Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 131 insertions, 0 deletions

diff --git a/include/net/gue.h b/include/net/gue.h
new file mode 100644
index 000000000..d377155fd
--- /dev/null
+++ b/include/net/gue.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_GUE_H
+#define __NET_GUE_H
+
+/* Definitions for the GUE header, standard and private flags, lengths
+ * of optional fields are below.
+ *
+ * Diagram of GUE header:
+ *
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |Ver|C|  Hlen   | Proto/ctype   |        Standard flags       |P|
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                                                               |
+ * ~                      Fields (optional)                        ~
+ * |                                                               |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |            Private flags (optional, P bit is set)             |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                                                               |
+ * ~                   Private fields (optional)                   ~
+ * |                                                               |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * C bit indicates control message when set, data message when unset.
+ * For a control message, proto/ctype is interpreted as a type of
+ * control message. For data messages, proto/ctype is the IP protocol
+ * of the next header.
+ *
+ * P bit indicates private flags field is present. The private flags
+ * may refer to options placed after this field.
+ */
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8	hlen:5,
+				control:1,
+				version:2;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+			__u8	version:2,
+				control:1,
+				hlen:5;
+#else
+#error  "Please fix <asm/byteorder.h>"
+#endif
+			__u8	proto_ctype;
+			__be16	flags;
+		};
+		__be32	word;
+	};
+};
+
+/* Standard flags in GUE header */
+
+#define GUE_FLAG_PRIV	htons(1<<0)	/* Private flags are in options */
+#define GUE_LEN_PRIV	4
+
+#define GUE_FLAGS_ALL	(GUE_FLAG_PRIV)
+
+/* Private flags in the private option extension */
+
+#define GUE_PFLAG_REMCSUM	htonl(1U << 31)
+#define GUE_PLEN_REMCSUM	4
+
+#define GUE_PFLAGS_ALL	(GUE_PFLAG_REMCSUM)
+
+/* Functions to compute options length corresponding to flags.
+ * If we ever have a lot of flags this can be potentially be
+ * converted to a more optimized algorithm (table lookup
+ * for instance).
+ */
+static inline size_t guehdr_flags_len(__be16 flags)
+{
+	return ((flags & GUE_FLAG_PRIV) ? GUE_LEN_PRIV : 0);
+}
+
+static inline size_t guehdr_priv_flags_len(__be32 flags)
+{
+	return (flags & GUE_PFLAG_REMCSUM) ? GUE_PLEN_REMCSUM : 0;
+}
+
+/* Validate standard and private flags. Returns non-zero (meaning invalid)
+ * if there is an unknown standard or private flags, if the options length for
+ * the flags exceeds the options length specified in hlen of the GUE header, or
+ * if a private option contains invalid data.
+ */
+static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen)
+{
+	__be16 flags = guehdr->flags;
+	size_t len;
+
+	if (flags & ~GUE_FLAGS_ALL)
+		return 1;
+
+	len = guehdr_flags_len(flags);
+	if (len > optlen)
+		return 1;
+
+	if (flags & GUE_FLAG_PRIV) {
+		/* Private flags are last four bytes accounted in
+		 * guehdr_flags_len
+		 */
+		void *data = (void *)&guehdr[1] + len;
+		__be32 pflags = *(__be32 *)(data - GUE_LEN_PRIV);
+
+		if (pflags & ~GUE_PFLAGS_ALL)
+			return 1;
+
+		len += guehdr_priv_flags_len(pflags);
+		if (len > optlen)
+			return 1;
+
+		if (pflags & GUE_PFLAG_REMCSUM) {
+			__be16 *pd = data;
+
+			/* The field offset pd[1] must not be less
+			 * than the start pd[0].
+			 */
+			if (ntohs(pd[1]) < ntohs(pd[0]))
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+#endif