Merge tag 'for-7.2/io_uring-20260615' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring updates from Jens Axboe:

 - Rework the task_work infrastructure.

   Both the local (DEFER_TASKRUN) and the normal (tctx) task_work lists
   were llist based, which is LIFO ordered, and hence each run had to do
   an O(n) list reversal pass first to restore queue order.
   Additionally, to cap the amount of task_work run, each method needed
   a retry list as well.

   Add a lockless MPCS FIFO queue (based on Dmitry Vyukov's intrusive
   MPSC algorithm) and switch both task_work lists to it. It performs
   better than llists and we can then also ditch the retry lists as well
   as entries are popped one-at-the-time.

   On top of those changes, run the tctx fallback task_work directly and
   remove the now-unused per-ctx fallback machinery entirely.

 - zcrx user notifications.

   Add a mechanism for zcrx to communicate conditions back to userspace
   via a dedicated CQE, with the initial users being notification on
   running out of buffers and on a frag copy fallback, plus
   shared-memory notification statistics.

   Alongside that, a series of zcrx reliability and cleanup fixes: more
   reliable scrubbing, poisoning pointers on unregistration, dropping an
   extra ifq close, adding a ctx back-pointer, reordering fd allocation
   in the export path, and killing a dead 'sock' member.

 - Allow using io_uring registered buffers for plain SEND and RECV, not
   just for the zero-copy send path.

   This enables targets like ublk's NBD backend to push/pull IO data
   directly to/from a registered buffer over a plain send/recv on a TCP
   socket.

 - Registered buffer improvements: account huge pages correctly, bump
   the io_mapped_ubuf length field to size_t, and raise the previous 1GB
   registered buffer size limit.

 - Restrict the ctx access exposed to io_uring BPF struct_ops programs
   by handing them an opaque type rather than the full io_ring_ctx, and
   add a separate MAINTAINERS entry for the bpf-ops code.

 - Allow opcode filtering on IORING_OP_CONNECT.

 - Validate ring-provided buffer addresses with access_ok(), and align
   the legacy buffer add limit with MAX_BIDS_PER_BGID.

 - Various other cleanups and minor fixes, including avoiding msghdr
   async data on connect/bind, dropping async_size for OP_LISTEN, making
   the POLL_FIRST receive side checks consistent, re-checking
   IO_WQ_BIT_EXIT for each linked work item, and using
   trace_call__##name() at guarded tracepoint call sites.

* tag 'for-7.2/io_uring-20260615' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (31 commits)
  io_uring/bpf-ops: add a separate maintainer entry
  io_uring/net: make POLL_FIRST receive side checks consistent
  io_uring: remove the per-ctx fallback task_work machinery
  io_uring: run the tctx task_work fallback directly
  io_uring: switch normal task_work to a mpscq
  io_uring: switch local task_work to a mpscq
  io_uring/mpscq: add lockless multi-producer, single-consumer FIFO queue
  io_uring: grab RCU read lock marking task run
  io_uring/zcrx: kill dead 'sock' member in struct io_zcrx_args
  io_uring/kbuf: validate ring provided buffer addresses with access_ok()
  io_uring/net: support registered buffer for plain send and recv
  io_uring/nop: Drop a wrong comment in struct io_nop
  io_uring/net: Remove async_size for OP_LISTEN
  io_uring/net: Avoid msghdr on op_connect/op_bind async data
  io_uring/bpf-ops: restrict ctx access to BPF
  io_uring/io-wq: re-check IO_WQ_BIT_EXIT for each linked work item
  io_uring/kbuf: align legacy buffer add limit with MAX_BIDS_PER_BGID
  io_uring/zcrx: add shared-memory notification statistics
  io_uring/zcrx: notify user on frag copy fallback
  io_uring/zcrx: notify user when out of buffers
  ...

3 files changed, 63 insertions, 1 deletions

diff --git a/include/uapi/linux/io_uring/bpf_filter.h b/include/uapi/linux/io_uring/bpf_filter.h
index 1b461d792a7b..ce7d78ab13b3 100644
--- a/include/uapi/linux/io_uring/bpf_filter.h
+++ b/include/uapi/linux/io_uring/bpf_filter.h
@@ -27,6 +27,22 @@ struct io_uring_bpf_ctx {
 			__u64	mode;
 			__u64	resolve;
 		} open;
+		/*
+		 * For CONNECT: fields are populated only when addr_len covers
+		 * them; unpopulated fields are zero from the caller-side memset
+		 * in io_uring_populate_bpf_ctx(). port and v4_addr are network
+		 * byte order. Filters may only issue BPF_LD|BPF_W|BPF_ABS at
+		 * 4-byte aligned offsets; load + mask for sub-word fields.
+		 */
+		struct {
+			__u32	family;	/* sa_family_t zero-extended */
+			__be16	port;
+			__u8	pad[2];
+			union {
+				__be32	v4_addr;
+				__u8	v6_addr[16];
+			};
+		} connect;
 	};
 };
 
diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h
index 95500759cc13..1a68eca7c6b4 100644
--- a/include/uapi/linux/io_uring/query.h
+++ b/include/uapi/linux/io_uring/query.h
@@ -23,6 +23,7 @@ enum {
 	IO_URING_QUERY_OPCODES			= 0,
 	IO_URING_QUERY_ZCRX			= 1,
 	IO_URING_QUERY_SCQ			= 2,
+	IO_URING_QUERY_ZCRX_NOTIF		= 3,
 
 	__IO_URING_QUERY_MAX,
 };
@@ -62,6 +63,17 @@ struct io_uring_query_zcrx {
 	__u64 __resv2;
 };
 
+struct io_uring_query_zcrx_notif {
+	/* Bitmask of supported ZCRX_NOTIF_* flags */
+	__u32 notif_flags;
+	/* Size of io_uring_zcrx_notif_stats */
+	__u32 notif_stats_size;
+	/* Required alignment for the stats struct within the region (ie stats_offset) */
+	__u32 notif_stats_off_alignment;
+	__u32 __resv1;
+	__u64 __resv2[4];
+};
+
 struct io_uring_query_scq {
 	/* The SQ/CQ rings header size */
 	__u64 hdr_size;
diff --git a/include/uapi/linux/io_uring/zcrx.h b/include/uapi/linux/io_uring/zcrx.h
index 5ce02c7a6096..15c05c45ce36 100644
--- a/include/uapi/linux/io_uring/zcrx.h
+++ b/include/uapi/linux/io_uring/zcrx.h
@@ -65,6 +65,32 @@ enum zcrx_features {
 	 * value in struct io_uring_zcrx_ifq_reg::rx_buf_len.
 	 */
 	ZCRX_FEATURE_RX_PAGE_SIZE	= 1 << 0,
+	ZCRX_FEATURE_NOTIFICATION	= 1 << 1,
+};
+
+enum zcrx_notification_type {
+	ZCRX_NOTIF_NO_BUFFERS,
+	ZCRX_NOTIF_COPY,
+
+	__ZCRX_NOTIF_TYPE_LAST,
+};
+
+enum zcrx_notification_desc_flags {
+	/* If set, stats_offset holds a valid offset to a notif_stats struct */
+	ZCRX_NOTIF_DESC_FLAG_STATS = 1 << 0,
+};
+
+struct zcrx_notif_stats {
+	__u64	copy_count;	/* cumulative copy-fallback CQEs */
+	__u64	copy_bytes;	/* cumulative bytes copied */
+};
+
+struct zcrx_notification_desc {
+	__u64	user_data;
+	__u32	type_mask;
+	__u32	flags; /* see enum zcrx_notification_desc_flags */
+	__u64	stats_offset; /* offset from the beginning of refill ring region for stats */
+	__u64	__resv2[9];
 };
 
 /*
@@ -82,12 +108,14 @@ struct io_uring_zcrx_ifq_reg {
 	struct io_uring_zcrx_offsets offsets;
 	__u32	zcrx_id;
 	__u32	rx_buf_len;
-	__u64	__resv[3];
+	__u64	notif_desc; /* see struct zcrx_notification_desc */
+	__u64	__resv[2];
 };
 
 enum zcrx_ctrl_op {
 	ZCRX_CTRL_FLUSH_RQ,
 	ZCRX_CTRL_EXPORT,
+	ZCRX_CTRL_ARM_NOTIFICATION,
 
 	__ZCRX_CTRL_LAST,
 };
@@ -101,6 +129,11 @@ struct zcrx_ctrl_export {
 	__u32 		__resv1[11];
 };
 
+struct zcrx_ctrl_arm_notif {
+	__u32		notif_type;
+	__u32		__resv[11];
+};
+
 struct zcrx_ctrl {
 	__u32	zcrx_id;
 	__u32	op; /* see enum zcrx_ctrl_op */
@@ -109,6 +142,7 @@ struct zcrx_ctrl {
 	union {
 		struct zcrx_ctrl_export		zc_export;
 		struct zcrx_ctrl_flush_rq	zc_flush;
+		struct zcrx_ctrl_arm_notif	zc_arm_notif;
 	};
 };