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

3 files changed, 209 insertions, 0 deletions

diff --git a/tools/perf/util/hisi-ptt-decoder/Build b/tools/perf/util/hisi-ptt-decoder/Build
new file mode 100644
index 000000000..2ee0eb731
--- /dev/null
+++ b/tools/perf/util/hisi-ptt-decoder/Build
@@ -0,0 +1 @@
+perf-util-y += hisi-ptt-pkt-decoder.o
diff --git a/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c
new file mode 100644
index 000000000..72a877fd7
--- /dev/null
+++ b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HiSilicon PCIe Trace and Tuning (PTT) support
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/unaligned.h>
+#include <stdarg.h>
+
+#include "../color.h"
+#include "hisi-ptt-pkt-decoder.h"
+
+/*
+ * For 8DW format, the bit[31:11] of DW0 is always 0x1fffff, which can be
+ * used to distinguish the data format.
+ * 8DW format is like:
+ *   bits [                 31:11                 ][       10:0       ]
+ *        |---------------------------------------|-------------------|
+ *    DW0 [                0x1fffff               ][ Reserved (0x7ff) ]
+ *    DW1 [                       Prefix                              ]
+ *    DW2 [                     Header DW0                            ]
+ *    DW3 [                     Header DW1                            ]
+ *    DW4 [                     Header DW2                            ]
+ *    DW5 [                     Header DW3                            ]
+ *    DW6 [                   Reserved (0x0)                          ]
+ *    DW7 [                        Time                               ]
+ *
+ * 4DW format is like:
+ *   bits [31:30] [ 29:25 ][24][23][22][21][    20:11   ][    10:0    ]
+ *        |-----|---------|---|---|---|---|-------------|-------------|
+ *    DW0 [ Fmt ][  Type  ][T9][T8][TH][SO][   Length   ][    Time    ]
+ *    DW1 [                     Header DW1                            ]
+ *    DW2 [                     Header DW2                            ]
+ *    DW3 [                     Header DW3                            ]
+ */
+
+enum hisi_ptt_8dw_pkt_field_type {
+	HISI_PTT_8DW_CHK_AND_RSV0,
+	HISI_PTT_8DW_PREFIX,
+	HISI_PTT_8DW_HEAD0,
+	HISI_PTT_8DW_HEAD1,
+	HISI_PTT_8DW_HEAD2,
+	HISI_PTT_8DW_HEAD3,
+	HISI_PTT_8DW_RSV1,
+	HISI_PTT_8DW_TIME,
+	HISI_PTT_8DW_TYPE_MAX
+};
+
+enum hisi_ptt_4dw_pkt_field_type {
+	HISI_PTT_4DW_HEAD1,
+	HISI_PTT_4DW_HEAD2,
+	HISI_PTT_4DW_HEAD3,
+	HISI_PTT_4DW_TYPE_MAX
+};
+
+static const char * const hisi_ptt_8dw_pkt_field_name[] = {
+	[HISI_PTT_8DW_PREFIX]	= "Prefix",
+	[HISI_PTT_8DW_HEAD0]	= "Header DW0",
+	[HISI_PTT_8DW_HEAD1]	= "Header DW1",
+	[HISI_PTT_8DW_HEAD2]	= "Header DW2",
+	[HISI_PTT_8DW_HEAD3]	= "Header DW3",
+	[HISI_PTT_8DW_TIME]	= "Time"
+};
+
+static const char * const hisi_ptt_4dw_pkt_field_name[] = {
+	[HISI_PTT_4DW_HEAD1]	= "Header DW1",
+	[HISI_PTT_4DW_HEAD2]	= "Header DW2",
+	[HISI_PTT_4DW_HEAD3]	= "Header DW3",
+};
+
+static void hisi_ptt_print_pkt(const unsigned char *buf, int pos, const char *desc)
+{
+	const char *color = PERF_COLOR_BLUE;
+	uint8_t byte;
+	uint32_t dw;
+	int i;
+
+	dw = get_unaligned_le32(buf + pos);
+	printf(".");
+	color_fprintf(stdout, color, "  %08x: ", pos);
+	for (i = 0; i < HISI_PTT_FIELD_LENGTH; i++) {
+		byte = (dw >> (24 - i * 8)) & 0xFF;
+		color_fprintf(stdout, color, "%02x ", byte);
+	}
+	for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++)
+		color_fprintf(stdout, color, "   ");
+	color_fprintf(stdout, color, "  %s\n", desc);
+}
+
+static int hisi_ptt_8dw_pkt_desc(const unsigned char *buf, int pos)
+{
+	int i;
+
+	for (i = 0; i < HISI_PTT_8DW_TYPE_MAX; i++) {
+		/* Do not show 8DW check field and reserved fields */
+		if (i == HISI_PTT_8DW_CHK_AND_RSV0 || i == HISI_PTT_8DW_RSV1) {
+			pos += HISI_PTT_FIELD_LENGTH;
+			continue;
+		}
+
+		hisi_ptt_print_pkt(buf, pos, hisi_ptt_8dw_pkt_field_name[i]);
+		pos += HISI_PTT_FIELD_LENGTH;
+	}
+
+	return hisi_ptt_pkt_size[HISI_PTT_8DW_PKT];
+}
+
+static void hisi_ptt_4dw_print_dw0(const unsigned char *buf, int pos)
+{
+	const char *color = PERF_COLOR_BLUE;
+	uint8_t byte;
+	uint32_t dw;
+	int i;
+
+	dw = get_unaligned_le32(buf + pos);
+	printf(".");
+	color_fprintf(stdout, color, "  %08x: ", pos);
+	for (i = 0; i < HISI_PTT_FIELD_LENGTH; i++) {
+		byte = (dw >> (24 - i * 8)) & 0xFF;
+		color_fprintf(stdout, color, "%02x ", byte);
+	}
+	for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++)
+		color_fprintf(stdout, color, "   ");
+
+	color_fprintf(stdout, color,
+		      "  %s %x %s %x %s %x %s %x %s %x %s %x %s %x %s %x\n",
+		      "Format", FIELD_GET(HISI_PTT_HEAD0_4DW_FORMAT, dw),
+		      "Type", FIELD_GET(HISI_PTT_HEAD0_4DW_TYPE, dw),
+		      "T9", FIELD_GET(HISI_PTT_HEAD0_4DW_T9, dw),
+		      "T8", FIELD_GET(HISI_PTT_HEAD0_4DW_T8, dw),
+		      "TH", FIELD_GET(HISI_PTT_HEAD0_4DW_TH, dw),
+		      "SO", FIELD_GET(HISI_PTT_HEAD0_4DW_SO, dw),
+		      "Length", FIELD_GET(HISI_PTT_HEAD0_4DW_LEN, dw),
+		      "Time", FIELD_GET(HISI_PTT_HEAD0_4DW_TIME, dw));
+}
+
+static int hisi_ptt_4dw_pkt_desc(const unsigned char *buf, int pos)
+{
+	int i;
+
+	hisi_ptt_4dw_print_dw0(buf, pos);
+	pos += HISI_PTT_FIELD_LENGTH;
+
+	for (i = 0; i < HISI_PTT_4DW_TYPE_MAX; i++) {
+		hisi_ptt_print_pkt(buf, pos, hisi_ptt_4dw_pkt_field_name[i]);
+		pos += HISI_PTT_FIELD_LENGTH;
+	}
+
+	return hisi_ptt_pkt_size[HISI_PTT_4DW_PKT];
+}
+
+int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type)
+{
+	if (type == HISI_PTT_8DW_PKT)
+		return hisi_ptt_8dw_pkt_desc(buf, pos);
+
+	return hisi_ptt_4dw_pkt_desc(buf, pos);
+}
diff --git a/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h
new file mode 100644
index 000000000..3b349fcc2
--- /dev/null
+++ b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * HiSilicon PCIe Trace and Tuning (PTT) support
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ */
+
+#ifndef INCLUDE__HISI_PTT_PKT_DECODER_H__
+#define INCLUDE__HISI_PTT_PKT_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
+
+#define HISI_PTT_8DW_CHECK_MASK		GENMASK(31, 11)
+#define HISI_PTT_IS_8DW_PKT		GENMASK(31, 11)
+#define HISI_PTT_MAX_SPACE_LEN		10
+#define HISI_PTT_FIELD_LENGTH		4
+
+/* Header DW0 fields for 4DW format */
+#define HISI_PTT_HEAD0_4DW_TIME		GENMASK_U32(10, 0)
+#define HISI_PTT_HEAD0_4DW_LEN		GENMASK_U32(20, 11)
+#define HISI_PTT_HEAD0_4DW_SO		BIT_U32(21)
+#define HISI_PTT_HEAD0_4DW_TH		BIT_U32(22)
+#define HISI_PTT_HEAD0_4DW_T8		BIT_U32(23)
+#define HISI_PTT_HEAD0_4DW_T9		BIT_U32(24)
+#define HISI_PTT_HEAD0_4DW_TYPE		GENMASK_U32(29, 25)
+#define HISI_PTT_HEAD0_4DW_FORMAT	GENMASK_U32(31, 30)
+
+enum hisi_ptt_pkt_type {
+	HISI_PTT_4DW_PKT,
+	HISI_PTT_8DW_PKT,
+	HISI_PTT_PKT_MAX
+};
+
+static int hisi_ptt_pkt_size[] = {
+	[HISI_PTT_4DW_PKT]	= 16,
+	[HISI_PTT_8DW_PKT]	= 32,
+};
+
+int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type);
+
+#endif