq *ifq)
+{
+ io_free_region(ifq->ctx, &ifq->ctx->zcrx_region);
+ ifq->rq_ring = NULL;
+ ifq->rqes = NULL;
+}
+
+static void io_zcrx_free_area(struct io_zcrx_area *area)
+{
+ io_zcrx_unmap_area(area->ifq, area);
+
+ kvfree(area->freelist);
+ kvfree(area->nia.niovs);
+ kvfree(area->user_refs);
+ if (area->pages) {
+ unpin_user_pages(area->pages, area->nia.num_niovs);
+ kvfree(area->pages);
+ }
+ kfree(area);
+}
+
+static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
+ struct io_zcrx_area **res,
+ struct io_uring_zcrx_area_reg *area_reg)
+{
+ struct io_zcrx_area *area;
+ int i, ret, nr_pages;
+ struct iovec iov;
+
+ if (area_reg->flags || area_reg->rq_area_token)
+ return -EINVAL;
+ if (area_reg->__resv1 || area_reg->__resv2[0] || area_reg->__resv2[1])
+ return -EINVAL;
+ if (area_reg->addr & ~PAGE_MASK || area_reg->len & ~PAGE_MASK)
+ return -EINVAL;
+
+ iov.iov_base = u64_to_user_ptr(area_reg->addr);
+ iov.iov_len = area_reg->len;
+ ret = io_buffer_validate(&iov);
+ if (ret)
+ return ret;
+
+ ret = -ENOMEM;
+ area = kzalloc(sizeof(*area), GFP_KERNEL);
+ if (!area)
+ goto err;
+
+ area->pages = io_pin_pages((unsigned long)area_reg->addr, area_reg->len,
+ &nr_pages);
+ if (IS_ERR(area->pages)) {
+ ret = PTR_ERR(area->pages);
+ area->pages = NULL;
+ goto err;
+ }
+ area->nia.num_niovs = nr_pages;
+
+ area->nia.niovs = kvmalloc_array(nr_pages, sizeof(area->nia.niovs[0]),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!area->nia.niovs)
+ goto err;
+
+ area->freelist = kvmalloc_array(nr_pages, sizeof(area->freelist[0]),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!area->freelist)
+ goto err;
+
+ for (i = 0; i < nr_pages; i++)
+ area->freelist[i] = i;
+
+ area->user_refs = kvmalloc_array(nr_pages, sizeof(area->user_refs[0]),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!area->user_refs)
+ goto err;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct net_iov *niov = &area->nia.niovs[i];
+
+ niov->owner = &area->nia;
+ area->freelist[i] = i;
+ atomic_set(&area->user_refs[i], 0);
+ }
+
+ area->free_count = nr_pages;
+ area->ifq = ifq;
+ /* we're only supporting one area per ifq for now */
+ area->area_id = 0;
+ area_reg->rq_area_token = (u64)area->area_id << IORING_ZCRX_AREA_SHIFT;
+ spin_lock_init(&area->freelist_lock);
+ *res = area;
+ return 0;
+err:
+ if (area)
+ io_zcrx_free_area(area);
+ return ret;
+}
+
+static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
+{
+ struct io_zcrx_ifq *ifq;
+
+ ifq = kzalloc(sizeof(*ifq), GFP_KERNEL);
+ if (!ifq)
+ return NULL;
+
+ ifq->if_rxq = -1;
+ ifq->ctx = ctx;
+ spin_lock_init(&ifq->lock);
+ spin_lock_init(&ifq->rq_lock);
+ return ifq;
+}
+
+static void io_zcrx_drop_netdev(struct io_zcrx_ifq *ifq)
+{
+ spin_lock(&ifq->lock);
+ if (ifq->netdev) {
+ netdev_put(ifq->netdev, &ifq->netdev_tracker);
+ ifq->netdev = NULL;
+ }
+ spin_unlock(&ifq->lock);
+}
+
+static void io_close_queue(struct io_zcrx_ifq *ifq)
+{
+ struct net_device *netdev;
+ netdevice_tracker netdev_tracker;
+ struct pp_memory_provider_params p = {
+ .mp_ops = &io_uring_pp_zc_ops,
+ .mp_priv = ifq,
+ };
+
+ if (ifq->if_rxq == -1)
+ return;
+
+ spin_lock(&ifq->lock);
+ netdev = ifq->netdev;
+ netdev_tracker = ifq->netdev_tracker;
+ ifq->netdev = NULL;
+ spin_unlock(&ifq->lock);
+
+ if (netdev) {
+ net_mp_close_rxq(netdev, ifq->if_rxq, &p);
+ netdev_put(netdev, &netdev_tracker);
+ }
+ ifq->if_rxq = -1;
+}
+
+static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
+{
+ io_close_queue(ifq);
+ io_zcrx_drop_netdev(ifq);
+
+ if (ifq->area)
+ io_zcrx_free_area(ifq->area);
+ if (ifq->dev)
+ put_device(ifq->dev);
+
+ io_free_rbuf_ring(ifq);
+ kfree(ifq);
+}
+
+int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+ struct io_uring_zcrx_ifq_reg __user *arg)
+{
+ struct pp_memory_provider_params mp_param = {};
+ struct io_uring_zcrx_area_reg area;
+ struct io_uring_zcrx_ifq_reg reg;
+ struct io_uring_region_desc rd;
+ struct io_zcrx_ifq *ifq;
+ int ret;
+
+ /*
+ * 1. Interface queue allocation.
+ * 2. It can observe data destined for sockets of other tasks.
+ */
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ /* mandatory io_uring features for zc rx */
+ if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN &&
+ ctx->flags & IORING_SETUP_CQE32))
+ return -EINVAL;
+ if (ctx->ifq)
+ return -EBUSY;
+ if (copy_from_user(&reg, arg, sizeof(reg)))
+ return -EFAULT;
+ if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd)))
+ return -EFAULT;
+ if (memchr_inv(&reg.__resv, 0, sizeof(reg.__resv)))
+ return -EINVAL;
+ if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags)
+ return -EINVAL;
+ if (reg.rq_entries > IO_RQ_MAX_ENTRIES) {
+ if (!(ctx->flags & IORING_SETUP_CLAMP))
+ return -EINVAL;
+ reg.rq_entries = IO_RQ_MAX_ENTRIES;
+ }
+ reg.rq_entries = roundup_pow_of_two(reg.rq_entries);
+
+ if (copy_from_user(&area, u64_to_user_ptr(reg.area_ptr), sizeof(area)))
+ return -EFAULT;
+
+ ifq = io_zcrx_ifq_alloc(ctx);
+ if (!ifq)
+ return -ENOMEM;
+
+ ret = io_allocate_rbuf_ring(ifq, &reg, &rd);
+ if (ret)
+ goto err;
+
+ ret = io_zcrx_create_area(ifq, &ifq->area, &area);
+ if (ret)
+ goto err;
+
+ ifq->rq_entries = reg.rq_entries;
+
+ ret = -ENODEV;
+ ifq->netdev = netdev_get_by_index(current->nsproxy->net_ns, reg.if_idx,
+ &ifq->netdev_tracker, GFP_KERNEL);
+ if (!ifq->netdev)
+ goto err;
+
+ ifq->dev = ifq->netdev->dev.parent;
+ ret = -EOPNOTSUPP;
+ if (!ifq->dev)
+ goto err;
+ get_device(ifq->dev);
+
+ ret = io_zcrx_map_area(ifq, ifq->area);
+ if (ret)
+ goto err;
+
+ mp_param.mp_ops = &io_uring_pp_zc_ops;
+ mp_param.mp_priv = ifq;
+ ret = net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param);
+ if (ret)
+ goto err;
+ ifq->if_rxq = reg.if_rxq;
+
+ reg.offsets.rqes = sizeof(struct io_uring);
+ reg.offsets.head = offsetof(struct io_uring, head);
+ reg.offsets.tail = offsetof(struct io_uring, tail);
+
+ if (copy_to_user(arg, &reg, sizeof(reg)) ||
+ copy_to_user(u64_to_user_ptr(reg.region_ptr), &rd, sizeof(rd)) ||
+ copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) {
+ ret = -EFAULT;
+ goto err;
+ }
+ ctx->ifq = ifq;
+ return 0;
+err:
+ io_zcrx_ifq_free(ifq);
+ return ret;
+}
+
+void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+ struct io_zcrx_ifq *ifq = ctx->ifq;
+
+ lockdep_assert_held(&ctx->uring_lock);
+
+ if (!ifq)
+ return;
+
+ ctx->ifq = NULL;
+ io_zcrx_ifq_free(ifq);
+}
+
+static struct net_iov *__io_zcrx_get_free_niov(struct io_zcrx_area *area)
+{
+ unsigned niov_idx;
+
+ lockdep_assert_held(&area->freelist_lock);
+
+ niov_idx = area->freelist[--area->free_count];
+ return &area->nia.niovs[niov_idx];
+}
+
+static void io_zcrx_return_niov_freelist(struct net_iov *niov)
+{
+ struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+ spin_lock_bh(&area->freelist_lock);
+ area->freelist[area->free_count++] = net_iov_idx(niov);
+ spin_unlock_bh(&area->freelist_lock);
+}
+
+static void io_zcrx_return_niov(struct net_iov *niov)
+{
+ netmem_ref netmem = net_iov_to_netmem(niov);
+
+ if (!niov->pp) {
+ /* copy fallback allocated niovs */
+ io_zcrx_return_niov_freelist(niov);
+ return;
+ }
+ page_pool_put_unrefed_netmem(niov->pp, netmem, -1, false);
+}
+
+static void io_zcrx_scrub(struct io_zcrx_ifq *ifq)
+{
+ struct io_zcrx_area *area = ifq->area;
+ int i;
+
+ if (!area)
+ return;
+
+ /* Reclaim back all buffers given to the user space. */
+ for (i = 0; i < area->nia.num_niovs; i++) {
+ struct net_iov *niov = &area->nia.niovs[i];
+ int nr;
+
+ if (!atomic_read(io_get_user_counter(niov)))
+ continue;
+ nr = atomic_xchg(io_get_user_counter(niov), 0);
+ if (nr && !page_pool_unref_netmem(net_iov_to_netmem(niov), nr))
+ io_zcrx_return_niov(niov);
+ }
+}
+
+void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+ lockdep_assert_held(&ctx->uring_lock);
+
+ if (!ctx->ifq)
+ return;
+ io_zcrx_scrub(ctx->ifq);
+ io_close_queue(ctx->ifq);
+}
+
+static inline u32 io_zcrx_rqring_entries(struct io_zcrx_ifq *ifq)
+{
+ u32 entries;
+
+ entries = smp_load_acquire(&ifq->rq_ring->tail) - ifq->cached_rq_head;
+ return min(entries, ifq->rq_entries);
+}
+
+static struct io_uring_zcrx_rqe *io_zcrx_get_rqe(struct io_zcrx_ifq *ifq,
+ unsigned mask)
+{
+ unsigned int idx = ifq->cached_rq_head++ & mask;
+
+ return &ifq->rqes[idx];
+}
+
+static void io_zcrx_ring_refill(struct page_pool *pp,
+ struct io_zcrx_ifq *ifq)
+{
+ unsigned int mask = ifq->rq_entries - 1;
+ unsigned int entries;
+ netmem_ref netmem;
+
+ spin_lock_bh(&ifq->rq_lock);
+
+ entries = io_zcrx_rqring_entries(ifq);
+ entries = min_t(unsigned, entries, PP_ALLOC_CACHE_REFILL - pp->alloc.count);
+ if (unlikely(!entries)) {
+ spin_unlock_bh(&ifq->rq_lock);
+ return;
+ }
+
+ do {
+ struct io_uring_zcrx_rqe *rqe = io_zcrx_get_rqe(ifq, mask);
+ struct io_zcrx_area *area;
+ struct net_iov *niov;
+ unsigned niov_idx, area_idx;
+
+ area_idx = rqe->off >> IORING_ZCRX_AREA_SHIFT;
+ niov_idx = (rqe->off & ~IORING_ZCRX_AREA_MASK) >> PAGE_SHIFT;
+
+ if (unlikely(rqe->__pad || area_idx))
+ continue;
+ area = ifq->area;
+
+ if (unlikely(niov_idx >= area->nia.num_niovs))
+ continue;
+ niov_idx = array_index_nospec(niov_idx, area->nia.num_niovs);
+
+ niov = &area->nia.niovs[niov_idx];
+ if (!io_zcrx_put_niov_uref(niov))
+ continue;
+
+ netmem = net_iov_to_netmem(niov);
+ if (page_pool_unref_netmem(netmem, 1) != 0)
+ continue;
+
+ if (unlikely(niov->pp != pp)) {
+ io_zcrx_return_niov(niov);
+ continue;
+ }
+
+ io_zcrx_sync_for_device(pp, niov);
+ net_mp_netmem_place_in_cache(pp, netmem);
+ } while (--entries);
+
+ smp_store_release(&ifq->rq_ring->head, ifq->cached_rq_head);
+ spin_unlock_bh(&ifq->rq_lock);
+}
+
+static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq)
+{
+ struct io_zcrx_area *area = ifq->area;
+
+ spin_lock_bh(&area->freelist_lock);
+ while (area->free_count && pp->alloc.count < PP_ALLOC_CACHE_REFILL) {
+ struct net_iov *niov = __io_zcrx_get_free_niov(area);
+ netmem_ref netmem = net_iov_to_netmem(niov);
+
+ net_mp_niov_set_page_pool(pp, niov);
+ io_zcrx_sync_for_device(pp, niov);
+ net_mp_netmem_place_in_cache(pp, netmem);
+ }
+ spin_unlock_bh(&area->freelist_lock);
+}
+
+static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp)
+{
+ struct io_zcrx_ifq *ifq = pp->mp_priv;
+
+ /* pp should already be ensuring that */
+ if (unlikely(pp->alloc.count))
+ goto out_return;
+
+ io_zcrx_ring_refill(pp, ifq);
+ if (likely(pp->alloc.count))
+ goto out_return;
+
+ io_zcrx_refill_slow(pp, ifq);
+ if (!pp->alloc.count)
+ return 0;
+out_return:
+ return pp->alloc.cache[--pp->alloc.count];
+}
+
+static bool io_pp_zc_release_netmem(struct page_pool *pp, netmem_ref netmem)
+{
+ struct net_iov *niov;
+
+ if (WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+ return false;
+
+ niov = netmem_to_net_iov(netmem);
+ net_mp_niov_clear_page_pool(niov);
+ io_zcrx_return_niov_freelist(niov);
+ return false;
+}
+
+static int io_pp_zc_init(struct page_pool *pp)
+{
+ struct io_zcrx_ifq *ifq = pp->mp_priv;
+
+ if (WARN_ON_ONCE(!ifq))
+ return -EINVAL;
+ if (WARN_ON_ONCE(ifq->dev != pp->p.dev))
+ return -EINVAL;
+ if (WARN_ON_ONCE(!pp->dma_map))
+ return -EOPNOTSUPP;
+ if (pp->p.order != 0)
+ return -EOPNOTSUPP;
+ if (pp->p.dma_dir != DMA_FROM_DEVICE)
+ return -EOPNOTSUPP;
+
+ percpu_ref_get(&ifq->ctx->refs);
+ return 0;
+}
+
+static void io_pp_zc_destroy(struct page_pool *pp)
+{
+ struct io_zcrx_ifq *ifq = pp->mp_priv;
+ struct io_zcrx_area *area = ifq->area;
+
+ if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs))
+ return;
+ percpu_ref_put(&ifq->ctx->refs);
+}
+
+static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp,
+ struct netdev_rx_queue *rxq)
+{
+ struct nlattr *nest;
+ int type;
+
+ type = rxq ? NETDEV_A_QUEUE_IO_URING : NETDEV_A_PAGE_POOL_IO_URING;
+ nest = nla_nest_start(rsp, type);
+ if (!nest)
+ return -EMSGSIZE;
+ nla_nest_end(rsp, nest);
+
+ return 0;
+}
+
+static void io_pp_uninstall(void *mp_priv, struct netdev_rx_queue *rxq)
+{
+ struct pp_memory_provider_params *p = &rxq->mp_params;
+ struct io_zcrx_ifq *ifq = mp_priv;
+
+ io_zcrx_drop_netdev(ifq);
+ p->mp_ops = NULL;
+ p->mp_priv = NULL;
+}
+
+static const struct memory_provider_ops io_uring_pp_zc_ops = {
+ .alloc_netmems = io_pp_zc_alloc_netmems,
+ .release_netmem = io_pp_zc_release_netmem,
+ .init = io_pp_zc_init,
+ .destroy = io_pp_zc_destroy,
+ .nl_fill = io_pp_nl_fill,
+ .uninstall = io_pp_uninstall,
+};
+
+static bool io_zcrx_queue_cqe(struct io_kiocb *req, struct net_iov *niov,
+ struct io_zcrx_ifq *ifq, int off, int len)
+{
+ struct io_uring_zcrx_cqe *rcqe;
+ struct io_zcrx_area *area;
+ struct io_uring_cqe *cqe;
+ u64 offset;
+
+ if (!io_defer_get_uncommited_cqe(req->ctx, &cqe))
+ return false;
+
+ cqe->user_data = req->cqe.user_data;
+ cqe->res = len;
+ cqe->flags = IORING_CQE_F_MORE;
+
+ area = io_zcrx_iov_to_area(niov);
+ offset = off + (net_iov_idx(niov) << PAGE_SHIFT);
+ rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+ rcqe->off = offset + ((u64)area->area_id << IORING_ZCRX_AREA_SHIFT);
+ rcqe->__pad = 0;
+ return true;
+}
+
+static struct net_iov *io_zcrx_alloc_fallback(struct io_zcrx_area *area)
+{
+ struct net_iov *niov = NULL;
+
+ spin_lock_bh(&area->freelist_lock);
+ if (area->free_count)
+ niov = __io_zcrx_get_free_niov(area);
+ spin_unlock_bh(&area->freelist_lock);
+
+ if (niov)
+ page_pool_fragment_netmem(net_iov_to_netmem(niov), 1);
+ return niov;
+}
+
+static ssize_t io_zcrx_copy_chunk(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ void *src_base, struct page *src_page,
+ unsigned int src_offset, size_t len)
+{
+ struct io_zcrx_area *area = ifq->area;
+ size_t copied = 0;
+ int ret = 0;
+
+ while (len) {
+ size_t copy_size = min_t(size_t, PAGE_SIZE, len);
+ const int dst_off = 0;
+ struct net_iov *niov;
+ struct page *dst_page;
+ void *dst_addr;
+
+ niov = io_zcrx_alloc_fallback(area);
+ if (!niov) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ dst_page = io_zcrx_iov_page(niov);
+ dst_addr = kmap_local_page(dst_page);
+ if (src_page)
+ src_base = kmap_local_page(src_page);
+
+ memcpy(dst_addr, src_base + src_offset, copy_size);
+
+ if (src_page)
+ kunmap_local(src_base);
+ kunmap_local(dst_addr);
+
+ if (!io_zcrx_queue_cqe(req, niov, ifq, dst_off, copy_size)) {
+ io_zcrx_return_niov(niov);
+ ret = -ENOSPC;
+ break;
+ }
+
+ io_zcrx_get_niov_uref(niov);
+ src_offset += copy_size;
+ len -= copy_size;
+ copied += copy_size;
+ }
+
+ return copied ? copied : ret;
+}
+
+static int io_zcrx_copy_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ const skb_frag_t *frag, int off, int len)
+{
+ struct page *page = skb_frag_page(frag);
+ u32 p_off, p_len, t, copied = 0;
+ int ret = 0;
+
+ off += skb_frag_off(frag);
+
+ skb_frag_foreach_page(frag, off, len,
+ page, p_off, p_len, t) {
+ ret = io_zcrx_copy_chunk(req, ifq, NULL, page, p_off, p_len);
+ if (ret < 0)
+ return copied ? copied : ret;
+ copied += ret;
+ }
+ return copied;
+}
+
+static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ const skb_frag_t *frag, int off, int len)
+{
+ struct net_iov *niov;
+
+ if (unlikely(!skb_frag_is_net_iov(frag)))
+ return io_zcrx_copy_frag(req, ifq, frag, off, len);
+
+ niov = netmem_to_net_iov(frag->netmem);
+ if (niov->pp->mp_ops != &io_uring_pp_zc_ops ||
+ niov->pp->mp_priv != ifq)
+ return -EFAULT;
+
+ if (!io_zcrx_queue_cqe(req, niov, ifq, off + skb_frag_off(frag), len))
+ return -ENOSPC;
+
+ /*
+ * Prevent it from being recycled while user is accessing it.
+ * It has to be done before grabbing a user reference.
+ */
+ page_pool_ref_netmem(net_iov_to_netmem(niov));
+ io_zcrx_get_niov_uref(niov);
+ return len;
+}
+
+static int
+io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
+ unsigned int offset, size_t len)
+{
+ struct io_zcrx_args *args = desc->arg.data;
+ struct io_zcrx_ifq *ifq = args->ifq;
+ struct io_kiocb *req = args->req;
+ struct sk_buff *frag_iter;
+ unsigned start, start_off = offset;
+ int i, copy, end, off;
+ int ret = 0;
+
+ len = min_t(size_t, len, desc->count);
+ if (unlikely(args->nr_skbs++ > IO_SKBS_PER_CALL_LIMIT))
+ return -EAGAIN;
+
+ if (unlikely(offset < skb_headlen(skb))) {
+ ssize_t copied;
+ size_t to_copy;
+
+ to_copy = min_t(size_t, skb_headlen(skb) - offset, len);
+ copied = io_zcrx_copy_chunk(req, ifq, skb->data, NULL,
+ offset, to_copy);
+ if (copied < 0) {
+ ret = copied;
+ goto out;
+ }
+ offset += copied;
+ len -= copied;
+ if (!len)
+ goto out;
+ if (offset != skb_headlen(skb))
+ goto out;
+ }
+
+ start = skb_headlen(skb);
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ const skb_frag_t *frag;
+
+ if (WARN_ON(start > offset + len))
+ return -EFAULT;
+
+ frag = &skb_shinfo(skb)->frags[i];
+ end = start + skb_frag_size(frag);
+
+ if (offset < end) {
+ copy = end - offset;
+ if (copy > len)
+ copy = len;
+
+ off = offset - start;
+ ret = io_zcrx_recv_frag(req, ifq, frag, off, copy);
+ if (ret < 0)
+ goto out;
+
+ offset += ret;
+ len -= ret;
+ if (len == 0 || ret != copy)
+ goto out;
+ }
+ start = end;
+ }
+
+ skb_walk_frags(skb, frag_iter) {
+ if (WARN_ON(start > offset + len))
+ return -EFAULT;
+
+ end = start + frag_iter->len;
+ if (offset < end) {
+ copy = end - offset;
+ if (copy > len)
+ copy = len;
+
+ off = offset - start;
+ ret = io_zcrx_recv_skb(desc, frag_iter, off, copy);
+ if (ret < 0)
+ goto out;
+
+ offset += ret;
+ len -= ret;
+ if (len == 0 || ret != copy)
+ goto out;
+ }
+ start = end;
+ }
+
+out:
+ if (offset == start_off)
+ return ret;
+ desc->count -= (offset - start_off);
+ return offset - start_off;
+}
+
+static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ struct sock *sk, int flags,
+ unsigned issue_flags, unsigned int *outlen)
+{
+ unsigned int len = *outlen;
+ struct io_zcrx_args args = {
+ .req = req,
+ .ifq = ifq,
+ .sock = sk->sk_socket,
+ };
+ read_descriptor_t rd_desc = {
+ .count = len ? len : UINT_MAX,
+ .arg.data = &args,
+ };
+ int ret;
+
+ lock_sock(sk);
+ ret = tcp_read_sock(sk, &rd_desc, io_zcrx_recv_skb);
+ if (len && ret > 0)
+ *outlen = len - ret;
+ if (ret <= 0) {
+ if (ret < 0 || sock_flag(sk, SOCK_DONE))
+ goto out;
+ if (sk->sk_err)
+ ret = sock_error(sk);
+ else if (sk->sk_shutdown & RCV_SHUTDOWN)
+ goto out;
+ else if (sk->sk_state == TCP_CLOSE)
+ ret = -ENOTCONN;
+ else
+ ret = -EAGAIN;
+ } else if (unlikely(args.nr_skbs > IO_SKBS_PER_CALL_LIMIT) &&
+ (issue_flags & IO_URING_F_MULTISHOT)) {
+ ret = IOU_REQUEUE;
+ } else if (sock_flag(sk, SOCK_DONE)) {
+ /* Make it to retry until it finally gets 0. */
+ if (issue_flags & IO_URING_F_MULTISHOT)
+ ret = IOU_REQUEUE;
+ else
+ ret = -EAGAIN;
+ }
+out:
+ release_sock(sk);
+ return ret;
+}
+
+int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ struct socket *sock, unsigned int flags,
+ unsigned issue_flags, unsigned int *len)
+{
+ struct sock *sk = sock->sk;
+ const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+ if (prot->recvmsg != tcp_recvmsg)
+ return -EPROTONOSUPPORT;
+
+ sock_rps_record_flow(sk);
+ return io_zcrx_tcp_recvmsg(req, ifq, sk, flags, issue_flags, len);
+}
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
new file mode 100644
index 000000000000..706cc7300780
--- /dev/null
+++ b/io_uring/zcrx.h
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_ZC_RX_H
+#define IOU_ZC_RX_H
+
+#include <linux/io_uring_types.h>
+#include <linux/socket.h>
+#include <net/page_pool/types.h>
+#include <net/net_trackers.h>
+
+struct io_zcrx_area {
+ struct net_iov_area nia;
+ struct io_zcrx_ifq *ifq;
+ atomic_t *user_refs;
+
+ bool is_mapped;
+ u16 area_id;
+ struct page **pages;
+
+ /* freelist */
+ spinlock_t freelist_lock ____cacheline_aligned_in_smp;
+ u32 free_count;
+ u32 *freelist;
+};
+
+struct io_zcrx_ifq {
+ struct io_ring_ctx *ctx;
+ struct io_zcrx_area *area;
+
+ struct io_uring *rq_ring;
+ struct io_uring_zcrx_rqe *rqes;
+ u32 rq_entries;
+ u32 cached_rq_head;
+ spinlock_t rq_lock;
+
+ u32 if_rxq;
+ struct device *dev;
+ struct net_device *netdev;
+ netdevice_tracker netdev_tracker;
+ spinlock_t lock;
+};
+
+#if defined(CONFIG_IO_URING_ZCRX)
+int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+ struct io_uring_zcrx_ifq_reg __user *arg);
+void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx);
+void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx);
+int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ struct socket *sock, unsigned int flags,
+ unsigned issue_flags, unsigned int *len);
+#else
+static inline int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+ struct io_uring_zcrx_ifq_reg __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+static inline void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+ struct socket *sock, unsigned int flags,
+ unsigned issue_flags, unsigned int *len)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags);
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
+#endif