Merge tag 'for-6.7/io_uring-2023-10-30' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "This contains the core io_uring updates, of which there are not many,
  and adds support for using WAITID through io_uring and hence not
  needing to block on these kinds of events.

  Outside of that, tweaks to the legacy provided buffer handling and
  some cleanups related to cancelations for uring_cmd support"

* tag 'for-6.7/io_uring-2023-10-30' of git://git.kernel.dk/linux:
  io_uring/poll: use IOU_F_TWQ_LAZY_WAKE for wakeups
  io_uring/kbuf: Use slab for struct io_buffer objects
  io_uring/kbuf: Allow the full buffer id space for provided buffers
  io_uring/kbuf: Fix check of BID wrapping in provided buffers
  io_uring/rsrc: cleanup io_pin_pages()
  io_uring: cancelable uring_cmd
  io_uring: retain top 8bits of uring_cmd flags for kernel internal use
  io_uring: add IORING_OP_WAITID support
  exit: add internal include file with helpers
  exit: add kernel_waitid_prepare() helper
  exit: move core of do_wait() into helper
  exit: abstract out should_wake helper for child_wait_callback()
  io_uring/rw: add support for IORING_OP_READ_MULTISHOT
  io_uring/rw: mark readv/writev as vectored in the opcode definition
  io_uring/rw: split io_read() into a helper

14 files changed, 649 insertions, 56 deletions

diff --git a/io_uring/Makefile b/io_uring/Makefile
index 8cc8e5387a75..7bd64e442567 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -7,5 +7,6 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					openclose.o uring_cmd.o epoll.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
-					cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o
+					cancel.o kbuf.o rsrc.o rw.o opdef.o \
+					notif.o waitid.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 7b23607cf4af..eb77a51c5a79 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -15,6 +15,7 @@
 #include "tctx.h"
 #include "poll.h"
 #include "timeout.h"
+#include "waitid.h"
 #include "cancel.h"
 
 struct io_cancel {
@@ -119,6 +120,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,
 	if (ret != -ENOENT)
 		return ret;
 
+	ret = io_waitid_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);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8d1bc6cdfe71..36ae5ac2b070 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -92,6 +92,7 @@
 #include "cancel.h"
 #include "net.h"
 #include "notif.h"
+#include "waitid.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -338,7 +339,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	spin_lock_init(&ctx->completion_lock);
 	spin_lock_init(&ctx->timeout_lock);
 	INIT_WQ_LIST(&ctx->iopoll_list);
-	INIT_LIST_HEAD(&ctx->io_buffers_pages);
 	INIT_LIST_HEAD(&ctx->io_buffers_comp);
 	INIT_LIST_HEAD(&ctx->defer_list);
 	INIT_LIST_HEAD(&ctx->timeout_list);
@@ -348,8 +348,10 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->tctx_list);
 	ctx->submit_state.free_list.next = NULL;
 	INIT_WQ_LIST(&ctx->locked_free_list);
+	INIT_HLIST_HEAD(&ctx->waitid_list);
 	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
 	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
+	INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd);
 	return ctx;
 err:
 	kfree(ctx->cancel_table.hbs);
@@ -3276,6 +3278,37 @@ static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
 	return ret;
 }
 
+static bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
+		struct task_struct *task, bool cancel_all)
+{
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	bool ret = false;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	hlist_for_each_entry_safe(req, tmp, &ctx->cancelable_uring_cmd,
+			hash_node) {
+		struct io_uring_cmd *cmd = io_kiocb_to_cmd(req,
+				struct io_uring_cmd);
+		struct file *file = req->file;
+
+		if (!cancel_all && req->task != task)
+			continue;
+
+		if (cmd->flags & IORING_URING_CMD_CANCELABLE) {
+			/* ->sqe isn't available if no async data */
+			if (!req_has_async_data(req))
+				cmd->sqe = NULL;
+			file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL);
+			ret = true;
+		}
+	}
+	io_submit_flush_completions(ctx);
+
+	return ret;
+}
+
 static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 						struct task_struct *task,
 						bool cancel_all)
@@ -3323,6 +3356,8 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 	ret |= io_cancel_defer_files(ctx, task, cancel_all);
 	mutex_lock(&ctx->uring_lock);
 	ret |= io_poll_remove_all(ctx, task, cancel_all);
+	ret |= io_waitid_remove_all(ctx, task, cancel_all);
+	ret |= io_uring_try_cancel_uring_cmd(ctx, task, cancel_all);
 	mutex_unlock(&ctx->uring_lock);
 	ret |= io_kill_timeouts(ctx, task, cancel_all);
 	if (task)
@@ -4686,6 +4721,9 @@ static int __init io_uring_init(void)
 
 	BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32));
 
+	/* top 8bits are for internal use */
+	BUILD_BUG_ON((IORING_URING_CMD_MASK & 0xff000000) != 0);
+
 	io_uring_optable_init();
 
 	/*
@@ -4701,6 +4739,9 @@ static int __init io_uring_init(void)
 				SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU,
 				offsetof(struct io_kiocb, cmd.data),
 				sizeof_field(struct io_kiocb, cmd.data), NULL);
+	io_buf_cachep = kmem_cache_create("io_buffer", sizeof(struct io_buffer), 0,
+					  SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
+					  NULL);
 
 #ifdef CONFIG_SYSCTL
 	register_sysctl_init("kernel", kernel_io_uring_disabled_table);
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 0bc145614a6e..dc6d779b452b 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -343,6 +343,7 @@ static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
 }
 
 extern struct kmem_cache *req_cachep;
+extern struct kmem_cache *io_buf_cachep;
 
 static inline struct io_kiocb *io_extract_req(struct io_ring_ctx *ctx)
 {
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 9123138aa9f4..fea06810b43d 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -19,12 +19,17 @@
 
 #define BGID_ARRAY	64
 
+/* BIDs are addressed by a 16-bit field in a CQE */
+#define MAX_BIDS_PER_BGID (1 << 16)
+
+struct kmem_cache *io_buf_cachep;
+
 struct io_provide_buf {
 	struct file			*file;
 	__u64				addr;
 	__u32				len;
 	__u32				bgid;
-	__u16				nbufs;
+	__u32				nbufs;
 	__u16				bid;
 };
 
@@ -255,6 +260,8 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
 void io_destroy_buffers(struct io_ring_ctx *ctx)
 {
 	struct io_buffer_list *bl;
+	struct list_head *item, *tmp;
+	struct io_buffer *buf;
 	unsigned long index;
 	int i;
 
@@ -270,12 +277,9 @@ void io_destroy_buffers(struct io_ring_ctx *ctx)
 		kfree(bl);
 	}
 
-	while (!list_empty(&ctx->io_buffers_pages)) {
-		struct page *page;
-
-		page = list_first_entry(&ctx->io_buffers_pages, struct page, lru);
-		list_del_init(&page->lru);
-		__free_page(page);
+	list_for_each_safe(item, tmp, &ctx->io_buffers_cache) {
+		buf = list_entry(item, struct io_buffer, list);
+		kmem_cache_free(io_buf_cachep, buf);
 	}
 }
 
@@ -289,7 +293,7 @@ int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 
 	tmp = READ_ONCE(sqe->fd);
-	if (!tmp || tmp > USHRT_MAX)
+	if (!tmp || tmp > MAX_BIDS_PER_BGID)
 		return -EINVAL;
 
 	memset(p, 0, sizeof(*p));
@@ -332,7 +336,7 @@ int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 		return -EINVAL;
 
 	tmp = READ_ONCE(sqe->fd);
-	if (!tmp || tmp > USHRT_MAX)
+	if (!tmp || tmp > MAX_BIDS_PER_BGID)
 		return -E2BIG;
 	p->nbufs = tmp;
 	p->addr = READ_ONCE(sqe->addr);
@@ -352,17 +356,18 @@ int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 	tmp = READ_ONCE(sqe->off);
 	if (tmp > USHRT_MAX)
 		return -E2BIG;
-	if (tmp + p->nbufs >= USHRT_MAX)
+	if (tmp + p->nbufs > MAX_BIDS_PER_BGID)
 		return -EINVAL;
 	p->bid = tmp;
 	return 0;
 }
 
+#define IO_BUFFER_ALLOC_BATCH 64
+
 static int io_refill_buffer_cache(struct io_ring_ctx *ctx)
 {
-	struct io_buffer *buf;
-	struct page *page;
-	int bufs_in_page;
+	struct io_buffer *bufs[IO_BUFFER_ALLOC_BATCH];
+	int allocated;
 
 	/*
 	 * Completions that don't happen inline (eg not under uring_lock) will
@@ -382,22 +387,25 @@ static int io_refill_buffer_cache(struct io_ring_ctx *ctx)
 
 	/*
 	 * No free buffers and no completion entries either. Allocate a new
-	 * page worth of buffer entries and add those to our freelist.
+	 * batch of buffer entries and add those to our freelist.
 	 */
-	page = alloc_page(GFP_KERNEL_ACCOUNT);
-	if (!page)
-		return -ENOMEM;
-
-	list_add(&page->lru, &ctx->io_buffers_pages);
 
-	buf = page_address(page);
-	bufs_in_page = PAGE_SIZE / sizeof(*buf);
-	while (bufs_in_page) {
-		list_add_tail(&buf->list, &ctx->io_buffers_cache);
-		buf++;
-		bufs_in_page--;
+	allocated = kmem_cache_alloc_bulk(io_buf_cachep, GFP_KERNEL_ACCOUNT,
+					  ARRAY_SIZE(bufs), (void **) bufs);
+	if (unlikely(!allocated)) {
+		/*
+		 * Bulk alloc is all-or-nothing. If we fail to get a batch,
+		 * retry single alloc to be on the safe side.
+		 */
+		bufs[0] = kmem_cache_alloc(io_buf_cachep, GFP_KERNEL);
+		if (!bufs[0])
+			return -ENOMEM;
+		allocated = 1;
 	}
 
+	while (allocated)
+		list_add_tail(&bufs[--allocated]->list, &ctx->io_buffers_cache);
+
 	return 0;
 }
 
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 3b9c6489b8b6..aadcbf7136b0 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -33,6 +33,7 @@
 #include "poll.h"
 #include "cancel.h"
 #include "rw.h"
+#include "waitid.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -63,6 +64,7 @@ const struct io_issue_def io_issue_defs[] = {
 		.ioprio			= 1,
 		.iopoll			= 1,
 		.iopoll_queue		= 1,
+		.vectored		= 1,
 		.prep			= io_prep_rw,
 		.issue			= io_read,
 	},
@@ -76,6 +78,7 @@ const struct io_issue_def io_issue_defs[] = {
 		.ioprio			= 1,
 		.iopoll			= 1,
 		.iopoll_queue		= 1,
+		.vectored		= 1,
 		.prep			= io_prep_rw,
 		.issue			= io_write,
 	},
@@ -428,9 +431,21 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_eopnotsupp_prep,
 #endif
 	},
+	[IORING_OP_READ_MULTISHOT] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
+		.audit_skip		= 1,
+		.prep			= io_read_mshot_prep,
+		.issue			= io_read_mshot,
+	},
+	[IORING_OP_WAITID] = {
+		.prep			= io_waitid_prep,
+		.issue			= io_waitid,
+	},
 };
 
-
 const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_NOP] = {
 		.name			= "NOP",
@@ -648,6 +663,13 @@ const struct io_cold_def io_cold_defs[] = {
 		.fail			= io_sendrecv_fail,
 #endif
 	},
+	[IORING_OP_READ_MULTISHOT] = {
+		.name			= "READ_MULTISHOT",
+	},
+	[IORING_OP_WAITID] = {
+		.name			= "WAITID",
+		.async_size		= sizeof(struct io_waitid_async),
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/opdef.h b/io_uring/opdef.h
index c22c8696e749..9e5435ec27d0 100644
--- a/io_uring/opdef.h
+++ b/io_uring/opdef.h
@@ -29,6 +29,8 @@ struct io_issue_def {
 	unsigned		iopoll_queue : 1;
 	/* opcode specific path will handle ->async_data allocation if needed */
 	unsigned		manual_alloc : 1;
+	/* vectored opcode, set if 1) vectored, and 2) handler needs to know */
+	unsigned		vectored : 1;
 
 	int (*issue)(struct io_kiocb *, unsigned int);
 	int (*prep)(struct io_kiocb *, const struct io_uring_sqe *);
diff --git a/io_uring/poll.c b/io_uring/poll.c
index 4c360ba8793a..d38d05edb4fa 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -370,7 +370,7 @@ static void __io_poll_execute(struct io_kiocb *req, int mask)
 	req->io_task_work.func = io_poll_task_func;
 
 	trace_io_uring_task_add(req, mask);
-	io_req_task_work_add(req);
+	__io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
 }
 
 static inline void io_poll_execute(struct io_kiocb *req, int res)
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index d9c853d10587..7034be555334 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1037,39 +1037,36 @@ struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
 {
 	unsigned long start, end, nr_pages;
 	struct page **pages = NULL;
-	int pret, ret = -ENOMEM;
+	int ret;
 
 	end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	start = ubuf >> PAGE_SHIFT;
 	nr_pages = end - start;
+	WARN_ON(!nr_pages);
 
 	pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
-		goto done;
+		return ERR_PTR(-ENOMEM);
 
-	ret = 0;
 	mmap_read_lock(current->mm);
-	pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
-			      pages);
-	if (pret == nr_pages)
+	ret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, pages);
+	mmap_read_unlock(current->mm);
+
+	/* success, mapped all pages */
+	if (ret == nr_pages) {
 		*npages = nr_pages;
-	else
-		ret = pret < 0 ? pret : -EFAULT;
+		return pages;
+	}
 
-	mmap_read_unlock(current->mm);
-	if (ret) {
+	/* partial map, or didn't map anything */
+	if (ret >= 0) {
 		/* if we did partial map, release any pages we did get */
-		if (pret > 0)
-			unpin_user_pages(pages, pret);
-		goto done;
-	}
-	ret = 0;
-done:
-	if (ret < 0) {
-		kvfree(pages);
-		pages = ERR_PTR(ret);
+		if (ret)
+			unpin_user_pages(pages, ret);
+		ret = -EFAULT;
 	}
-	return pages;
+	kvfree(pages);
+	return ERR_PTR(ret);
 }
 
 static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 8f68d5ad4564..3398e1d944c2 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -123,6 +123,22 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
+/*
+ * Multishot read is prepared just like a normal read/write request, only
+ * difference is that we set the MULTISHOT flag.
+ */
+int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	int ret;
+
+	ret = io_prep_rw(req, sqe);
+	if (unlikely(ret))
+		return ret;
+
+	req->flags |= REQ_F_APOLL_MULTISHOT;
+	return 0;
+}
+
 void io_readv_writev_cleanup(struct io_kiocb *req)
 {
 	struct io_async_rw *io = req->async_data;
@@ -388,8 +404,7 @@ static struct iovec *__io_import_iovec(int ddir, struct io_kiocb *req,
 	buf = u64_to_user_ptr(rw->addr);
 	sqe_len = rw->len;
 
-	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE ||
-	    (req->flags & REQ_F_BUFFER_SELECT)) {
+	if (!io_issue_defs[opcode].vectored || req->flags & REQ_F_BUFFER_SELECT) {
 		if (io_do_buffer_select(req)) {
 			buf = io_buffer_select(req, &sqe_len, issue_flags);
 			if (!buf)
@@ -708,7 +723,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
 	return 0;
 }
 
-int io_read(struct io_kiocb *req, unsigned int issue_flags)
+static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 	struct io_rw_state __s, *s = &__s;
@@ -776,8 +791,11 @@ int io_read(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
 		req->flags &= ~REQ_F_REISSUE;
-		/* if we can poll, just do that */
-		if (req->opcode == IORING_OP_READ && file_can_poll(req->file))
+		/*
+		 * If we can poll, just do that. For a vectored read, we'll
+		 * need to copy state first.
+		 */
+		if (file_can_poll(req->file) && !io_issue_defs[req->opcode].vectored)
 			return -EAGAIN;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
@@ -853,7 +871,69 @@ done:
 	/* it's faster to check here then delegate to kfree */
 	if (iovec)
 		kfree(iovec);
-	return kiocb_done(req, ret, issue_flags);
+	return ret;
+}
+
+int io_read(struct io_kiocb *req, unsigned int issue_flags)
+{
+	int ret;
+
+	ret = __io_read(req, issue_flags);
+	if (ret >= 0)
+		return kiocb_done(req, ret, issue_flags);
+
+	return ret;
+}
+
+int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
+{
+	unsigned int cflags = 0;
+	int ret;
+
+	/*
+	 * Multishot MUST be used on a pollable file
+	 */
+	if (!file_can_poll(req->file))
+		return -EBADFD;
+
+	ret = __io_read(req, issue_flags);
+
+	/*
+	 * If we get -EAGAIN, recycle our buffer and just let normal poll
+	 * handling arm it.
+	 */
+	if (ret == -EAGAIN) {
+		io_kbuf_recycle(req, issue_flags);
+		return -EAGAIN;
+	}
+
+	/*
+	 * Any successful return value will keep the multishot read armed.
+	 */
+	if (ret > 0) {
+		/*
+		 * Put our buffer and post a CQE. If we fail to post a CQE, then
+		 * jump to the termination path. This request is then done.
+		 */
+		cflags = io_put_kbuf(req, issue_flags);
+
+		if (io_fill_cqe_req_aux(req,
+					issue_flags & IO_URING_F_COMPLETE_DEFER,
+					ret, cflags | IORING_CQE_F_MORE)) {
+			if (issue_flags & IO_URING_F_MULTISHOT)
+				return IOU_ISSUE_SKIP_COMPLETE;
+			return -EAGAIN;
+		}
+	}
+
+	/*
+	 * Either an error, or we've hit overflow posting the CQE. For any
+	 * multishot request, hitting overflow will terminate it.
+	 */
+	io_req_set_res(req, ret, cflags);
+	if (issue_flags & IO_URING_F_MULTISHOT)
+		return IOU_STOP_MULTISHOT;
+	return IOU_OK;
 }
 
 int io_write(struct io_kiocb *req, unsigned int issue_flags)
diff --git a/io_uring/rw.h b/io_uring/rw.h
index 4b89f9659366..c5aed03d42a4 100644
--- a/io_uring/rw.h
+++ b/io_uring/rw.h
@@ -23,3 +23,5 @@ int io_writev_prep_async(struct io_kiocb *req);
 void io_readv_writev_cleanup(struct io_kiocb *req);
 void io_rw_fail(struct io_kiocb *req);
 void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts);
+int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 537795fddc87..00a5e5621a28 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -13,6 +13,51 @@
 #include "rsrc.h"
 #include "uring_cmd.h"
 
+static void io_uring_cmd_del_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (!(cmd->flags & IORING_URING_CMD_CANCELABLE))
+		return;
+
+	cmd->flags &= ~IORING_URING_CMD_CANCELABLE;
+	io_ring_submit_lock(ctx, issue_flags);
+	hlist_del(&req->hash_node);
+	io_ring_submit_unlock(ctx, issue_flags);
+}
+
+/*
+ * Mark this command as concelable, then io_uring_try_cancel_uring_cmd()
+ * will try to cancel this issued command by sending ->uring_cmd() with
+ * issue_flags of IO_URING_F_CANCEL.
+ *
+ * The command is guaranteed to not be done when calling ->uring_cmd()
+ * with IO_URING_F_CANCEL, but it is driver's responsibility to deal
+ * with race between io_uring canceling and normal completion.
+ */
+void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (!(cmd->flags & IORING_URING_CMD_CANCELABLE)) {
+		cmd->flags |= IORING_URING_CMD_CANCELABLE;
+		io_ring_submit_lock(ctx, issue_flags);
+		hlist_add_head(&req->hash_node, &ctx->cancelable_uring_cmd);
+		io_ring_submit_unlock(ctx, issue_flags);
+	}
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable);
+
+struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->task;
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_get_task);
+
 static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
@@ -56,6 +101,8 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2,
 {
 	struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
 
+	io_uring_cmd_del_cancelable(ioucmd, issue_flags);
+
 	if (ret < 0)
 		req_set_fail(req);
 
@@ -91,7 +138,7 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EINVAL;
 
 	ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags);
-	if (ioucmd->flags & ~IORING_URING_CMD_FIXED)
+	if (ioucmd->flags & ~IORING_URING_CMD_MASK)
 		return -EINVAL;
 
 	if (ioucmd->flags & IORING_URING_CMD_FIXED) {
diff --git a/io_uring/waitid.c b/io_uring/waitid.c
new file mode 100644
index 000000000000..6f851978606d
--- /dev/null
+++ b/io_uring/waitid.c
@@ -0,0 +1,372 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Support for async notification of waitid
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/compat.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "cancel.h"
+#include "waitid.h"
+#include "../kernel/exit.h"
+
+static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts);
+
+#define IO_WAITID_CANCEL_FLAG	BIT(31)
+#define IO_WAITID_REF_MASK	GENMASK(30, 0)
+
+struct io_waitid {
+	struct file *file;
+	int which;
+	pid_t upid;
+	int options;
+	atomic_t refs;
+	struct wait_queue_head *head;
+	struct siginfo __user *infop;
+	struct waitid_info info;
+};
+
+static void io_waitid_free(struct io_kiocb *req)
+{
+	struct io_waitid_async *iwa = req->async_data;
+
+	put_pid(iwa->wo.wo_pid);
+	kfree(req->async_data);
+	req->async_data = NULL;
+	req->flags &= ~REQ_F_ASYNC_DATA;
+}
+
+#ifdef CONFIG_COMPAT
+static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo)
+{
+	struct compat_siginfo __user *infop;
+	bool ret;
+
+	infop = (struct compat_siginfo __user *) iw->infop;
+
+	if (!user_write_access_begin(infop, sizeof(*infop)))
+		return false;
+
+	unsafe_put_user(signo, &infop->si_signo, Efault);
+	unsafe_put_user(0, &infop->si_errno, Efault);
+	unsafe_put_user(iw->info.cause, &infop->si_code, Efault);
+	unsafe_put_user(iw->info.pid, &infop->si_pid, Efault);
+	unsafe_put_user(iw->info.uid, &infop->si_uid, Efault);
+	unsafe_put_user(iw->info.status, &infop->si_status, Efault);
+	ret = true;
+done:
+	user_write_access_end();
+	return ret;
+Efault:
+	ret = false;
+	goto done;
+}
+#endif
+
+static bool io_waitid_copy_si(struct io_kiocb *req, int signo)
+{
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+	bool ret;
+
+	if (!iw->infop)
+		return true;
+
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		return io_waitid_compat_copy_si(iw, signo);
+#endif
+
+	if (!user_write_access_begin(iw->infop, sizeof(*iw->infop)))
+		return false;
+
+	unsafe_put_user(signo, &iw->infop->si_signo, Efault);
+	unsafe_put_user(0, &iw->infop->si_errno, Efault);
+	unsafe_put_user(iw->info.cause, &iw->infop->si_code, Efault);
+	unsafe_put_user(iw->info.pid, &iw->infop->si_pid, Efault);
+	unsafe_put_user(iw->info.uid, &iw->infop->si_uid, Efault);
+	unsafe_put_user(iw->info.status, &iw->infop->si_status, Efault);
+	ret = true;
+done:
+	user_write_access_end();
+	return ret;
+Efault:
+	ret = false;
+	goto done;
+}
+
+static int io_waitid_finish(struct io_kiocb *req, int ret)
+{
+	int signo = 0;
+
+	if (ret > 0) {
+		signo = SIGCHLD;
+		ret = 0;
+	}
+
+	if (!io_waitid_copy_si(req, signo))
+		ret = -EFAULT;
+	io_waitid_free(req);
+	return ret;
+}
+
+static void io_waitid_complete(struct io_kiocb *req, int ret)
+{
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+	struct io_tw_state ts = { .locked = true };
+
+	/* anyone completing better be holding a reference */
+	WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK));
+
+	lockdep_assert_held(&req->ctx->uring_lock);
+
+	/*
+	 * Did cancel find it meanwhile?
+	 */
+	if (hlist_unhashed(&req->hash_node))
+		return;
+
+	hlist_del_init(&req->hash_node);
+
+	ret = io_waitid_finish(req, ret);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	io_req_task_complete(req, &ts);
+}
+
+static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
+{
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+	struct io_waitid_async *iwa = req->async_data;
+
+	/*
+	 * Mark us canceled regardless of ownership. This will prevent a
+	 * potential retry from a spurious wakeup.
+	 */
+	atomic_or(IO_WAITID_CANCEL_FLAG, &iw->refs);
+
+	/* claim ownership */
+	if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK)
+		return false;
+
+	spin_lock_irq(&iw->head->lock);
+	list_del_init(&iwa->wo.child_wait.entry);
+	spin_unlock_irq(&iw->head->lock);
+	io_waitid_complete(req, -ECANCELED);
+	return true;
+}
+
+int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		     unsigned int issue_flags)
+{
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	int nr = 0;
+
+	if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED))
+		return -ENOENT;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) {
+		if (req->cqe.user_data != cd->data &&
+		    !(cd->flags & IORING_ASYNC_CANCEL_ANY))
+			continue;
+		if (__io_waitid_cancel(ctx, req))
+			nr++;
+		if (!(cd->flags & IORING_ASYNC_CANCEL_ALL))
+			break;
+	}
+	io_ring_submit_unlock(ctx, issue_flags);
+
+	if (nr)
+		return nr;
+
+	return -ENOENT;
+}
+
+bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task,
+			  bool cancel_all)
+{
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	bool found = false;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) {
+		if (!io_match_task_safe(req, task, cancel_all))
+			continue;
+		__io_waitid_cancel(ctx, req);
+		found = true;
+	}
+
+	return found;
+}
+
+static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req)
+{
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+	struct io_waitid_async *iwa = req->async_data;
+
+	if (!atomic_sub_return(1, &iw->refs))
+		return false;
+
+	/*
+	 * Wakeup triggered, racing with us. It was prevented from
+	 * completing because of that, queue up the tw to do that.
+	 */
+	req->io_task_work.func = io_waitid_cb;
+	io_req_task_work_add(req);
+	remove_wait_queue(iw->head, &iwa->wo.child_wait);
+	return true;
+}
+
+static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts)
+{
+	struct io_waitid_async *iwa = req->async_data;
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
+
+	io_tw_lock(ctx, ts);
+
+	ret = __do_wait(&iwa->wo);
+
+	/*
+	 * If we get -ERESTARTSYS here, we need to re-arm and check again
+	 * to ensure we get another callback. If the retry works, then we can
+	 * just remove ourselves from the waitqueue again and finish the
+	 * request.
+	 */
+	if (unlikely(ret == -ERESTARTSYS)) {
+		struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+
+		/* Don't retry if cancel found it meanwhile */
+		ret = -ECANCELED;
+		if (!(atomic_read(&iw->refs) & IO_WAITID_CANCEL_FLAG)) {
+			iw->head = &current->signal->wait_chldexit;
+			add_wait_queue(iw->head, &iwa->wo.child_wait);
+			ret = __do_wait(&iwa->wo);
+			if (ret == -ERESTARTSYS) {
+				/* retry armed, drop our ref */
+				io_waitid_drop_issue_ref(req);
+				return;
+			}
+
+			remove_wait_queue(iw->head, &iwa->wo.child_wait);
+		}
+	}
+
+	io_waitid_complete(req, ret);
+}
+
+static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode,
+			  int sync, void *key)
+{
+	struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait);
+	struct io_waitid_async *iwa = container_of(wo, struct io_waitid_async, wo);
+	struct io_kiocb *req = iwa->req;
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+	struct task_struct *p = key;
+
+	if (!pid_child_should_wake(wo, p))
+		return 0;
+
+	/* cancel is in progress */
+	if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK)
+		return 1;
+
+	req->io_task_work.func = io_waitid_cb;
+	io_req_task_work_add(req);
+	list_del_init(&wait->entry);
+	return 1;
+}
+
+int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+
+	if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags)
+		return -EINVAL;
+
+	iw->which = READ_ONCE(sqe->len);
+	iw->upid = READ_ONCE(sqe->fd);
+	iw->options = READ_ONCE(sqe->file_index);
+	iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	return 0;
+}
+
+int io_waitid(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_waitid_async *iwa;
+	int ret;
+
+	if (io_alloc_async_data(req))
+		return -ENOMEM;
+
+	iwa = req->async_data;
+	iwa->req = req;
+
+	ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info,
+					iw->options, NULL);
+	if (ret)
+		goto done;
+
+	/*
+	 * Mark the request as busy upfront, in case we're racing with the
+	 * wakeup. If we are, then we'll notice when we drop this initial
+	 * reference again after arming.
+	 */
+	atomic_set(&iw->refs, 1);
+
+	/*
+	 * Cancel must hold the ctx lock, so there's no risk of cancelation
+	 * finding us until a) we remain on the list, and b) the lock is
+	 * dropped. We only need to worry about racing with the wakeup
+	 * callback.
+	 */
+	io_ring_submit_lock(ctx, issue_flags);
+	hlist_add_head(&req->hash_node, &ctx->waitid_list);
+
+	init_waitqueue_func_entry(&iwa->wo.child_wait, io_waitid_wait);
+	iwa->wo.child_wait.private = req->task;
+	iw->head = &current->signal->wait_chldexit;
+	add_wait_queue(iw->head, &iwa->wo.child_wait);
+
+	ret = __do_wait(&iwa->wo);
+	if (ret == -ERESTARTSYS) {
+		/*
+		 * Nobody else grabbed a reference, it'll complete when we get
+		 * a waitqueue callback, or if someone cancels it.
+		 */
+		if (!io_waitid_drop_issue_ref(req)) {
+			io_ring_submit_unlock(ctx, issue_flags);
+			return IOU_ISSUE_SKIP_COMPLETE;
+		}
+
+		/*
+		 * Wakeup triggered, racing with us. It was prevented from
+		 * completing because of that, queue up the tw to do that.
+		 */
+		io_ring_submit_unlock(ctx, issue_flags);
+		return IOU_ISSUE_SKIP_COMPLETE;
+	}
+
+	hlist_del_init(&req->hash_node);
+	remove_wait_queue(iw->head, &iwa->wo.child_wait);
+	ret = io_waitid_finish(req, ret);
+
+	io_ring_submit_unlock(ctx, issue_flags);
+done:
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
diff --git a/io_uring/waitid.h b/io_uring/waitid.h
new file mode 100644
index 000000000000..956a8adafe8c
--- /dev/null
+++ b/io_uring/waitid.h
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../kernel/exit.h"
+
+struct io_waitid_async {
+	struct io_kiocb *req;
+	struct wait_opts wo;
+};
+
+int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_waitid(struct io_kiocb *req, unsigned int issue_flags);
+int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		     unsigned int issue_flags);
+bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task,
+			  bool cancel_all);