Merge branch 'for-7.4/io_uring' into for-next

* for-7.4/io_uring: (21 commits)
  io_uring/io-wq: don't call try_to_wake_up() twice in io_wq_worker_wake()
  io_uring: cleanup the io_uring_attr_pi definition
  io_uring: cleanup __io_prep_rw
  io_uring/memmap: fix non-compound alloc fallback with memcg accounting
  io_uring: wait for in-flight requests on ring release
  io_uring: drop registered files and buffers at release time
  io_uring: run cancelations synchronously on ring release
  io_uring/cancel: cancel and wait for all requests on process exit
  io_uring/notif: count pending zerocopy notifications per ring
  io_uring/uring_cmd: only cancel requests of the given task
  io_uring: put request files before posting the completions
  io_uring/rw: don't reap io-wq IOPOLL completions while io-wq has a reference
  io_uring: post io-wq completions from the last request reference
  io_uring/io-wq: put the request file before posting a completion
  io_uring/io-wq: release raw spinlock before calling wake_up()
  io_uring/rsrc: fix accounting for cloned buffers with huge pages
  io_uring: check for room before posting the dummy skip CQE
  io_uring/fdinfo: ignore IORING_CQE_F_32 in last CQ array slot
  nvme/ioctl: call io_uring_cmd_set_res32() in ->end_io()
  io_uring/cmd: split io_uring_cmd_set_res() from io_uring_cmd_done()
  ...

4 files changed, 70 insertions, 13 deletions

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index d1aa4edfc2a5..505caa99c621 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -2,10 +2,42 @@
 #ifndef _LINUX_IO_URING_H
 #define _LINUX_IO_URING_H
 
+#include <linux/io_uring_types.h>
 #include <linux/sched.h>
 #include <linux/xarray.h>
 #include <uapi/linux/io_uring.h>
 
+static inline void req_set_fail(struct io_kiocb *req)
+{
+	req->flags |= REQ_F_FAIL;
+	if (req->flags & REQ_F_CQE_SKIP) {
+		req->flags &= ~REQ_F_CQE_SKIP;
+		req->flags |= REQ_F_SKIP_LINK_CQES;
+	}
+}
+
+static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags;
+}
+
+static inline u32 ctx_cqe32_flags(struct io_ring_ctx *ctx)
+{
+	if (ctx->flags & IORING_SETUP_CQE_MIXED)
+		return IORING_CQE_F_32;
+	return 0;
+}
+
+static inline void io_req_set_res32(struct io_kiocb *req, s32 res, u32 cflags,
+				    __u64 extra1, __u64 extra2)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags | ctx_cqe32_flags(req->ctx);
+	req->big_cqe.extra1 = extra1;
+	req->big_cqe.extra2 = extra2;
+}
+
 #if defined(CONFIG_IO_URING)
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 42801f0b6456..e18d4af62e1a 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -3,6 +3,7 @@
 #define _LINUX_IO_URING_CMD_H
 
 #include <uapi/linux/io_uring.h>
+#include <linux/io_uring.h>
 #include <linux/io_uring_types.h>
 #include <linux/blk-mq.h>
 
@@ -41,6 +42,24 @@ static inline void io_uring_cmd_private_sz_check(size_t cmd_sz)
 	((pdu_type *)&(cmd)->pdu) \
 )
 
+static inline void io_uring_cmd_set_res(struct io_uring_cmd *cmd, s32 ret)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+}
+
+static inline void io_uring_cmd_set_res32(struct io_uring_cmd *cmd, s32 ret, u64 res2)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res32(req, ret, 0, res2, 0);
+}
+
 #if defined(CONFIG_IO_URING)
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 			      struct iov_iter *iter,
@@ -56,11 +75,12 @@ int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
  * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd
  * and the corresponding io_uring request.
  *
+ * io_uring_cmd_set_res()/io_uring_cmd_set_res32() must be called first.
+ *
  * 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, s32 ret, u64 res2,
-			 unsigned issue_flags, bool is_cqe32);
+void __io_uring_cmd_done(struct io_uring_cmd *, unsigned issue_flags);
 
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 			    io_req_tw_func_t task_work_cb,
@@ -116,8 +136,8 @@ static inline int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
 {
 	return -EOPNOTSUPP;
 }
-static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret,
-		u64 ret2, unsigned issue_flags, bool is_cqe32)
+static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd,
+				       unsigned issue_flags)
 {
 }
 static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
@@ -205,13 +225,15 @@ static inline void *io_uring_cmd_ctx_handle(struct io_uring_cmd *cmd)
 static inline void io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret,
 				     unsigned issue_flags)
 {
-	return __io_uring_cmd_done(ioucmd, ret, 0, issue_flags, false);
+	io_uring_cmd_set_res(ioucmd, ret);
+	__io_uring_cmd_done(ioucmd, issue_flags);
 }
 
 static inline void io_uring_cmd_done32(struct io_uring_cmd *ioucmd, s32 ret,
 				       u64 res2, unsigned issue_flags)
 {
-	return __io_uring_cmd_done(ioucmd, ret, res2, issue_flags, true);
+	io_uring_cmd_set_res32(ioucmd, ret, res2);
+	__io_uring_cmd_done(ioucmd, issue_flags);
 }
 
 #endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 8126af652845..53941c6a6875 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -524,6 +524,8 @@ struct io_ring_ctx {
 
 	/* protected by ->completion_lock */
 	unsigned			nr_req_allocated;
+	/* pending SEND_ZC notifications, protected by ->uring_lock */
+	unsigned			nr_notifs;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	struct list_head	napi_list;	/* track busy poll napi_id */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 909fb7aea638..b42b66b424a7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -121,14 +121,15 @@ struct io_uring_sqe {
 
 /* sqe->attr_type_mask flags */
 #define IORING_RW_ATTR_FLAG_PI	(1U << 0)
-/* PI attribute information */
+
+/* PI attribute information in sqe->attr_ptr for IORING_RW_ATTR_FLAG_PI: */
 struct io_uring_attr_pi {
-		__u16	flags;
-		__u16	app_tag;
-		__u32	len;
-		__u64	addr;
-		__u64	seed;
-		__u64	rsvd;
+	__u16	flags;
+	__u16	app_tag;
+	__u32	len;
+	__u64	addr;
+	__u64	seed;
+	__u64	rsvd;
 };
 
 /*