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
  ...

1 files changed, 315 insertions, 0 deletions

diff --git a/io_uring/cancel.c b/io_uring/cancel.c
new file mode 100644
index 000000000000..8435a1eba59a
--- /dev/null
+++ b/io_uring/cancel.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "tctx.h"
+#include "poll.h"
+#include "timeout.h"
+#include "cancel.h"
+
+struct io_cancel {
+	struct file			*file;
+	u64				addr;
+	u32				flags;
+	s32				fd;
+};
+
+#define CANCEL_FLAGS	(IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \
+			 IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED)
+
+static bool io_cancel_cb(struct io_wq_work *work, void *data)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+	struct io_cancel_data *cd = data;
+
+	if (req->ctx != cd->ctx)
+		return false;
+	if (cd->flags & IORING_ASYNC_CANCEL_ANY) {
+		;
+	} else if (cd->flags & IORING_ASYNC_CANCEL_FD) {
+		if (req->file != cd->file)
+			return false;
+	} else {
+		if (req->cqe.user_data != cd->data)
+			return false;
+	}
+	if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) {
+		if (cd->seq == req->work.cancel_seq)
+			return false;
+		req->work.cancel_seq = cd->seq;
+	}
+	return true;
+}
+
+static int io_async_cancel_one(struct io_uring_task *tctx,
+			       struct io_cancel_data *cd)
+{
+	enum io_wq_cancel cancel_ret;
+	int ret = 0;
+	bool all;
+
+	if (!tctx || !tctx->io_wq)
+		return -ENOENT;
+
+	all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY);
+	cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all);
+	switch (cancel_ret) {
+	case IO_WQ_CANCEL_OK:
+		ret = 0;
+		break;
+	case IO_WQ_CANCEL_RUNNING:
+		ret = -EALREADY;
+		break;
+	case IO_WQ_CANCEL_NOTFOUND:
+		ret = -ENOENT;
+		break;
+	}
+
+	return ret;
+}
+
+int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,
+		  unsigned issue_flags)
+{
+	struct io_ring_ctx *ctx = cd->ctx;
+	int ret;
+
+	WARN_ON_ONCE(!io_wq_current_is_worker() && tctx != current->io_uring);
+
+	ret = io_async_cancel_one(tctx, cd);
+	/*
+	 * Fall-through even for -EALREADY, as we may have poll armed
+	 * that need unarming.
+	 */
+	if (!ret)
+		return 0;
+
+	ret = io_poll_cancel(ctx, cd, issue_flags);
+	if (ret != -ENOENT)
+		return ret;
+
+	spin_lock(&ctx->completion_lock);
+	if (!(cd->flags & IORING_ASYNC_CANCEL_FD))
+		ret = io_timeout_cancel(ctx, cd);
+	spin_unlock(&ctx->completion_lock);
+	return ret;
+}
+
+int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_cancel *cancel = io_kiocb_to_cmd(req);
+
+	if (unlikely(req->flags & REQ_F_BUFFER_SELECT))
+		return -EINVAL;
+	if (sqe->off || sqe->len || sqe->splice_fd_in)
+		return -EINVAL;
+
+	cancel->addr = READ_ONCE(sqe->addr);
+	cancel->flags = READ_ONCE(sqe->cancel_flags);
+	if (cancel->flags & ~CANCEL_FLAGS)
+		return -EINVAL;
+	if (cancel->flags & IORING_ASYNC_CANCEL_FD) {
+		if (cancel->flags & IORING_ASYNC_CANCEL_ANY)
+			return -EINVAL;
+		cancel->fd = READ_ONCE(sqe->fd);
+	}
+
+	return 0;
+}
+
+static int __io_async_cancel(struct io_cancel_data *cd,
+			     struct io_uring_task *tctx,
+			     unsigned int issue_flags)
+{
+	bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY);
+	struct io_ring_ctx *ctx = cd->ctx;
+	struct io_tctx_node *node;
+	int ret, nr = 0;
+
+	do {
+		ret = io_try_cancel(tctx, cd, issue_flags);
+		if (ret == -ENOENT)
+			break;
+		if (!all)
+			return ret;
+		nr++;
+	} while (1);
+
+	/* slow path, try all io-wq's */
+	io_ring_submit_lock(ctx, issue_flags);
+	ret = -ENOENT;
+	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+		struct io_uring_task *tctx = node->task->io_uring;
+
+		ret = io_async_cancel_one(tctx, cd);
+		if (ret != -ENOENT) {
+			if (!all)
+				break;
+			nr++;
+		}
+	}
+	io_ring_submit_unlock(ctx, issue_flags);
+	return all ? nr : ret;
+}
+
+int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_cancel *cancel = io_kiocb_to_cmd(req);
+	struct io_cancel_data cd = {
+		.ctx	= req->ctx,
+		.data	= cancel->addr,
+		.flags	= cancel->flags,
+		.seq	= atomic_inc_return(&req->ctx->cancel_seq),
+	};
+	struct io_uring_task *tctx = req->task->io_uring;
+	int ret;
+
+	if (cd.flags & IORING_ASYNC_CANCEL_FD) {
+		if (req->flags & REQ_F_FIXED_FILE ||
+		    cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) {
+			req->flags |= REQ_F_FIXED_FILE;
+			req->file = io_file_get_fixed(req, cancel->fd,
+							issue_flags);
+		} else {
+			req->file = io_file_get_normal(req, cancel->fd);
+		}
+		if (!req->file) {
+			ret = -EBADF;
+			goto done;
+		}
+		cd.file = req->file;
+	}
+
+	ret = __io_async_cancel(&cd, tctx, issue_flags);
+done:
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
+void init_hash_table(struct io_hash_table *table, unsigned size)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++) {
+		spin_lock_init(&table->hbs[i].lock);
+		INIT_HLIST_HEAD(&table->hbs[i].list);
+	}
+}
+
+static int __io_sync_cancel(struct io_uring_task *tctx,
+			    struct io_cancel_data *cd, int fd)
+{
+	struct io_ring_ctx *ctx = cd->ctx;
+
+	/* fixed must be grabbed every time since we drop the uring_lock */
+	if ((cd->flags & IORING_ASYNC_CANCEL_FD) &&
+	    (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) {
+		unsigned long file_ptr;
+
+		if (unlikely(fd > ctx->nr_user_files))
+			return -EBADF;
+		fd = array_index_nospec(fd, ctx->nr_user_files);
+		file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
+		cd->file = (struct file *) (file_ptr & FFS_MASK);
+		if (!cd->file)
+			return -EBADF;
+	}
+
+	return __io_async_cancel(cd, tctx, 0);
+}
+
+int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_cancel_data cd = {
+		.ctx	= ctx,
+		.seq	= atomic_inc_return(&ctx->cancel_seq),
+	};
+	ktime_t timeout = KTIME_MAX;
+	struct io_uring_sync_cancel_reg sc;
+	struct fd f = { };
+	DEFINE_WAIT(wait);
+	int ret;
+
+	if (copy_from_user(&sc, arg, sizeof(sc)))
+		return -EFAULT;
+	if (sc.flags & ~CANCEL_FLAGS)
+		return -EINVAL;
+	if (sc.pad[0] || sc.pad[1] || sc.pad[2] || sc.pad[3])
+		return -EINVAL;
+
+	cd.data = sc.addr;
+	cd.flags = sc.flags;
+
+	/* we can grab a normal file descriptor upfront */
+	if ((cd.flags & IORING_ASYNC_CANCEL_FD) &&
+	   !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) {
+		f = fdget(sc.fd);
+		if (!f.file)
+			return -EBADF;
+		cd.file = f.file;
+	}
+
+	ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
+
+	/* found something, done! */
+	if (ret != -EALREADY)
+		goto out;
+
+	if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) {
+		struct timespec64 ts = {
+			.tv_sec		= sc.timeout.tv_sec,
+			.tv_nsec	= sc.timeout.tv_nsec
+		};
+
+		timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+	}
+
+	/*
+	 * Keep looking until we get -ENOENT. we'll get woken everytime
+	 * every time a request completes and will retry the cancelation.
+	 */
+	do {
+		cd.seq = atomic_inc_return(&ctx->cancel_seq);
+
+		prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE);
+
+		ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
+
+		if (ret != -EALREADY)
+			break;
+
+		mutex_unlock(&ctx->uring_lock);
+		ret = io_run_task_work_sig();
+		if (ret < 0) {
+			mutex_lock(&ctx->uring_lock);
+			break;
+		}
+		ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS);
+		mutex_lock(&ctx->uring_lock);
+		if (!ret) {
+			ret = -ETIME;
+			break;
+		}
+	} while (1);
+
+	finish_wait(&ctx->cq_wait, &wait);
+
+	if (ret == -ENOENT || ret > 0)
+		ret = 0;
+out:
+	fdput(f);
+	return ret;
+}