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

2 files changed, 94 insertions, 0 deletions

diff --git a/tools/tracing/rtla/example/timerlat_bpf_action.c b/tools/tracing/rtla/example/timerlat_bpf_action.c
new file mode 100644
index 000000000..ac1be049a
--- /dev/null
+++ b/tools/tracing/rtla/example/timerlat_bpf_action.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_tracing.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+struct trace_event_raw_timerlat_sample {
+	unsigned long long timer_latency;
+} __attribute__((preserve_access_index));
+
+SEC("tp/timerlat_action")
+int action_handler(struct trace_event_raw_timerlat_sample *tp_args)
+{
+	bpf_printk("Latency: %lld\n", tp_args->timer_latency);
+	return 0;
+}
diff --git a/tools/tracing/rtla/example/timerlat_load.py b/tools/tracing/rtla/example/timerlat_load.py
new file mode 100644
index 000000000..a819c3588
--- /dev/null
+++ b/tools/tracing/rtla/example/timerlat_load.py
@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2024 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
+#
+# This is a sample code about how to use timerlat's timer by any workload
+# so rtla can measure and provide auto-analysis for the overall latency (IOW
+# the response time) for a task.
+#
+# Before running it, you need to dispatch timerlat with -U option in a terminal.
+# Then # run this script pinned to a CPU on another terminal. For example:
+#
+# timerlat_load.py 1 -p 95
+#
+# The "Timerlat IRQ" is the IRQ latency, The thread latency is the latency
+# for the python process to get the CPU. The Ret from user Timer Latency is
+# the overall latency. In other words, it is the response time for that
+# activation.
+#
+# This is just an example, the load is reading 20MB of data from /dev/full
+# It is in python because it is easy to read :-)
+
+import argparse
+import sys
+import os
+
+parser = argparse.ArgumentParser(description='user-space timerlat thread in Python')
+parser.add_argument("cpu", type=int, help='CPU to run timerlat thread')
+parser.add_argument("-p", "--prio", type=int, help='FIFO priority')
+args = parser.parse_args()
+
+try:
+    affinity_mask = {args.cpu}
+    os.sched_setaffinity(0, affinity_mask)
+except Exception as e:
+    print(f"Error setting affinity: {e}")
+    sys.exit(1)
+
+if args.prio:
+    try:
+        param = os.sched_param(args.prio)
+        os.sched_setscheduler(0, os.SCHED_FIFO, param)
+    except Exception as e:
+        print(f"Error setting priority: {e}")
+        sys.exit(1)
+
+try:
+    timerlat_path = f"/sys/kernel/tracing/osnoise/per_cpu/cpu{args.cpu}/timerlat_fd"
+    timerlat_fd = open(timerlat_path, 'r')
+except PermissionError:
+    print("Permission denied. Please check your access rights.")
+    sys.exit(1)
+except OSError:
+    print("Error opening timerlat fd, did you run timerlat -U?")
+    sys.exit(1)
+
+try:
+    data_fd = open("/dev/full", 'r')
+except Exception as e:
+    print(f"Error opening data fd: {e}")
+    sys.exit(1)
+
+while True:
+    try:
+        timerlat_fd.read(1)
+        data_fd.read(20 * 1024 * 1024)
+    except KeyboardInterrupt:
+        print("Leaving")
+        break
+    except IOError as e:
+        print(f"I/O error occurred: {e}")
+        break
+    except Exception as e:
+        print(f"Unexpected error: {e}")
+        break
+
+timerlat_fd.close()
+data_fd.close()