Merge tag 'for-6.18/io_uring-20250929' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring updates from Jens Axboe:

 - Store ring provided buffers locally for the users, rather than stuff
   them into struct io_kiocb.

   These types of buffers must always be fully consumed or recycled in
   the current context, and leaving them in struct io_kiocb is hence not
   a good ideas as that struct has a vastly different life time.

   Basically just an architecture cleanup that can help prevent issues
   with ring provided buffers in the future.

 - Support for mixed CQE sizes in the same ring.

   Before this change, a CQ ring either used the default 16b CQEs, or it
   was setup with 32b CQE using IORING_SETUP_CQE32. For use cases where
   a few 32b CQEs were needed, this caused everything else to use big
   CQEs. This is wasteful both in terms of memory usage, but also memory
   bandwidth for the posted CQEs.

   With IORING_SETUP_CQE_MIXED, applications may use request types that
   post both normal 16b and big 32b CQEs on the same ring.

 - Add helpers for async data management, to make it harder for opcode
   handlers to mess it up.

 - Add support for multishot for uring_cmd, which ublk can use. This
   helps improve efficiency, by providing a persistent request type that
   can trigger multiple CQEs.

 - Add initial support for ring feature querying.

   We had basic support for probe operations, but the API isn't great.
   Rather than expand that, add support for QUERY which is easily
   expandable and can cover a lot more cases than the existing probe
   support. This will help applications get a better idea of what
   operations are supported on a given host.

 - zcrx improvements from Pavel:
        - Improve refill entry alignment for better caching
        - Various cleanups, especially around deduplicating normal
          memory vs dmabuf setup.
        - Generalisation of the niov size (Patch 12). It's still hard
          coded to PAGE_SIZE on init, but will let the user to specify
          the rx buffer length on setup.
        - Syscall / synchronous bufer return. It'll be used as a slow
          fallback path for returning buffers when the refill queue is
          full. Useful for tolerating slight queue size misconfiguration
          or with inconsistent load.
        - Accounting more memory to cgroups.
        - Additional independent cleanups that will also be useful for
          mutli-area support.

 - Various fixes and cleanups

* tag 'for-6.18/io_uring-20250929' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (68 commits)
  io_uring/cmd: drop unused res2 param from io_uring_cmd_done()
  io_uring: fix nvme's 32b cqes on mixed cq
  io_uring/query: cap number of queries
  io_uring/query: prevent infinite loops
  io_uring/zcrx: account niov arrays to cgroup
  io_uring/zcrx: allow synchronous buffer return
  io_uring/zcrx: introduce io_parse_rqe()
  io_uring/zcrx: don't adjust free cache space
  io_uring/zcrx: use guards for the refill lock
  io_uring/zcrx: reduce netmem scope in refill
  io_uring/zcrx: protect netdev with pp_lock
  io_uring/zcrx: rename dma lock
  io_uring/zcrx: make niov size variable
  io_uring/zcrx: set sgt for umem area
  io_uring/zcrx: remove dmabuf_offset
  io_uring/zcrx: deduplicate area mapping
  io_uring/zcrx: pass ifq to io_zcrx_alloc_fallback()
  io_uring/zcrx: check all niovs filled with dma addresses
  io_uring/zcrx: move area reg checks into io_import_area
  io_uring/zcrx: don't pass slot to io_zcrx_create_area
  ...

25 files changed, 839 insertions, 406 deletions

diff --git a/io_uring/Makefile b/io_uring/Makefile
index b3f1bd492804..bc4e4a3fa0a5 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					sync.o msg_ring.o advise.o openclose.o \
 					statx.o timeout.o cancel.o \
 					waitid.o register.o truncate.o \
-					memmap.o alloc_cache.o
+					memmap.o alloc_cache.o query.o
 obj-$(CONFIG_IO_URING_ZCRX)	+= zcrx.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 6d57602304df..64b51e82baa2 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -11,6 +11,7 @@
 
 #include <uapi/linux/io_uring.h>
 
+#include "filetable.h"
 #include "io_uring.h"
 #include "tctx.h"
 #include "poll.h"
diff --git a/io_uring/cmd_net.c b/io_uring/cmd_net.c
index 3866fe6ff541..27a09aa4c9d0 100644
--- a/io_uring/cmd_net.c
+++ b/io_uring/cmd_net.c
@@ -4,6 +4,7 @@
 #include <net/sock.h>
 
 #include "uring_cmd.h"
+#include "io_uring.h"
 
 static inline int io_uring_cmd_getsockopt(struct socket *sock,
 					  struct io_uring_cmd *cmd,
@@ -73,7 +74,7 @@ static bool io_process_timestamp_skb(struct io_uring_cmd *cmd, struct sock *sk,
 
 	cqe->user_data = 0;
 	cqe->res = tskey;
-	cqe->flags = IORING_CQE_F_MORE;
+	cqe->flags = IORING_CQE_F_MORE | ctx_cqe32_flags(cmd_to_io_kiocb(cmd)->ctx);
 	cqe->flags |= tstype << IORING_TIMESTAMP_TYPE_SHIFT;
 	if (ret == SOF_TIMESTAMPING_TX_HARDWARE)
 		cqe->flags |= IORING_CQE_F_TSTAMP_HW;
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 9798d6fb4ec7..ff3364531c77 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -9,7 +9,7 @@
 
 #include <uapi/linux/io_uring.h>
 
-#include "io_uring.h"
+#include "filetable.h"
 #include "sqpoll.h"
 #include "fdinfo.h"
 #include "cancel.h"
@@ -65,15 +65,12 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 	unsigned int sq_tail = READ_ONCE(r->sq.tail);
 	unsigned int cq_head = READ_ONCE(r->cq.head);
 	unsigned int cq_tail = READ_ONCE(r->cq.tail);
-	unsigned int cq_shift = 0;
 	unsigned int sq_shift = 0;
-	unsigned int sq_entries, cq_entries;
+	unsigned int sq_entries;
 	int sq_pid = -1, sq_cpu = -1;
 	u64 sq_total_time = 0, sq_work_time = 0;
 	unsigned int i;
 
-	if (ctx->flags & IORING_SETUP_CQE32)
-		cq_shift = 1;
 	if (ctx->flags & IORING_SETUP_SQE128)
 		sq_shift = 1;
 
@@ -125,18 +122,23 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 		seq_printf(m, "\n");
 	}
 	seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
-	cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
-	for (i = 0; i < cq_entries; i++) {
-		unsigned int entry = i + cq_head;
-		struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift];
+	while (cq_head < cq_tail) {
+		struct io_uring_cqe *cqe;
+		bool cqe32 = false;
 
+		cqe = &r->cqes[(cq_head & cq_mask)];
+		if (cqe->flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32)
+			cqe32 = true;
 		seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x",
-			   entry & cq_mask, cqe->user_data, cqe->res,
+			   cq_head & cq_mask, cqe->user_data, cqe->res,
 			   cqe->flags);
-		if (cq_shift)
+		if (cqe32)
 			seq_printf(m, ", extra1:%llu, extra2:%llu\n",
 					cqe->big_cqe[0], cqe->big_cqe[1]);
 		seq_printf(m, "\n");
+		cq_head++;
+		if (cqe32)
+			cq_head++;
 	}
 
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
diff --git a/io_uring/futex.c b/io_uring/futex.c
index 9113a44984f3..64f3bd51c84c 100644
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -43,7 +43,6 @@ void io_futex_cache_free(struct io_ring_ctx *ctx)
 
 static void __io_futex_complete(struct io_kiocb *req, io_tw_token_t tw)
 {
-	req->async_data = NULL;
 	hlist_del_init(&req->hash_node);
 	io_req_task_complete(req, tw);
 }
@@ -54,6 +53,7 @@ static void io_futex_complete(struct io_kiocb *req, io_tw_token_t tw)
 
 	io_tw_lock(ctx, tw);
 	io_cache_free(&ctx->futex_cache, req->async_data);
+	io_req_async_data_clear(req, 0);
 	__io_futex_complete(req, tw);
 }
 
@@ -72,8 +72,7 @@ static void io_futexv_complete(struct io_kiocb *req, io_tw_token_t tw)
 			io_req_set_res(req, res, 0);
 	}
 
-	kfree(req->async_data);
-	req->flags &= ~REQ_F_ASYNC_DATA;
+	io_req_async_data_free(req);
 	__io_futex_complete(req, tw);
 }
 
@@ -232,9 +231,7 @@ int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags)
 		io_ring_submit_unlock(ctx, issue_flags);
 		req_set_fail(req);
 		io_req_set_res(req, ret, 0);
-		kfree(futexv);
-		req->async_data = NULL;
-		req->flags &= ~REQ_F_ASYNC_DATA;
+		io_req_async_data_free(req);
 		return IOU_COMPLETE;
 	}
 
@@ -310,9 +307,7 @@ done:
 	if (ret < 0)
 		req_set_fail(req);
 	io_req_set_res(req, ret, 0);
-	req->async_data = NULL;
-	req->flags &= ~REQ_F_ASYNC_DATA;
-	kfree(ifd);
+	io_req_async_data_free(req);
 	return IOU_COMPLETE;
 }
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 93665cebe9bd..49ebdeb5b2d9 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -79,6 +79,7 @@
 
 #include "io-wq.h"
 
+#include "filetable.h"
 #include "io_uring.h"
 #include "opdef.h"
 #include "refs.h"
@@ -108,9 +109,6 @@
 #define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
 			  IOSQE_IO_HARDLINK | IOSQE_ASYNC)
 
-#define SQE_VALID_FLAGS	(SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
-			IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
-
 #define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
 
 #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
@@ -179,6 +177,26 @@ static const struct ctl_table kernel_io_uring_disabled_table[] = {
 };
 #endif
 
+static void io_poison_cached_req(struct io_kiocb *req)
+{
+	req->ctx = IO_URING_PTR_POISON;
+	req->tctx = IO_URING_PTR_POISON;
+	req->file = IO_URING_PTR_POISON;
+	req->creds = IO_URING_PTR_POISON;
+	req->io_task_work.func = IO_URING_PTR_POISON;
+	req->apoll = IO_URING_PTR_POISON;
+}
+
+static void io_poison_req(struct io_kiocb *req)
+{
+	io_poison_cached_req(req);
+	req->async_data = IO_URING_PTR_POISON;
+	req->kbuf = IO_URING_PTR_POISON;
+	req->comp_list.next = IO_URING_PTR_POISON;
+	req->file_node = IO_URING_PTR_POISON;
+	req->link = IO_URING_PTR_POISON;
+}
+
 static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
 {
 	return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
@@ -235,6 +253,8 @@ static inline void req_fail_link_node(struct io_kiocb *req, int res)
 
 static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx)
 {
+	if (IS_ENABLED(CONFIG_KASAN))
+		io_poison_cached_req(req);
 	wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
 }
 
@@ -594,27 +614,29 @@ static void io_cq_unlock_post(struct io_ring_ctx *ctx)
 
 static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying)
 {
-	size_t cqe_size = sizeof(struct io_uring_cqe);
-
 	lockdep_assert_held(&ctx->uring_lock);
 
 	/* don't abort if we're dying, entries must get freed */
 	if (!dying && __io_cqring_events(ctx) == ctx->cq_entries)
 		return;
 
-	if (ctx->flags & IORING_SETUP_CQE32)
-		cqe_size <<= 1;
-
 	io_cq_lock(ctx);
 	while (!list_empty(&ctx->cq_overflow_list)) {
+		size_t cqe_size = sizeof(struct io_uring_cqe);
 		struct io_uring_cqe *cqe;
 		struct io_overflow_cqe *ocqe;
+		bool is_cqe32 = false;
 
 		ocqe = list_first_entry(&ctx->cq_overflow_list,
 					struct io_overflow_cqe, list);
+		if (ocqe->cqe.flags & IORING_CQE_F_32 ||
+		    ctx->flags & IORING_SETUP_CQE32) {
+			is_cqe32 = true;
+			cqe_size <<= 1;
+		}
 
 		if (!dying) {
-			if (!io_get_cqe_overflow(ctx, &cqe, true))
+			if (!io_get_cqe_overflow(ctx, &cqe, true, is_cqe32))
 				break;
 			memcpy(cqe, &ocqe->cqe, cqe_size);
 		}
@@ -726,10 +748,12 @@ static struct io_overflow_cqe *io_alloc_ocqe(struct io_ring_ctx *ctx,
 {
 	struct io_overflow_cqe *ocqe;
 	size_t ocq_size = sizeof(struct io_overflow_cqe);
-	bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+	bool is_cqe32 = false;
 
-	if (is_cqe32)
+	if (cqe->flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32) {
+		is_cqe32 = true;
 		ocq_size += sizeof(struct io_uring_cqe);
+	}
 
 	ocqe = kzalloc(ocq_size, gfp | __GFP_ACCOUNT);
 	trace_io_uring_cqe_overflow(ctx, cqe->user_data, cqe->res, cqe->flags, ocqe);
@@ -748,11 +772,29 @@ static struct io_overflow_cqe *io_alloc_ocqe(struct io_ring_ctx *ctx,
 }
 
 /*
+ * Fill an empty dummy CQE, in case alignment is off for posting a 32b CQE
+ * because the ring is a single 16b entry away from wrapping.
+ */
+static bool io_fill_nop_cqe(struct io_ring_ctx *ctx, unsigned int off)
+{
+	if (__io_cqring_events(ctx) < ctx->cq_entries) {
+		struct io_uring_cqe *cqe = &ctx->rings->cqes[off];
+
+		cqe->user_data = 0;
+		cqe->res = 0;
+		cqe->flags = IORING_CQE_F_SKIP;
+		ctx->cached_cq_tail++;
+		return true;
+	}
+	return false;
+}
+
+/*
  * writes to the cq entry need to come after reading head; the
  * control dependency is enough as we're using WRITE_ONCE to
  * fill the cq entry
  */
-bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow)
+bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32)
 {
 	struct io_rings *rings = ctx->rings;
 	unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
@@ -766,12 +808,22 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow)
 	if (!overflow && (ctx->check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)))
 		return false;
 
+	/*
+	 * Post dummy CQE if a 32b CQE is needed and there's only room for a
+	 * 16b CQE before the ring wraps.
+	 */
+	if (cqe32 && off + 1 == ctx->cq_entries) {
+		if (!io_fill_nop_cqe(ctx, off))
+			return false;
+		off = 0;
+	}
+
 	/* userspace may cheat modifying the tail, be safe and do min */
 	queued = min(__io_cqring_events(ctx), ctx->cq_entries);
 	free = ctx->cq_entries - queued;
 	/* we need a contiguous range, limit based on the current array offset */
 	len = min(free, ctx->cq_entries - off);
-	if (!len)
+	if (len < (cqe32 + 1))
 		return false;
 
 	if (ctx->flags & IORING_SETUP_CQE32) {
@@ -789,9 +841,9 @@ static bool io_fill_cqe_aux32(struct io_ring_ctx *ctx,
 {
 	struct io_uring_cqe *cqe;
 
-	if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32)))
+	if (WARN_ON_ONCE(!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED))))
 		return false;
-	if (unlikely(!io_get_cqe(ctx, &cqe)))
+	if (unlikely(!io_get_cqe(ctx, &cqe, true)))
 		return false;
 
 	memcpy(cqe, src_cqe, 2 * sizeof(*cqe));
@@ -802,14 +854,15 @@ static bool io_fill_cqe_aux32(struct io_ring_ctx *ctx,
 static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
 			      u32 cflags)
 {
+	bool cqe32 = cflags & IORING_CQE_F_32;
 	struct io_uring_cqe *cqe;
 
-	if (likely(io_get_cqe(ctx, &cqe))) {
+	if (likely(io_get_cqe(ctx, &cqe, cqe32))) {
 		WRITE_ONCE(cqe->user_data, user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, cflags);
 
-		if (ctx->flags & IORING_SETUP_CQE32) {
+		if (cqe32) {
 			WRITE_ONCE(cqe->big_cqe[0], 0);
 			WRITE_ONCE(cqe->big_cqe[1], 0);
 		}
@@ -981,7 +1034,7 @@ void io_req_defer_failed(struct io_kiocb *req, s32 res)
 	lockdep_assert_held(&req->ctx->uring_lock);
 
 	req_set_fail(req);
-	io_req_set_res(req, res, io_put_kbuf(req, res, IO_URING_F_UNLOCKED));
+	io_req_set_res(req, res, io_put_kbuf(req, res, NULL));
 	if (def->fail)
 		def->fail(req);
 	io_req_complete_defer(req);
@@ -2001,11 +2054,9 @@ fail:
 
 	switch (io_arm_poll_handler(req, 0)) {
 	case IO_APOLL_READY:
-		io_kbuf_recycle(req, 0);
 		io_req_task_queue(req);
 		break;
 	case IO_APOLL_ABORTED:
-		io_kbuf_recycle(req, 0);
 		io_queue_iowq(req);
 		break;
 	case IO_APOLL_OK:
@@ -2734,6 +2785,10 @@ unsigned long rings_size(unsigned int flags, unsigned int sq_entries,
 		if (check_shl_overflow(off, 1, &off))
 			return SIZE_MAX;
 	}
+	if (flags & IORING_SETUP_CQE_MIXED) {
+		if (cq_entries < 2)
+			return SIZE_MAX;
+	}
 
 #ifdef CONFIG_SMP
 	off = ALIGN(off, SMP_CACHE_BYTES);
@@ -2765,6 +2820,7 @@ static __cold void __io_req_caches_free(struct io_ring_ctx *ctx)
 
 	while (!io_req_cache_empty(ctx)) {
 		req = io_extract_req(ctx);
+		io_poison_req(req);
 		kmem_cache_free(req_cachep, req);
 		nr++;
 	}
@@ -3045,10 +3101,10 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 
 	INIT_WORK(&ctx->exit_work, io_ring_exit_work);
 	/*
-	 * Use system_unbound_wq to avoid spawning tons of event kworkers
+	 * Use system_dfl_wq to avoid spawning tons of event kworkers
 	 * if we're exiting a ton of rings at the same time. It just adds
 	 * noise and overhead, there's no discernable change in runtime
-	 * over using system_wq.
+	 * over using system_percpu_wq.
 	 */
 	queue_work(iou_wq, &ctx->exit_work);
 }
@@ -3402,12 +3458,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	struct file *file;
 	long ret;
 
-	if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
-			       IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG |
-			       IORING_ENTER_REGISTERED_RING |
-			       IORING_ENTER_ABS_TIMER |
-			       IORING_ENTER_EXT_ARG_REG |
-			       IORING_ENTER_NO_IOWAIT)))
+	if (unlikely(flags & ~IORING_ENTER_FLAGS))
 		return -EINVAL;
 
 	/*
@@ -3657,6 +3708,14 @@ static int io_uring_sanitise_params(struct io_uring_params *p)
 	    !(flags & IORING_SETUP_SINGLE_ISSUER))
 		return -EINVAL;
 
+	/*
+	 * Nonsensical to ask for CQE32 and mixed CQE support, it's not
+	 * supported to post 16b CQEs on a ring setup with CQE32.
+	 */
+	if ((flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED)) ==
+	    (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -3807,15 +3866,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 	if (ret)
 		goto err;
 
-	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
-			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
-			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
-			IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
-			IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
-			IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP |
-			IORING_FEAT_LINKED_FILE | IORING_FEAT_REG_REG_RING |
-			IORING_FEAT_RECVSEND_BUNDLE | IORING_FEAT_MIN_TIMEOUT |
-			IORING_FEAT_RW_ATTR | IORING_FEAT_NO_IOWAIT;
+	p->features = IORING_FEAT_FLAGS;
 
 	if (copy_to_user(params, p, sizeof(*p))) {
 		ret = -EFAULT;
@@ -3823,8 +3874,13 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
 	}
 
 	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER
-	    && !(ctx->flags & IORING_SETUP_R_DISABLED))
-		WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
+	    && !(ctx->flags & IORING_SETUP_R_DISABLED)) {
+		/*
+		 * Unlike io_register_enable_rings(), don't need WRITE_ONCE()
+		 * since ctx isn't yet accessible from other tasks
+		 */
+		ctx->submitter_task = get_task_struct(current);
+	}
 
 	file = io_uring_get_file(ctx);
 	if (IS_ERR(file)) {
@@ -3875,17 +3931,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 			return -EINVAL;
 	}
 
-	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
-			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
-			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
-			IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL |
-			IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG |
-			IORING_SETUP_SQE128 | IORING_SETUP_CQE32 |
-			IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN |
-			IORING_SETUP_NO_MMAP | IORING_SETUP_REGISTERED_FD_ONLY |
-			IORING_SETUP_NO_SQARRAY | IORING_SETUP_HYBRID_IOPOLL))
+	if (p.flags & ~IORING_SETUP_FLAGS)
 		return -EINVAL;
-
 	return io_uring_create(entries, &p, params);
 }
 
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 1880902be6fd..46d9141d772a 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -11,13 +11,69 @@
 #include "alloc_cache.h"
 #include "io-wq.h"
 #include "slist.h"
-#include "filetable.h"
 #include "opdef.h"
 
 #ifndef CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
 #endif
 
+#define IORING_FEAT_FLAGS (IORING_FEAT_SINGLE_MMAP |\
+			IORING_FEAT_NODROP |\
+			IORING_FEAT_SUBMIT_STABLE |\
+			IORING_FEAT_RW_CUR_POS |\
+			IORING_FEAT_CUR_PERSONALITY |\
+			IORING_FEAT_FAST_POLL |\
+			IORING_FEAT_POLL_32BITS |\
+			IORING_FEAT_SQPOLL_NONFIXED |\
+			IORING_FEAT_EXT_ARG |\
+			IORING_FEAT_NATIVE_WORKERS |\
+			IORING_FEAT_RSRC_TAGS |\
+			IORING_FEAT_CQE_SKIP |\
+			IORING_FEAT_LINKED_FILE |\
+			IORING_FEAT_REG_REG_RING |\
+			IORING_FEAT_RECVSEND_BUNDLE |\
+			IORING_FEAT_MIN_TIMEOUT |\
+			IORING_FEAT_RW_ATTR |\
+			IORING_FEAT_NO_IOWAIT)
+
+#define IORING_SETUP_FLAGS (IORING_SETUP_IOPOLL |\
+			IORING_SETUP_SQPOLL |\
+			IORING_SETUP_SQ_AFF |\
+			IORING_SETUP_CQSIZE |\
+			IORING_SETUP_CLAMP |\
+			IORING_SETUP_ATTACH_WQ |\
+			IORING_SETUP_R_DISABLED |\
+			IORING_SETUP_SUBMIT_ALL |\
+			IORING_SETUP_COOP_TASKRUN |\
+			IORING_SETUP_TASKRUN_FLAG |\
+			IORING_SETUP_SQE128 |\
+			IORING_SETUP_CQE32 |\
+			IORING_SETUP_SINGLE_ISSUER |\
+			IORING_SETUP_DEFER_TASKRUN |\
+			IORING_SETUP_NO_MMAP |\
+			IORING_SETUP_REGISTERED_FD_ONLY |\
+			IORING_SETUP_NO_SQARRAY |\
+			IORING_SETUP_HYBRID_IOPOLL |\
+			IORING_SETUP_CQE_MIXED)
+
+#define IORING_ENTER_FLAGS (IORING_ENTER_GETEVENTS |\
+			IORING_ENTER_SQ_WAKEUP |\
+			IORING_ENTER_SQ_WAIT |\
+			IORING_ENTER_EXT_ARG |\
+			IORING_ENTER_REGISTERED_RING |\
+			IORING_ENTER_ABS_TIMER |\
+			IORING_ENTER_EXT_ARG_REG |\
+			IORING_ENTER_NO_IOWAIT)
+
+
+#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE |\
+			IOSQE_IO_DRAIN |\
+			IOSQE_IO_LINK |\
+			IOSQE_IO_HARDLINK |\
+			IOSQE_ASYNC |\
+			IOSQE_BUFFER_SELECT |\
+			IOSQE_CQE_SKIP_SUCCESS)
+
 enum {
 	IOU_COMPLETE		= 0,
 
@@ -75,7 +131,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq)
 unsigned long rings_size(unsigned int flags, unsigned int sq_entries,
 			 unsigned int cq_entries, size_t *sq_offset);
 int io_uring_fill_params(unsigned entries, struct io_uring_params *p);
-bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
+bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
 void io_req_defer_failed(struct io_kiocb *req, s32 res);
 bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
@@ -169,25 +225,31 @@ static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
 
 static inline bool io_get_cqe_overflow(struct io_ring_ctx *ctx,
 					struct io_uring_cqe **ret,
-					bool overflow)
+					bool overflow, bool cqe32)
 {
 	io_lockdep_assert_cq_locked(ctx);
 
-	if (unlikely(ctx->cqe_cached >= ctx->cqe_sentinel)) {
-		if (unlikely(!io_cqe_cache_refill(ctx, overflow)))
+	if (unlikely(ctx->cqe_sentinel - ctx->cqe_cached < (cqe32 + 1))) {
+		if (unlikely(!io_cqe_cache_refill(ctx, overflow, cqe32)))
 			return false;
 	}
 	*ret = ctx->cqe_cached;
 	ctx->cached_cq_tail++;
 	ctx->cqe_cached++;
-	if (ctx->flags & IORING_SETUP_CQE32)
+	if (ctx->flags & IORING_SETUP_CQE32) {
+		ctx->cqe_cached++;
+	} else if (cqe32 && ctx->flags & IORING_SETUP_CQE_MIXED) {
 		ctx->cqe_cached++;
+		ctx->cached_cq_tail++;
+	}
+	WARN_ON_ONCE(ctx->cqe_cached > ctx->cqe_sentinel);
 	return true;
 }
 
-static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret)
+static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret,
+				bool cqe32)
 {
-	return io_get_cqe_overflow(ctx, ret, false);
+	return io_get_cqe_overflow(ctx, ret, false, cqe32);
 }
 
 static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx,
@@ -196,25 +258,24 @@ static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx,
 	io_lockdep_assert_cq_locked(ctx);
 
 	ctx->submit_state.cq_flush = true;
-	return io_get_cqe(ctx, cqe_ret);
+	return io_get_cqe(ctx, cqe_ret, ctx->flags & IORING_SETUP_CQE_MIXED);
 }
 
 static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
 					    struct io_kiocb *req)
 {
+	bool is_cqe32 = req->cqe.flags & IORING_CQE_F_32;
 	struct io_uring_cqe *cqe;
 
 	/*
-	 * If we can't get a cq entry, userspace overflowed the
-	 * submission (by quite a lot). Increment the overflow count in
-	 * the ring.
+	 * If we can't get a cq entry, userspace overflowed the submission
+	 * (by quite a lot).
 	 */
-	if (unlikely(!io_get_cqe(ctx, &cqe)))
+	if (unlikely(!io_get_cqe(ctx, &cqe, is_cqe32)))
 		return false;
 
-
 	memcpy(cqe, &req->cqe, sizeof(*cqe));
-	if (ctx->flags & IORING_SETUP_CQE32) {
+	if (ctx->flags & IORING_SETUP_CQE32 || is_cqe32) {
 		memcpy(cqe->big_cqe, &req->big_cqe, sizeof(*cqe));
 		memset(&req->big_cqe, 0, sizeof(req->big_cqe));
 	}
@@ -239,6 +300,22 @@ static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
 	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;
+}
+
 static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache,
 					      struct io_kiocb *req)
 {
@@ -260,6 +337,19 @@ static inline bool req_has_async_data(struct io_kiocb *req)
 	return req->flags & REQ_F_ASYNC_DATA;
 }
 
+static inline void io_req_async_data_clear(struct io_kiocb *req,
+					   io_req_flags_t extra_flags)
+{
+	req->flags &= ~(REQ_F_ASYNC_DATA|extra_flags);
+	req->async_data = NULL;
+}
+
+static inline void io_req_async_data_free(struct io_kiocb *req)
+{
+	kfree(req->async_data);
+	io_req_async_data_clear(req, 0);
+}
+
 static inline void io_put_file(struct io_kiocb *req)
 {
 	if (!(req->flags & REQ_F_FIXED_FILE) && req->file)
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 19a8bde5e1e1..aad655e38672 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -155,19 +155,19 @@ static int io_provided_buffers_select(struct io_kiocb *req, size_t *len,
 	return 1;
 }
 
-static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
-					  struct io_buffer_list *bl,
-					  unsigned int issue_flags)
+static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len,
+					      struct io_buffer_list *bl,
+					      unsigned int issue_flags)
 {
 	struct io_uring_buf_ring *br = bl->buf_ring;
 	__u16 tail, head = bl->head;
+	struct io_br_sel sel = { };
 	struct io_uring_buf *buf;
-	void __user *ret;
 	u32 buf_len;
 
 	tail = smp_load_acquire(&br->tail);
 	if (unlikely(tail == head))
-		return NULL;
+		return sel;
 
 	if (head + 1 == tail)
 		req->flags |= REQ_F_BL_EMPTY;
@@ -177,9 +177,9 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	if (*len == 0 || *len > buf_len)
 		*len = buf_len;
 	req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT;
-	req->buf_list = bl;
 	req->buf_index = buf->bid;
-	ret = u64_to_user_ptr(buf->addr);
+	sel.buf_list = bl;
+	sel.addr = u64_to_user_ptr(buf->addr);
 
 	if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) {
 		/*
@@ -192,30 +192,30 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 		 * the transfer completes (or if we get -EAGAIN and must poll of
 		 * retry).
 		 */
-		io_kbuf_commit(req, bl, *len, 1);
-		req->buf_list = NULL;
+		io_kbuf_commit(req, sel.buf_list, *len, 1);
+		sel.buf_list = NULL;
 	}
-	return ret;
+	return sel;
 }
 
-void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
-			      unsigned buf_group, unsigned int issue_flags)
+struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len,
+				  unsigned buf_group, unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_br_sel sel = { };
 	struct io_buffer_list *bl;
-	void __user *ret = NULL;
 
 	io_ring_submit_lock(req->ctx, issue_flags);
 
 	bl = io_buffer_get_list(ctx, buf_group);
 	if (likely(bl)) {
 		if (bl->flags & IOBL_BUF_RING)
-			ret = io_ring_buffer_select(req, len, bl, issue_flags);
+			sel = io_ring_buffer_select(req, len, bl, issue_flags);
 		else
-			ret = io_provided_buffer_select(req, len, bl);
+			sel.addr = io_provided_buffer_select(req, len, bl);
 	}
 	io_ring_submit_unlock(req->ctx, issue_flags);
-	return ret;
+	return sel;
 }
 
 /* cap it at a reasonable 256, will be one page even for 4K */