Merge tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - As per (valid) complaint in the last merge window, fs/io_uring.c has
   grown quite large these days. io_uring isn't really tied to fs
   either, as it supports a wide variety of functionality outside of
   that.

   Move the code to io_uring/ and split it into files that either
   implement a specific request type, and split some code into helpers
   as well. The code is organized a lot better like this, and io_uring.c
   is now < 4K LOC (me).

 - Deprecate the epoll_ctl opcode. It'll still work, just trigger a
   warning once if used. If we don't get any complaints on this, and I
   don't expect any, then we can fully remove it in a future release
   (me).

 - Improve the cancel hash locking (Hao)

 - kbuf cleanups (Hao)

 - Efficiency improvements to the task_work handling (Dylan, Pavel)

 - Provided buffer improvements (Dylan)

 - Add support for recv/recvmsg multishot support. This is similar to
   the accept (or poll) support for have for multishot, where a single
   SQE can trigger everytime data is received. For applications that
   expect to do more than a few receives on an instantiated socket, this
   greatly improves efficiency (Dylan).

 - Efficiency improvements for poll handling (Pavel)

 - Poll cancelation improvements (Pavel)

 - Allow specifiying a range for direct descriptor allocations (Pavel)

 - Cleanup the cqe32 handling (Pavel)

 - Move io_uring types to greatly cleanup the tracing (Pavel)

 - Tons of great code cleanups and improvements (Pavel)

 - Add a way to do sync cancelations rather than through the sqe -> cqe
   interface, as that's a lot easier to use for some use cases (me).

 - Add support to IORING_OP_MSG_RING for sending direct descriptors to a
   different ring. This avoids the usually problematic SCM case, as we
   disallow those. (me)

 - Make the per-command alloc cache we use for apoll generic, place
   limits on it, and use it for netmsg as well (me).

 - Various cleanups (me, Michal, Gustavo, Uros)

* tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block: (172 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

2 files changed, 33 insertions, 43 deletions

diff --git a/net/compat.c b/net/compat.c
index 210fc3b4d0d8..ed880729d159 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -34,20 +34,15 @@
 #include <net/compat.h>
 
 int __get_compat_msghdr(struct msghdr *kmsg,
-			struct compat_msghdr __user *umsg,
-			struct sockaddr __user **save_addr,
-			compat_uptr_t *ptr, compat_size_t *len)
+			struct compat_msghdr *msg,
+			struct sockaddr __user **save_addr)
 {
-	struct compat_msghdr msg;
 	ssize_t err;
 
-	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
-		return -EFAULT;
-
-	kmsg->msg_flags = msg.msg_flags;
-	kmsg->msg_namelen = msg.msg_namelen;
+	kmsg->msg_flags = msg->msg_flags;
+	kmsg->msg_namelen = msg->msg_namelen;
 
-	if (!msg.msg_name)
+	if (!msg->msg_name)
 		kmsg->msg_namelen = 0;
 
 	if (kmsg->msg_namelen < 0)
@@ -57,15 +52,15 @@ int __get_compat_msghdr(struct msghdr *kmsg,
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 
 	kmsg->msg_control_is_user = true;
-	kmsg->msg_control_user = compat_ptr(msg.msg_control);
-	kmsg->msg_controllen = msg.msg_controllen;
+	kmsg->msg_control_user = compat_ptr(msg->msg_control);
+	kmsg->msg_controllen = msg->msg_controllen;
 
 	if (save_addr)
-		*save_addr = compat_ptr(msg.msg_name);
+		*save_addr = compat_ptr(msg->msg_name);
 
-	if (msg.msg_name && kmsg->msg_namelen) {
+	if (msg->msg_name && kmsg->msg_namelen) {
 		if (!save_addr) {
-			err = move_addr_to_kernel(compat_ptr(msg.msg_name),
+			err = move_addr_to_kernel(compat_ptr(msg->msg_name),
 						  kmsg->msg_namelen,
 						  kmsg->msg_name);
 			if (err < 0)
@@ -76,12 +71,10 @@ int __get_compat_msghdr(struct msghdr *kmsg,
 		kmsg->msg_namelen = 0;
 	}
 
-	if (msg.msg_iovlen > UIO_MAXIOV)
+	if (msg->msg_iovlen > UIO_MAXIOV)
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
-	*ptr = msg.msg_iov;
-	*len = msg.msg_iovlen;
 	return 0;
 }
 
@@ -90,15 +83,17 @@ int get_compat_msghdr(struct msghdr *kmsg,
 		      struct sockaddr __user **save_addr,
 		      struct iovec **iov)
 {
-	compat_uptr_t ptr;
-	compat_size_t len;
+	struct compat_msghdr msg;
 	ssize_t err;
 
-	err = __get_compat_msghdr(kmsg, umsg, save_addr, &ptr, &len);
+	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
+		return -EFAULT;
+
+	err = __get_compat_msghdr(kmsg, &msg, save_addr);
 	if (err)
 		return err;
 
-	err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len,
+	err = import_iovec(save_addr ? READ : WRITE, compat_ptr(msg.msg_iov), msg.msg_iovlen,
 			   UIO_FASTIOV, iov, &kmsg->msg_iter);
 	return err < 0 ? err : 0;
 }
diff --git a/net/socket.c b/net/socket.c
index 96300cdc0625..843545c21ec2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2358,25 +2358,20 @@ struct used_address {
 	unsigned int name_len;
 };
 
-int __copy_msghdr_from_user(struct msghdr *kmsg,
-			    struct user_msghdr __user *umsg,
-			    struct sockaddr __user **save_addr,
-			    struct iovec __user **uiov, size_t *nsegs)
+int __copy_msghdr(struct msghdr *kmsg,
+		  struct user_msghdr *msg,
+		  struct sockaddr __user **save_addr)
 {
-	struct user_msghdr msg;
 	ssize_t err;
 
-	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
-		return -EFAULT;
-
 	kmsg->msg_control_is_user = true;
 	kmsg->msg_get_inq = 0;
-	kmsg->msg_control_user = msg.msg_control;
-	kmsg->msg_controllen = msg.msg_controllen;
-	kmsg->msg_flags = msg.msg_flags;
+	kmsg->msg_control_user = msg->msg_control;
+	kmsg->msg_controllen = msg->msg_controllen;
+	kmsg->msg_flags = msg->msg_flags;
 
-	kmsg->msg_namelen = msg.msg_namelen;
-	if (!msg.msg_name)
+	kmsg->msg_namelen = msg->msg_namelen;
+	if (!msg->msg_name)
 		kmsg->msg_namelen = 0;
 
 	if (kmsg->msg_namelen < 0)
@@ -2386,11 +2381,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 
 	if (save_addr)
-		*save_addr = msg.msg_name;
+		*save_addr = msg->msg_name;
 
-	if (msg.msg_name && kmsg->msg_namelen) {
+	if (msg->msg_name && kmsg->msg_namelen) {
 		if (!save_addr) {
-			err = move_addr_to_kernel(msg.msg_name,
+			err = move_addr_to_kernel(msg->msg_name,
 						  kmsg->msg_namelen,
 						  kmsg->msg_name);
 			if (err < 0)
@@ -2401,12 +2396,10 @@ int __copy_msghdr_from_user(struct msghdr *kmsg,
 		kmsg->msg_namelen = 0;
 	}
 
-	if (msg.msg_iovlen > UIO_MAXIOV)
+	if (msg->msg_iovlen > UIO_MAXIOV)
 		return -EMSGSIZE;
 
 	kmsg->msg_iocb = NULL;
-	*uiov = msg.msg_iov;
-	*nsegs = msg.msg_iovlen;
 	return 0;
 }
 
@@ -2418,8 +2411,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 	struct user_msghdr msg;
 	ssize_t err;
 
-	err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov,
-					&msg.msg_iovlen);
+	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
+		return -EFAULT;
+
+	err = __copy_msghdr(kmsg, &msg, save_addr);
 	if (err)
 		return err;