Merge tag 'perf-tools-fixes-for-v6.12-1-2024-10-08' of...

Merge tag 'perf-tools-fixes-for-v6.12-1-2024-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix an assert() to handle captured and unprocessed ARM CoreSight CPU
   traces

 - Fix static build compilation error when libdw isn't installed or is
   too old

 - Add missing include when building with
   !HAVE_DWARF_GETLOCATIONS_SUPPORT

 - Add missing refcount put on 32-bit DSOs

 - Fix disassembly of user space binaries by setting the binary_type of
   DSO when loading

 - Update headers with the kernel sources, including asound.h, sched.h,
   fcntl, msr-index.h, irq_vectors.h, socket.h, list_sort.c and arm64's
   cputype.h

* tag 'perf-tools-fixes-for-v6.12-1-2024-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
  perf cs-etm: Fix the assert() to handle captured and unprocessed cpu trace
  perf build: Fix build feature-dwarf_getlocations fail for old libdw
  perf build: Fix static compilation error when libdw is not installed
  perf dwarf-aux: Fix build with !HAVE_DWARF_GETLOCATIONS_SUPPORT
  tools headers arm64: Sync arm64's cputype.h with the kernel sources
  perf tools: Cope with differences for lib/list_sort.c copy from the kernel
  tools check_headers.sh: Add check variant that excludes some hunks
  perf beauty: Update copy of linux/socket.h with the kernel sources
  tools headers UAPI: Sync the linux/in.h with the kernel sources
  perf trace beauty: Update the arch/x86/include/asm/irq_vectors.h copy with the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools include UAPI: Sync linux/fcntl.h copy with the kernel sources
  tools include UAPI: Sync linux/sched.h copy with the kernel sources
  tools include UAPI: Sync sound/asound.h copy with the kernel sources
  perf vdso: Missed put on 32-bit dsos
  perf symbol: Set binary_type of dso when loading

tools/arch/arm64/include/asm/cputype.h

@@ -143,6 +143,7 @@
 #define APPLE_CPU_PART_M2_AVALANCHE_MAX	0x039
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
+#define AMPERE_CPU_PART_AMPERE1A	0xAC4
 
 #define MICROSOFT_CPU_PART_AZURE_COBALT_100	0xD49 /* Based on r0p0 of ARM Neoverse N2 */
 
@@ -212,6 +213,7 @@
 #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
 #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_AMPERE1A MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1A)
 #define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */

tools/arch/x86/include/asm/msr-index.h

@@ -247,6 +247,8 @@
 #define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
+#define MSR_INTEGRITY_CAPS_SBAF_BIT		8
+#define MSR_INTEGRITY_CAPS_SBAF			BIT(MSR_INTEGRITY_CAPS_SBAF_BIT)
 #define MSR_INTEGRITY_CAPS_SAF_GEN_MASK	GENMASK_ULL(10, 9)
 
 #define MSR_LBR_NHM_FROM		0x00000680

tools/build/feature/Makefile

@@ -172,7 +172,7 @@ DWARFLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
   DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd
 
-  LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw)
+  LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0
   LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION)))
   LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION)))
 
@@ -181,6 +181,9 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
   ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0)
     DWARFLIBS += -lebl
   endif
+
+  # Must put -ldl after -lebl for dependency
+  DWARFLIBS += -ldl
 endif
 
 $(OUTPUT)test-dwarf.bin:

tools/include/uapi/linux/in.h

@@ -141,7 +141,7 @@ struct in_addr {
  */
 #define IP_PMTUDISC_INTERFACE		4
 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
- * fragmented if they exeed the interface mtu
+ * fragmented if they exceed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
 

tools/perf/Makefile.config

@@ -147,9 +147,9 @@ ifdef LIBDW_DIR
 endif
 DWARFLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
-  DWARFLIBS += -lelf -ldl -lz -llzma -lbz2 -lzstd
+  DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd
 
-  LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw)
+  LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0
   LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION)))
   LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION)))
 
@@ -158,6 +158,9 @@ ifeq ($(findstring -static,${LDFLAGS}),-static)
   ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0)
     DWARFLIBS += -lebl
   endif
+
+  # Must put -ldl after -lebl for dependency
+  DWARFLIBS += -ldl
 endif
 FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS)

tools/perf/check-header_ignore_hunks/lib/list_sort.c

+@@ -1,5 +1,6 @@
+ // SPDX-License-Identifier: GPL-2.0
+ #include <linux/kernel.h>
++#include <linux/bug.h>
+ #include <linux/compiler.h>
+ #include <linux/export.h>
+ #include <linux/string.h>
+@@ -52,6 +53,7 @@
+ 			struct list_head *a, struct list_head *b)
+ {
+ 	struct list_head *tail = head;
++	u8 count = 0;
+ 
+ 	for (;;) {
+ 		/* if equal, take 'a' -- important for sort stability */
+@@ -77,6 +79,15 @@
+ 	/* Finish linking remainder of list b on to tail */
+ 	tail->next = b;
+ 	do {
++		/*
++		 * If the merge is highly unbalanced (e.g. the input is
++		 * already sorted), this loop may run many iterations.
++		 * Continue callbacks to the client even though no
++		 * element comparison is needed, so the client's cmp()
++		 * routine can invoke cond_resched() periodically.
++		 */
++		if (unlikely(!++count))
++			cmp(priv, b, b);
+ 		b->prev = tail;
+ 		tail = b;
+ 		b = b->next;

tools/perf/check-headers.sh

@@ -136,6 +136,30 @@ beauty_check () {
   check_2 "tools/perf/trace/beauty/$file" "$file" "$@"
 }
 
+check_ignore_some_hunks () {
+  orig_file="$1"
+  tools_file="tools/$orig_file"
+  hunks_to_ignore="tools/perf/check-header_ignore_hunks/$orig_file"
+
+  if [ ! -f "$hunks_to_ignore" ]; then
+    echo "$hunks_to_ignore not found. Skipping $orig_file check."
+    FAILURES+=(
+      "$tools_file $orig_file"
+    )
+    return
+  fi
+
+  cmd="diff -u \"$tools_file\" \"$orig_file\" | grep -vf \"$hunks_to_ignore\" | wc -l | grep -qw 0"
+
+  if [ -f "$orig_file" ] && ! eval "$cmd"
+  then
+    FAILURES+=(
+      "$tools_file $orig_file"
+    )
+  fi
+}
+
+
 # Check if we have the kernel headers (tools/perf/../../include), else
 # we're probably on a detached tarball, so no point in trying to check
 # differences.
@@ -169,7 +193,6 @@ check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/build_bug.h       '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
 check include/linux/ctype.h	      '-I "isdigit("'
 check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
-check lib/list_sort.c		      '-I "^#include <linux/bug.h>"'
 
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl
@@ -187,6 +210,10 @@ done
 check_2 tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h
 check_2 tools/perf/util/hashmap.c tools/lib/bpf/hashmap.c
 
+# Files with larger differences
+
+check_ignore_some_hunks lib/list_sort.c
+
 cd tools/perf || exit
 
 if [ ${#FAILURES[@]} -gt 0 ]

tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h

@@ -18,8 +18,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... LOCAL_TIMER_VECTOR-1
- *  Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
+ *  Vectors 129 ... FIRST_SYSTEM_VECTOR-1 : device interrupts
+ *  Vectors FIRST_SYSTEM_VECTOR ... 255   : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
  *

tools/perf/trace/beauty/fs_at_flags.sh

@@ -13,9 +13,14 @@ printf "static const char *fs_at_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+AT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
 # AT_EACCESS is only meaningful to faccessat, so we will special case it there...
 # AT_STATX_SYNC_TYPE is not a bit, its a mask of AT_STATX_SYNC_AS_STAT, AT_STATX_FORCE_SYNC and AT_STATX_DONT_SYNC
+# AT_HANDLE_FID and AT_HANDLE_MNT_ID_UNIQUE are reusing values and are valid only for name_to_handle_at()
+# AT_RENAME_NOREPLACE reuses 0x1 and is valid only for renameat2()
 grep -E $regex ${linux_fcntl} | \
 	grep -v AT_EACCESS | \
 	grep -v AT_STATX_SYNC_TYPE | \
+	grep -v AT_HANDLE_FID | \
+	grep -v AT_HANDLE_MNT_ID_UNIQUE | \
+	grep -v AT_RENAME_NOREPLACE | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
 printf "};\n"

tools/perf/trace/beauty/include/linux/socket.h

@@ -327,6 +327,7 @@ struct ucred {
 					  * plain text and require encryption
 					  */
 
+#define MSG_SOCK_DEVMEM 0x2000000	/* Receive devmem skbs as cmsg */
 #define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
 #define MSG_SPLICE_PAGES 0x8000000	/* Splice the pages from the iterator in sendmsg() */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */

tools/perf/trace/beauty/include/uapi/linux/fcntl.h

@@ -16,6 +16,9 @@
 
 #define F_DUPFD_QUERY	(F_LINUX_SPECIFIC_BASE + 3)
 
+/* Was the file just created? */
+#define F_CREATED_QUERY	(F_LINUX_SPECIFIC_BASE + 4)
+
 /*
  * Cancel a blocking posix lock; internal use only until we expose an
  * asynchronous lock api to userspace:
@@ -87,37 +90,70 @@
 #define DN_ATTRIB	0x00000020	/* File changed attibutes */
 #define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
 
+#define AT_FDCWD		-100    /* Special value for dirfd used to
+					   indicate openat should use the
+					   current working directory. */
+
+
+/* Generic flags for the *at(2) family of syscalls. */
+
+/* Reserved for per-syscall flags	0xff. */
+#define AT_SYMLINK_NOFOLLOW		0x100   /* Do not follow symbolic
+						   links. */
+/* Reserved for per-syscall flags	0x200 */
+#define AT_SYMLINK_FOLLOW		0x400   /* Follow symbolic links. */
+#define AT_NO_AUTOMOUNT			0x800	/* Suppress terminal automount
+						   traversal. */
+#define AT_EMPTY_PATH			0x1000	/* Allow empty relative
+						   pathname to operate on dirfd
+						   directly. */
+/*
+ * These flags are currently statx(2)-specific, but they could be made generic
+ * in the future and so they should not be used for other per-syscall flags.
+ */
+#define AT_STATX_SYNC_TYPE		0x6000	/* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT		0x0000	/* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC		0x2000	/* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC		0x4000	/* - Don't sync attributes with the server */
+
+#define AT_RECURSIVE			0x8000	/* Apply to the entire subtree */
+
 /*
- * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
- * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
- * unlinkat.  The two functions do completely different things and therefore,
- * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
- * faccessat would be undefined behavior and thus treating it equivalent to
- * AT_EACCESS is valid undefined behavior.
+ * Per-syscall flags for the *at(2) family of syscalls.
+ *
+ * These are flags that are so syscall-specific that a user passing these flags
+ * to the wrong syscall is so "clearly wrong" that we can safely call such
+ * usage "undefined behaviour".
+ *
+ * For example, the constants AT_REMOVEDIR and AT_EACCESS have the same value.
+ * AT_EACCESS is meaningful only to faccessat, while AT_REMOVEDIR is meaningful
+ * only to unlinkat. The two functions do completely different things and
+ * therefore, the flags can be allowed to overlap. For example, passing
+ * AT_REMOVEDIR to faccessat would be undefined behavior and thus treating it
+ * equivalent to AT_EACCESS is valid undefined behavior.
+ *
+ * Note for implementers: When picking a new per-syscall AT_* flag, try to
+ * reuse already existing flags first. This leaves us with as many unused bits
+ * as possible, so we can use them for generic bits in the future if necessary.
  */
-#define AT_FDCWD		-100    /* Special value used to indicate
-                                           openat should use the current
-                                           working directory. */
-#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+
+/* Flags for renameat2(2) (must match legacy RENAME_* flags). */
+#define AT_RENAME_NOREPLACE	0x0001
+#define AT_RENAME_EXCHANGE	0x0002
+#define AT_RENAME_WHITEOUT	0x0004
+
+/* Flag for faccessat(2). */
 #define AT_EACCESS		0x200	/* Test access permitted for
                                            effective IDs, not real IDs.  */
+/* Flag for unlinkat(2). */
 #define AT_REMOVEDIR		0x200   /* Remove directory instead of
                                            unlinking file.  */
-#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
-#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
-#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
-
-#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
-#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
-#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
-#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
-
-#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
+/* Flags for name_to_handle_at(2). */
+#define AT_HANDLE_FID		0x200	/* File handle is needed to compare
+					   object identity and may not be
+					   usable with open_by_handle_at(2). */
+#define AT_HANDLE_MNT_ID_UNIQUE	0x001	/* Return the u64 unique mount ID. */
 
-/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
-#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
-					compare object identity and may not
-					be usable to open_by_handle_at(2) */
 #if defined(__KERNEL__)
 #define AT_GETATTR_NOSEC	0x80000000
 #endif

tools/perf/trace/beauty/include/uapi/linux/sched.h

@@ -118,6 +118,7 @@ struct clone_args {
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
 #define SCHED_DEADLINE		6
+#define SCHED_EXT		7
 
 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
 #define SCHED_RESET_ON_FORK     0x40000000

tools/perf/trace/beauty/include/uapi/sound/asound.h

@@ -869,7 +869,7 @@ struct snd_ump_block_info {
  *  Timer section - /dev/snd/timer
  */
 
-#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 7)
+#define SNDRV_TIMER_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 8)
 
 enum {
 	SNDRV_TIMER_CLASS_NONE = -1,
@@ -894,6 +894,7 @@ enum {
 #define SNDRV_TIMER_GLOBAL_RTC		1	/* unused */
 #define SNDRV_TIMER_GLOBAL_HPET		2
 #define SNDRV_TIMER_GLOBAL_HRTIMER	3
+#define SNDRV_TIMER_GLOBAL_UDRIVEN	4
 
 /* info flags */
 #define SNDRV_TIMER_FLG_SLAVE		(1<<0)	/* cannot be controlled */
@@ -974,6 +975,18 @@ struct snd_timer_status {
 };
 #endif
 
+/*
+ * This structure describes the userspace-driven timer. Such timers are purely virtual,
+ * and can only be triggered from software (for instance, by userspace application).
+ */
+struct snd_timer_uinfo {
+	/* To pretend being a normal timer, we need to know the resolution in ns. */
+	__u64 resolution;
+	int fd;
+	unsigned int id;
+	unsigned char reserved[16];
+};
+
 #define SNDRV_TIMER_IOCTL_PVERSION	_IOR('T', 0x00, int)
 #define SNDRV_TIMER_IOCTL_NEXT_DEVICE	_IOWR('T', 0x01, struct snd_timer_id)
 #define SNDRV_TIMER_IOCTL_TREAD_OLD	_IOW('T', 0x02, int)
@@ -990,6 +1003,8 @@ struct snd_timer_status {
 #define SNDRV_TIMER_IOCTL_CONTINUE	_IO('T', 0xa2)
 #define SNDRV_TIMER_IOCTL_PAUSE		_IO('T', 0xa3)
 #define SNDRV_TIMER_IOCTL_TREAD64	_IOW('T', 0xa4, int)
+#define SNDRV_TIMER_IOCTL_CREATE	_IOWR('T', 0xa5, struct snd_timer_uinfo)
+#define SNDRV_TIMER_IOCTL_TRIGGER	_IO('T', 0xa6)
 
 #if __BITS_PER_LONG == 64
 #define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD

tools/perf/trace/beauty/msg_flags.c

@@ -11,6 +11,9 @@
 #ifndef MSG_BATCH
 #define MSG_BATCH		   0x40000
 #endif
+#ifndef MSG_SOCK_DEVMEM
+#define MSG_SOCK_DEVMEM		 0x2000000
+#endif
 #ifndef MSG_ZEROCOPY
 #define MSG_ZEROCOPY		 0x4000000
 #endif
@@ -57,6 +60,7 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
 	P_MSG_FLAG(MORE);
 	P_MSG_FLAG(WAITFORONE);
 	P_MSG_FLAG(BATCH);
+	P_MSG_FLAG(SOCK_DEVMEM);
 	P_MSG_FLAG(ZEROCOPY);
 	P_MSG_FLAG(SPLICE_PAGES);
 	P_MSG_FLAG(FASTOPEN);

tools/perf/util/cs-etm.c

@@ -3323,7 +3323,7 @@ static int cs_etm__create_decoders(struct cs_etm_auxtrace *etm)
 		 * Don't create decoders for empty queues, mainly because
 		 * etmq->format is unknown for empty queues.
 		 */
-		assert(empty == (etmq->format == UNSET));
+		assert(empty || etmq->format != UNSET);
 		if (empty)
 			continue;
 

tools/perf/util/dwarf-aux.h

@@ -9,6 +9,7 @@
 #include <elfutils/libdw.h>
 #include <elfutils/libdwfl.h>
 #include <elfutils/version.h>
+#include <errno.h>
 
 struct strbuf;
 

tools/perf/util/symbol.c

@@ -1931,6 +1931,9 @@ int dso__load(struct dso *dso, struct map *map)
 		if (next_slot) {
 			ss_pos++;
 
+			if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND)
+				dso__set_binary_type(dso, symtab_type);
+
 			if (syms_ss && runtime_ss)
 				break;
 		} else {

tools/perf/util/vdso.c

@@ -308,8 +308,10 @@ static struct dso *machine__find_vdso(struct machine *machine,
 		if (!dso) {
 			dso = dsos__find(&machine->dsos, DSO__NAME_VDSO,
 					 true);
-			if (dso && dso_type != dso__type(dso, machine))
+			if (dso && dso_type != dso__type(dso, machine)) {
+				dso__put(dso);
 				dso = NULL;
+			}
 		}
 		break;
 	case DSO__TYPE_X32BIT: