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, 84 insertions, 0 deletions

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
new file mode 100644
index 000000000..856b5e90f
--- /dev/null
+++ b/include/net/gen_stats.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_GEN_STATS_H
+#define __NET_GEN_STATS_H
+
+#include <linux/gen_stats.h>
+#include <linux/socket.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_sched.h>
+
+/* Throughput stats.
+ * Must be initialized beforehand with gnet_stats_basic_sync_init().
+ *
+ * If no reads can ever occur parallel to writes (e.g. stack-allocated
+ * bstats), then the internal stat values can be written to and read
+ * from directly. Otherwise, use _bstats_set/update() for writes and
+ * gnet_stats_add_basic() for reads.
+ */
+struct gnet_stats_basic_sync {
+	u64_stats_t bytes;
+	u64_stats_t packets;
+	struct u64_stats_sync syncp;
+} __aligned(2 * sizeof(u64));
+
+struct net_rate_estimator;
+
+struct gnet_dump {
+	spinlock_t *      lock;
+	struct sk_buff *  skb;
+	struct nlattr *   tail;
+
+	/* Backward compatibility */
+	int               compat_tc_stats;
+	int               compat_xstats;
+	int               padattr;
+	void *            xstats;
+	int               xstats_len;
+	struct tc_stats   tc_stats;
+};
+
+void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b);
+int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
+			  struct gnet_dump *d, int padattr);
+
+int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
+				 int tc_stats_type, int xstats_type,
+				 spinlock_t *lock, struct gnet_dump *d,
+				 int padattr);
+
+int gnet_stats_copy_basic(struct gnet_dump *d,
+			  const struct gnet_stats_basic_sync __percpu *cpu,
+			  const struct gnet_stats_basic_sync *b, bool running);
+void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats,
+			  const struct gnet_stats_basic_sync __percpu *cpu,
+			  const struct gnet_stats_basic_sync *b, bool running);
+int gnet_stats_copy_basic_hw(struct gnet_dump *d,
+			     const struct gnet_stats_basic_sync __percpu *cpu,
+			     const struct gnet_stats_basic_sync *b, bool running);
+int gnet_stats_copy_rate_est(struct gnet_dump *d,
+			     struct net_rate_estimator __rcu **ptr);
+int gnet_stats_copy_queue(struct gnet_dump *d,
+			  const struct gnet_stats_queue __percpu *cpu_q,
+			  const struct gnet_stats_queue *q, __u32 qlen);
+void gnet_stats_add_queue(struct gnet_stats_queue *qstats,
+			  const struct gnet_stats_queue __percpu *cpu_q,
+			  const struct gnet_stats_queue *q);
+int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
+
+int gnet_stats_finish_copy(struct gnet_dump *d);
+
+int gen_new_estimator(struct gnet_stats_basic_sync *bstats,
+		      struct gnet_stats_basic_sync __percpu *cpu_bstats,
+		      struct net_rate_estimator __rcu **rate_est,
+		      spinlock_t *lock,
+		      bool running, struct nlattr *opt);
+void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
+int gen_replace_estimator(struct gnet_stats_basic_sync *bstats,
+			  struct gnet_stats_basic_sync __percpu *cpu_bstats,
+			  struct net_rate_estimator __rcu **ptr,
+			  spinlock_t *lock,
+			  bool running, struct nlattr *opt);
+bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
+bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
+			struct gnet_stats_rate_est64 *sample);
+#endif