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, 116 insertions, 0 deletions

diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h
new file mode 100644
index 000000000..65151b681
--- /dev/null
+++ b/include/vdso/helpers.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_HELPERS_H
+#define __VDSO_HELPERS_H
+
+#ifndef __ASSEMBLER__
+
+#include <asm/barrier.h>
+#include <vdso/datapage.h>
+#include <vdso/processor.h>
+#include <vdso/clocksource.h>
+
+static __always_inline bool vdso_is_timens_clock(const struct vdso_clock *vc)
+{
+	return IS_ENABLED(CONFIG_TIME_NS) && vc->clock_mode == VDSO_CLOCKMODE_TIMENS;
+}
+
+static __always_inline u32 vdso_read_begin(const struct vdso_clock *vc)
+{
+	u32 seq;
+
+	while (unlikely((seq = READ_ONCE(vc->seq)) & 1))
+		cpu_relax();
+
+	smp_rmb();
+	return seq;
+}
+
+/*
+ * Variant of vdso_read_begin() to handle VDSO_CLOCKMODE_TIMENS.
+ *
+ * Time namespace enabled tasks have a special VVAR page installed which has
+ * vc->seq set to 1 and vc->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non
+ * time namespace affected tasks this does not affect performance because if
+ * vc->seq is odd, i.e. a concurrent update is in progress the extra check for
+ * vc->clock_mode is just a few extra instructions while spin waiting for
+ * vc->seq to become even again.
+ */
+static __always_inline bool vdso_read_begin_timens(const struct vdso_clock *vc, u32 *seq)
+{
+	while (unlikely((*seq = READ_ONCE(vc->seq)) & 1)) {
+		if (vdso_is_timens_clock(vc))
+			return true;
+		cpu_relax();
+	}
+	smp_rmb();
+
+	return false;
+}
+
+static __always_inline u32 vdso_read_retry(const struct vdso_clock *vc,
+					   u32 start)
+{
+	u32 seq;
+
+	smp_rmb();
+	seq = READ_ONCE(vc->seq);
+	return unlikely(seq != start);
+}
+
+static __always_inline void vdso_write_seq_begin(struct vdso_clock *vc)
+{
+	/*
+	 * WRITE_ONCE() is required otherwise the compiler can validly tear
+	 * updates to vc->seq and it is possible that the value seen by the
+	 * reader is inconsistent.
+	 */
+	WRITE_ONCE(vc->seq, vc->seq + 1);
+}
+
+static __always_inline void vdso_write_seq_end(struct vdso_clock *vc)
+{
+	/*
+	 * WRITE_ONCE() is required otherwise the compiler can validly tear
+	 * updates to vc->seq and it is possible that the value seen by the
+	 * reader is inconsistent.
+	 */
+	WRITE_ONCE(vc->seq, vc->seq + 1);
+}
+
+static __always_inline void vdso_write_begin_clock(struct vdso_clock *vc)
+{
+	vdso_write_seq_begin(vc);
+	/* Ensure the sequence invalidation is visible before data is modified */
+	smp_wmb();
+}
+
+static __always_inline void vdso_write_end_clock(struct vdso_clock *vc)
+{
+	/* Ensure the data update is visible before the sequence is set valid again */
+	smp_wmb();
+	vdso_write_seq_end(vc);
+}
+
+static __always_inline void vdso_write_begin(struct vdso_time_data *vd)
+{
+	struct vdso_clock *vc = vd->clock_data;
+
+	vdso_write_seq_begin(&vc[CS_HRES_COARSE]);
+	vdso_write_seq_begin(&vc[CS_RAW]);
+	/* Ensure the sequence invalidation is visible before data is modified */
+	smp_wmb();
+}
+
+static __always_inline void vdso_write_end(struct vdso_time_data *vd)
+{
+	struct vdso_clock *vc = vd->clock_data;
+
+	/* Ensure the data update is visible before the sequence is set valid again */
+	smp_wmb();
+	vdso_write_seq_end(&vc[CS_HRES_COARSE]);
+	vdso_write_seq_end(&vc[CS_RAW]);
+}
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /* __VDSO_HELPERS_H */