Merge tag 'io_uring-worker.v3-2021-02-25' of git://git.kernel.dk/linux-block

Pull io_uring thread rewrite from Jens Axboe:
 "This converts the io-wq workers to be forked off the tasks in question
  instead of being kernel threads that assume various bits of the
  original task identity.

  This kills > 400 lines of code from io_uring/io-wq, and it's the worst
  part of the code. We've had several bugs in this area, and the worry
  is always that we could be missing some pieces for file types doing
  unusual things (recent /dev/tty example comes to mind, userfaultfd
  reads installing file descriptors is another fun one... - both of
  which need special handling, and I bet it's not the last weird oddity
  we'll find).

  With these identical workers, we can have full confidence that we're
  never missing anything. That, in itself, is a huge win. Outside of
  that, it's also more efficient since we're not wasting space and code
  on tracking state, or switching between different states.

  I'm sure we're going to find little things to patch up after this
  series, but testing has been pretty thorough, from the usual
  regression suite to production. Any issue that may crop up should be
  manageable.

  There's also a nice series of further reductions we can do on top of
  this, but I wanted to get the meat of it out sooner rather than later.
  The general worry here isn't that it's fundamentally broken. Most of
  the little issues we've found over the last week have been related to
  just changes in how thread startup/exit is done, since that's the main
  difference between using kthreads and these kinds of threads. In fact,
  if all goes according to plan, I want to get this into the 5.10 and
  5.11 stable branches as well.

  That said, the changes outside of io_uring/io-wq are:

   - arch setup, simple one-liner to each arch copy_thread()
     implementation.

   - Removal of net and proc restrictions for io_uring, they are no
     longer needed or useful"

* tag 'io_uring-worker.v3-2021-02-25' of git://git.kernel.dk/linux-block: (30 commits)
  io-wq: remove now unused IO_WQ_BIT_ERROR
  io_uring: fix SQPOLL thread handling over exec
  io-wq: improve manager/worker handling over exec
  io_uring: ensure SQPOLL startup is triggered before error shutdown
  io-wq: make buffered file write hashed work map per-ctx
  io-wq: fix race around io_worker grabbing
  io-wq: fix races around manager/worker creation and task exit
  io_uring: ensure io-wq context is always destroyed for tasks
  arch: ensure parisc/powerpc handle PF_IO_WORKER in copy_thread()
  io_uring: cleanup ->user usage
  io-wq: remove nr_process accounting
  io_uring: flag new native workers with IORING_FEAT_NATIVE_WORKERS
  net: remove cmsg restriction from io_uring based send/recvmsg calls
  Revert "proc: don't allow async path resolution of /proc/self components"
  Revert "proc: don't allow async path resolution of /proc/thread-self components"
  io_uring: move SQPOLL thread io-wq forked worker
  io-wq: make io_wq_fork_thread() available to other users
  io-wq: only remove worker from free_list, if it was there
  io_uring: remove io_identity
  io_uring: remove any grabbing of context
  ...

4 files changed, 6 insertions, 23 deletions

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 2eb6d19de336..51ede771cd99 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -5,23 +5,6 @@
 #include <linux/sched.h>
 #include <linux/xarray.h>
 
-struct io_identity {
-	struct files_struct		*files;
-	struct mm_struct		*mm;
-#ifdef CONFIG_BLK_CGROUP
-	struct cgroup_subsys_state	*blkcg_css;
-#endif
-	const struct cred		*creds;
-	struct nsproxy			*nsproxy;
-	struct fs_struct		*fs;
-	unsigned long			fsize;
-#ifdef CONFIG_AUDIT
-	kuid_t				loginuid;
-	unsigned int			sessionid;
-#endif
-	refcount_t			count;
-};
-
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
@@ -36,9 +19,8 @@ struct io_uring_task {
 	struct xarray		xa;
 	struct wait_queue_head	wait;
 	struct file		*last;
+	void			*io_wq;
 	struct percpu_counter	inflight;
-	struct io_identity	__identity;
-	struct io_identity	*identity;
 	atomic_t		in_idle;
 	bool			sqpoll;
 
@@ -61,7 +43,7 @@ static inline void io_uring_task_cancel(void)
 }
 static inline void io_uring_files_cancel(struct files_struct *files)
 {
-	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+	if (current->io_uring)
 		__io_uring_files_cancel(files);
 }
 static inline void io_uring_free(struct task_struct *tsk)
diff --git a/include/linux/net.h b/include/linux/net.h
index 9e2324efc26a..ba736b457a06 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -42,8 +42,6 @@ struct net;
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
 
-#define PROTO_CMSG_DATA_ONLY	0x0001
-
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**
  * enum sock_type - Socket types
@@ -138,7 +136,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 
 struct proto_ops {
 	int		family;
-	unsigned int	flags;
 	struct module	*owner;
 	int		(*release)   (struct socket *sock);
 	int		(*bind)	     (struct socket *sock,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26f499810dfa..ef00bb22164c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -895,6 +895,9 @@ struct task_struct {
 	/* CLONE_CHILD_CLEARTID: */
 	int __user			*clear_child_tid;
 
+	/* PF_IO_WORKER */
+	void				*pf_io_worker;
+
 	u64				utime;
 	u64				stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ac4e1738a9af..2514eb6b1cf2 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -262,6 +262,7 @@ struct io_uring_params {
 #define IORING_FEAT_POLL_32BITS 	(1U << 6)
 #define IORING_FEAT_SQPOLL_NONFIXED	(1U << 7)
 #define IORING_FEAT_EXT_ARG		(1U << 8)
+#define IORING_FEAT_NATIVE_WORKERS	(1U << 9)
 
 /*
  * io_uring_register(2) opcodes and arguments