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, 121 insertions, 0 deletions

diff --git a/samples/bpf/xdp_sample.bpf.h b/samples/bpf/xdp_sample.bpf.h
new file mode 100644
index 000000000..fecc41c5d
--- /dev/null
+++ b/samples/bpf/xdp_sample.bpf.h
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _XDP_SAMPLE_BPF_H
+#define _XDP_SAMPLE_BPF_H
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+#include "net_shared.h"
+#include "xdp_sample_shared.h"
+
+#define EINVAL 22
+#define ENETDOWN 100
+#define EMSGSIZE 90
+#define EOPNOTSUPP 95
+#define ENOSPC 28
+
+typedef struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, unsigned int);
+	__type(value, struct datarec);
+} array_map;
+
+extern array_map rx_cnt;
+extern const volatile int nr_cpus;
+
+enum {
+	XDP_REDIRECT_SUCCESS = 0,
+	XDP_REDIRECT_ERROR = 1
+};
+
+static __always_inline void swap_src_dst_mac(void *data)
+{
+	unsigned short *p = data;
+	unsigned short dst[3];
+
+	dst[0] = p[0];
+	dst[1] = p[1];
+	dst[2] = p[2];
+	p[0] = p[3];
+	p[1] = p[4];
+	p[2] = p[5];
+	p[3] = dst[0];
+	p[4] = dst[1];
+	p[5] = dst[2];
+}
+
+/*
+ * Note: including linux/compiler.h or linux/kernel.h for the macros below
+ * conflicts with vmlinux.h include in BPF files, so we define them here.
+ *
+ * Following functions are taken from kernel sources and
+ * break aliasing rules in their original form.
+ *
+ * While kernel is compiled with -fno-strict-aliasing,
+ * perf uses -Wstrict-aliasing=3 which makes build fail
+ * under gcc 4.4.
+ *
+ * Using extra __may_alias__ type to allow aliasing
+ * in this case.
+ */
+typedef __u8  __attribute__((__may_alias__))  __u8_alias_t;
+typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
+typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
+typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8_alias_t  *) res = *(volatile __u8_alias_t  *) p; break;
+	case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
+	case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
+	case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
+	default:
+		asm volatile ("" : : : "memory");
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		asm volatile ("" : : : "memory");
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile  __u8_alias_t *) p = *(__u8_alias_t  *) res; break;
+	case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
+	case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
+	case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
+	default:
+		asm volatile ("" : : : "memory");
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		asm volatile ("" : : : "memory");
+	}
+}
+
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+/* Add a value using relaxed read and relaxed write. Less expensive than
+ * fetch_add when there is no write concurrency.
+ */
+#define NO_TEAR_ADD(x, val) WRITE_ONCE((x), READ_ONCE(x) + (val))
+#define NO_TEAR_INC(x) NO_TEAR_ADD((x), 1)
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#endif