summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--drivers/net/tap.c2
-rw-r--r--drivers/net/tun.c2
-rw-r--r--drivers/net/xen-netback/common.h5
-rw-r--r--drivers/net/xen-netback/interface.c2
-rw-r--r--drivers/net/xen-netback/netback.c11
-rw-r--r--drivers/nvme/host/ioctl.c15
-rw-r--r--drivers/vhost/net.c8
-rw-r--r--include/linux/io_uring.h6
-rw-r--r--include/linux/io_uring/cmd.h24
-rw-r--r--include/linux/io_uring/net.h18
-rw-r--r--include/linux/io_uring_types.h19
-rw-r--r--include/linux/skbuff.h21
-rw-r--r--include/uapi/linux/io_uring.h38
-rw-r--r--io_uring/Makefile15
-rw-r--r--io_uring/alloc_cache.h59
-rw-r--r--io_uring/cancel.c4
-rw-r--r--io_uring/fdinfo.c4
-rw-r--r--io_uring/filetable.c4
-rw-r--r--io_uring/futex.c30
-rw-r--r--io_uring/futex.h5
-rw-r--r--io_uring/io-wq.c67
-rw-r--r--io_uring/io_uring.c665
-rw-r--r--io_uring/io_uring.h33
-rw-r--r--io_uring/kbuf.c318
-rw-r--r--io_uring/kbuf.h64
-rw-r--r--io_uring/memmap.c336
-rw-r--r--io_uring/memmap.h25
-rw-r--r--io_uring/msg_ring.c12
-rw-r--r--io_uring/net.c852
-rw-r--r--io_uring/net.h29
-rw-r--r--io_uring/nop.c26
-rw-r--r--io_uring/notif.c108
-rw-r--r--io_uring/notif.h13
-rw-r--r--io_uring/opdef.c65
-rw-r--r--io_uring/opdef.h9
-rw-r--r--io_uring/poll.c15
-rw-r--r--io_uring/poll.h9
-rw-r--r--io_uring/refs.h7
-rw-r--r--io_uring/register.c3
-rw-r--r--io_uring/rsrc.c47
-rw-r--r--io_uring/rsrc.h13
-rw-r--r--io_uring/rw.c585
-rw-r--r--io_uring/rw.h25
-rw-r--r--io_uring/sqpoll.c8
-rw-r--r--io_uring/timeout.c9
-rw-r--r--io_uring/uring_cmd.c122
-rw-r--r--io_uring/uring_cmd.h8
-rw-r--r--io_uring/waitid.c2
-rw-r--r--mm/nommu.c7
-rw-r--r--net/core/skbuff.c36
-rw-r--r--net/socket.c2
51 files changed, 2050 insertions, 1762 deletions
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 9f0495e8df4d..bfdd3875fe86 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -754,7 +754,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
skb_zcopy_init(skb, msg_control);
} else if (msg_control) {
struct ubuf_info *uarg = msg_control;
- uarg->callback(NULL, uarg, false);
+ uarg->ops->complete(NULL, uarg, false);
}
dev_queue_xmit(skb);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 92da8c03d960..9254bca2813d 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1906,7 +1906,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
skb_zcopy_init(skb, msg_control);
} else if (msg_control) {
struct ubuf_info *uarg = msg_control;
- uarg->callback(NULL, uarg, false);
+ uarg->ops->complete(NULL, uarg, false);
}
skb_reset_network_header(skb);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 1fcbd83f7ff2..17421da139f2 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -390,9 +390,8 @@ bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb);
void xenvif_carrier_on(struct xenvif *vif);
-/* Callback from stack when TX packet can be released */
-void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf,
- bool zerocopy_success);
+/* Callbacks from stack when TX packet can be released */
+extern const struct ubuf_info_ops xenvif_ubuf_ops;
static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
{
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 7cff90aa8d24..65db5f14465f 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -593,7 +593,7 @@ int xenvif_init_queue(struct xenvif_queue *queue)
for (i = 0; i < MAX_PENDING_REQS; i++) {
queue->pending_tx_info[i].callback_struct = (struct ubuf_info_msgzc)
- { { .callback = xenvif_zerocopy_callback },
+ { { .ops = &xenvif_ubuf_ops },
{ { .ctx = NULL,
.desc = i } } };
queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index ef76850d9bcd..bab7e43ea05b 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1156,7 +1156,7 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s
uarg = skb_shinfo(skb)->destructor_arg;
/* increase inflight counter to offset decrement in callback */
atomic_inc(&queue->inflight_packets);
- uarg->callback(NULL, uarg, true);
+ uarg->ops->complete(NULL, uarg, true);
skb_shinfo(skb)->destructor_arg = NULL;
/* Fill the skb with the new (local) frags. */
@@ -1278,8 +1278,9 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
return work_done;
}
-void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base,
- bool zerocopy_success)
+static void xenvif_zerocopy_callback(struct sk_buff *skb,
+ struct ubuf_info *ubuf_base,
+ bool zerocopy_success)
{
unsigned long flags;
pending_ring_idx_t index;
@@ -1312,6 +1313,10 @@ void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base,
xenvif_skb_zerocopy_complete(queue);
}
+const struct ubuf_info_ops xenvif_ubuf_ops = {
+ .complete = xenvif_zerocopy_callback,
+};
+
static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
{
struct gnttab_unmap_grant_ref *gop;
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 3dfd5ae99ae0..499a8bb7cac7 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -423,13 +423,20 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
/*
- * For iopoll, complete it directly.
+ * For iopoll, complete it directly. Note that using the uring_cmd
+ * helper for this is safe only because we check blk_rq_is_poll().
+ * As that returns false if we're NOT on a polled queue, then it's
+ * safe to use the polled completion helper.
+ *
* Otherwise, move the completion to task work.
*/
- if (blk_rq_is_poll(req))
- nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
- else
+ if (blk_rq_is_poll(req)) {
+ if (pdu->bio)
+ blk_rq_unmap_user(pdu->bio);
+ io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
+ } else {
io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
+ }
return RQ_END_IO_FREE;
}
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c64ded183f8d..f16279351db5 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -380,7 +380,7 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
}
}
-static void vhost_zerocopy_callback(struct sk_buff *skb,
+static void vhost_zerocopy_complete(struct sk_buff *skb,
struct ubuf_info *ubuf_base, bool success)
{
struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base);
@@ -408,6 +408,10 @@ static void vhost_zerocopy_callback(struct sk_buff *skb,
rcu_read_unlock_bh();
}
+static const struct ubuf_info_ops vhost_ubuf_ops = {
+ .complete = vhost_zerocopy_complete,
+};
+
static inline unsigned long busy_clock(void)
{
return local_clock() >> 10;
@@ -879,7 +883,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
ubuf->ctx = nvq->ubufs;
ubuf->desc = nvq->upend_idx;
- ubuf->ubuf.callback = vhost_zerocopy_callback;
+ ubuf->ubuf.ops = &vhost_ubuf_ops;
ubuf->ubuf.flags = SKBFL_ZEROCOPY_FRAG;
refcount_set(&ubuf->ubuf.refcnt, 1);
msg.msg_control = &ctl;
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 68ed6697fece..e123d5e17b52 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -11,7 +11,6 @@ void __io_uring_cancel(bool cancel_all);
void __io_uring_free(struct task_struct *tsk);
void io_uring_unreg_ringfd(void);
const char *io_uring_get_opcode(u8 opcode);
-int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
bool io_is_uring_fops(struct file *file);
static inline void io_uring_files_cancel(void)
@@ -45,11 +44,6 @@ static inline const char *io_uring_get_opcode(u8 opcode)
{
return "";
}
-static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
- unsigned int issue_flags)
-{
- return -EOPNOTSUPP;
-}
static inline bool io_is_uring_fops(struct file *file)
{
return false;
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index e453a997c060..447fbfd32215 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -26,12 +26,25 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
#if defined(CONFIG_IO_URING)
int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
struct iov_iter *iter, void *ioucmd);
+
+/*
+ * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd
+ * and the corresponding io_uring request.
+ *
+ * Note: the caller should never hard code @issue_flags and is only allowed
+ * to pass the mask provided by the core io_uring code.
+ */
void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
unsigned issue_flags);
+
void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *, unsigned),
unsigned flags);
+/*
+ * Note: the caller should never hard code @issue_flags and only use the
+ * mask provided by the core io_uring code.
+ */
void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
unsigned int issue_flags);
@@ -56,6 +69,17 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
}
#endif
+/*
+ * Polled completions must ensure they are coming from a poll queue, and
+ * hence are completed inside the usual poll handling loops.
+ */
+static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd,
+ ssize_t ret, ssize_t res2)
+{
+ lockdep_assert(in_task());
+ io_uring_cmd_done(ioucmd, ret, res2, 0);
+}
+
/* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *, unsigned))
diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h
new file mode 100644
index 000000000000..b58f39fed4d5
--- /dev/null
+++ b/include/linux/io_uring/net.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_NET_H
+#define _LINUX_IO_URING_NET_H
+
+struct io_uring_cmd;
+
+#if defined(CONFIG_IO_URING)
+int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
+
+#else
+static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
+ unsigned int issue_flags)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
+#endif
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index ac333ea81d31..7a6b190c7da7 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -205,6 +205,7 @@ struct io_submit_state {
bool plug_started;
bool need_plug;
+ bool cq_flush;
unsigned short submit_nr;
unsigned int cqes_count;
struct blk_plug plug;
@@ -219,7 +220,7 @@ struct io_ev_fd {
};
struct io_alloc_cache {
- struct io_wq_work_node list;
+ void **entries;
unsigned int nr_cached;
unsigned int max_cached;
size_t elem_size;
@@ -299,6 +300,8 @@ struct io_ring_ctx {
struct io_hash_table cancel_table_locked;
struct io_alloc_cache apoll_cache;
struct io_alloc_cache netmsg_cache;
+ struct io_alloc_cache rw_cache;
+ struct io_alloc_cache uring_cache;
/*
* Any cancelable uring_cmd is added to this list in
@@ -341,14 +344,8 @@ struct io_ring_ctx {
unsigned cq_last_tm_flush;
} ____cacheline_aligned_in_smp;
- struct io_uring_cqe completion_cqes[16];
-
spinlock_t completion_lock;
- /* IRQ completion list, under ->completion_lock */
- unsigned int locked_free_nr;
- struct io_wq_work_list locked_free_list;
-
struct list_head io_buffers_comp;
struct list_head cq_overflow_list;
struct io_hash_table cancel_table;
@@ -371,9 +368,6 @@ struct io_ring_ctx {
struct list_head io_buffers_cache;
- /* deferred free list, protected by ->uring_lock */
- struct hlist_head io_buf_list;
-
/* Keep this last, we don't need it for the fast path */
struct wait_queue_head poll_wq;
struct io_restriction restrictions;
@@ -438,8 +432,6 @@ struct io_ring_ctx {
};
struct io_tw_state {
- /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */
- bool locked;
};
enum {
@@ -480,6 +472,7 @@ enum {
REQ_F_CAN_POLL_BIT,
REQ_F_BL_EMPTY_BIT,
REQ_F_BL_NO_RECYCLE_BIT,
+ REQ_F_BUFFERS_COMMIT_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -558,6 +551,8 @@ enum {
REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT),
/* don't recycle provided buffers for this request */
REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT),
+ /* buffer ring head needs incrementing on put */
+ REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
};
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4ff48eda3f64..1cc72c370190 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -527,6 +527,13 @@ enum {
#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \
SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS)
+struct ubuf_info_ops {
+ void (*complete)(struct sk_buff *, struct ubuf_info *,
+ bool zerocopy_success);
+ /* has to be compatible with skb_zcopy_set() */
+ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg);
+};
+
/*
* The callback notifies userspace to release buffers when skb DMA is done in
* lower device, the skb last reference should be 0 when calling this.
@@ -536,8 +543,7 @@ enum {
* The desc field is used to track userspace buffer index.
*/
struct ubuf_info {
- void (*callback)(struct sk_buff *, struct ubuf_info *,
- bool zerocopy_success);
+ const struct ubuf_info_ops *ops;
refcount_t refcnt;
u8 flags;
};
@@ -1662,14 +1668,13 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
}
#endif
+extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops;
+
struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
struct ubuf_info *uarg);
void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
-void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
- bool success);
-
int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, struct iov_iter *from,
size_t length);
@@ -1757,13 +1762,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
static inline void net_zcopy_put(struct ubuf_info *uarg)
{
if (uarg)
- uarg->callback(NULL, uarg, true);
+ uarg->ops->complete(NULL, uarg, true);
}
static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref)
{
if (uarg) {
- if (uarg->callback == msg_zerocopy_callback)
+ if (uarg->ops == &msg_zerocopy_ubuf_ops)
msg_zerocopy_put_abort(uarg, have_uref);
else if (have_uref)
net_zcopy_put(uarg);
@@ -1777,7 +1782,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
if (uarg) {
if (!skb_zcopy_is_nouarg(skb))
- uarg->callback(skb, uarg, zerocopy_success);
+ uarg->ops->complete(skb, uarg, zerocopy_success);
skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
}
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 7bd10201a02b..994bf7af0efe 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -72,6 +72,7 @@ struct io_uring_sqe {
__u32 waitid_flags;
__u32 futex_flags;
__u32 install_fd_flags;
+ __u32 nop_flags;
};
__u64 user_data; /* data to be passed back at completion time */
/* pack this to avoid bogus arm OABI complaints */
@@ -115,7 +116,7 @@ struct io_uring_sqe {
*/
#define IORING_FILE_INDEX_ALLOC (~0U)
-enum {
+enum io_uring_sqe_flags_bit {
IOSQE_FIXED_FILE_BIT,
IOSQE_IO_DRAIN_BIT,
IOSQE_IO_LINK_BIT,
@@ -351,11 +352,20 @@ enum io_uring_op {
* 0 is reported if zerocopy was actually possible.
* IORING_NOTIF_USAGE_ZC_COPIED if data was copied
* (at least partially).
+ *
+ * IORING_RECVSEND_BUNDLE Used with IOSQE_BUFFER_SELECT. If set, send or
+ * recv will grab as many buffers from the buffer
+ * group ID given and send them all. The completion
+ * result will be the number of buffers send, with
+ * the starting buffer ID in cqe->flags as per
+ * usual for provided buffer usage. The buffers
+ * will be contigious from the starting buffer ID.
*/
#define IORING_RECVSEND_POLL_FIRST (1U << 0)
#define IORING_RECV_MULTISHOT (1U << 1)
#define IORING_RECVSEND_FIXED_BUF (1U << 2)
#define IORING_SEND_ZC_REPORT_USAGE (1U << 3)
+#define IORING_RECVSEND_BUNDLE (1U << 4)
/*
* cqe.res for IORING_CQE_F_NOTIF if
@@ -370,11 +380,13 @@ enum io_uring_op {
* accept flags stored in sqe->ioprio
*/
#define IORING_ACCEPT_MULTISHOT (1U << 0)
+#define IORING_ACCEPT_DONTWAIT (1U << 1)
+#define IORING_ACCEPT_POLL_FIRST (1U << 2)
/*
* IORING_OP_MSG_RING command types, stored in sqe->addr
*/
-enum {
+enum io_uring_msg_ring_flags {
IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */
IORING_MSG_SEND_FD, /* send a registered fd to another ring */
};
@@ -397,6 +409,13 @@ enum {
#define IORING_FIXED_FD_NO_CLOEXEC (1U << 0)
/*
+ * IORING_OP_NOP flags (sqe->nop_flags)
+ *
+ * IORING_NOP_INJECT_RESULT Inject result from sqe->result
+ */
+#define IORING_NOP_INJECT_RESULT (1U << 0)
+
+/*
* IO completion data structure (Completion Queue Entry)
*/
struct io_uring_cqe {
@@ -425,9 +444,7 @@ struct io_uring_cqe {
#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2)
#define IORING_CQE_F_NOTIF (1U << 3)
-enum {
- IORING_CQE_BUFFER_SHIFT = 16,
-};
+#define IORING_CQE_BUFFER_SHIFT 16
/*
* Magic offsets for the application to mmap the data it needs
@@ -522,11 +539,12 @@ struct io_uring_params {
#define IORING_FEAT_CQE_SKIP (1U << 11)
#define IORING_FEAT_LINKED_FILE (1U << 12)
#define IORING_FEAT_REG_REG_RING (1U << 13)
+#define IORING_FEAT_RECVSEND_BUNDLE (1U << 14)
/*
* io_uring_register(2) opcodes and arguments
*/
-enum {
+enum io_uring_register_op {
IORING_REGISTER_BUFFERS = 0,
IORING_UNREGISTER_BUFFERS = 1,
IORING_REGISTER_FILES = 2,
@@ -583,7 +601,7 @@ enum {
};
/* io-wq worker categories */
-enum {
+enum io_wq_type {
IO_WQ_BOUND,
IO_WQ_UNBOUND,
};
@@ -688,7 +706,7 @@ struct io_uring_buf_ring {
* IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT)
* to get a virtual mapping for the ring.
*/
-enum {
+enum io_uring_register_pbuf_ring_flags {
IOU_PBUF_RING_MMAP = 1,
};
@@ -719,7 +737,7 @@ struct io_uring_napi {
/*
* io_uring_restriction->opcode values
*/
-enum {
+enum io_uring_register_restriction_op {
/* Allow an io_uring_register(2) opcode */
IORING_RESTRICTION_REGISTER_OP = 0,
@@ -775,7 +793,7 @@ struct io_uring_recvmsg_out {
/*
* Argument for IORING_OP_URING_CMD when file is a socket
*/
-enum {
+enum io_uring_socket_op {
SOCKET_URING_OP_SIOCINQ = 0,
SOCKET_URING_OP_SIOCOUTQ,
SOCKET_URING_OP_GETSOCKOPT,
diff --git a/io_uring/Makefile b/io_uring/Makefile
index 2e1d4e03799c..fc1b23c524e8 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -2,13 +2,14 @@
#
# Makefile for io_uring
-obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \
- sync.o advise.o filetable.o \
- openclose.o uring_cmd.o epoll.o \
- statx.o net.o msg_ring.o timeout.o \
- sqpoll.o fdinfo.o tctx.o poll.o \
- cancel.o kbuf.o rsrc.o rw.o opdef.o \
- notif.o waitid.o register.o truncate.o
+obj-$(CONFIG_IO_URING) += io_uring.o opdef.o kbuf.o rsrc.o notif.o \
+ tctx.o filetable.o rw.o net.o poll.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
obj-$(CONFIG_IO_WQ) += io-wq.o
obj-$(CONFIG_FUTEX) += futex.o
obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
index bf2fb26a6539..b7a38a2069cf 100644
--- a/io_uring/alloc_cache.h
+++ b/io_uring/alloc_cache.h
@@ -4,63 +4,58 @@
/*
* Don't allow the cache to grow beyond this size.
*/
-#define IO_ALLOC_CACHE_MAX 512
-
-struct io_cache_entry {
- struct io_wq_work_node node;
-};
+#define IO_ALLOC_CACHE_MAX 128
static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
- struct io_cache_entry *entry)
+ void *entry)
{
if (cache->nr_cached < cache->max_cached) {
- cache->nr_cached++;
- wq_stack_add_head(&entry->node, &cache->list);
- kasan_mempool_poison_object(entry);
+ if (!kasan_mempool_poison_object(entry))
+ return false;
+ cache->entries[cache->nr_cached++] = entry;
return true;
}
return false;
}
-static inline bool io_alloc_cache_empty(struct io_alloc_cache *cache)
-{
- return !cache->list.next;
-}
-
-static inline struct io_cache_entry *io_alloc_cache_get(struct io_alloc_cache *cache)
+static inline void *io_alloc_cache_get(struct io_alloc_cache *cache)
{
- if (cache->list.next) {
- struct io_cache_entry *entry;
+ if (cache->nr_cached) {
+ void *entry = cache->entries[--cache->nr_cached];
- entry = container_of(cache->list.next, struct io_cache_entry, node);
kasan_mempool_unpoison_object(entry, cache->elem_size);
- cache->list.next = cache->list.next->next;
- cache->nr_cached--;
return entry;
}
return NULL;
}
-static inline void io_alloc_cache_init(struct io_alloc_cache *cache,
+/* returns false if the cache was initialized properly */
+static inline bool io_alloc_cache_init(struct io_alloc_cache *cache,
unsigned max_nr, size_t size)
{
- cache->list.next = NULL;
- cache->nr_cached = 0;
- cache->max_cached = max_nr;
- cache->elem_size = size;
+ cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL);
+ if (cache->entries) {
+ cache->nr_cached = 0;
+ cache->max_cached = max_nr;
+ cache->elem_size = size;
+ return false;
+ }
+ return true;
}
static inline void io_alloc_cache_free(struct io_alloc_cache *cache,
- void (*free)(struct io_cache_entry *))
+ void (*free)(const void *))
{
- while (1) {
- struct io_cache_entry *entry = io_alloc_cache_get(cache);
+ void *entry;
+
+ if (!cache->entries)
+ return;
- if (!entry)
- break;
+ while ((entry = io_alloc_cache_get(cache)) != NULL)
free(entry);
- }
- cache->nr_cached = 0;
+
+ kvfree(cache->entries);
+ cache->entries = NULL;
}
#endif
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index acfcdd7f059a..a6e58a20efdd 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -184,9 +184,7 @@ static int __io_async_cancel(struct