From 5363c306787c88d41a41493f81b4308643696f6e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 26 Apr 2024 14:51:38 -0700 Subject: perf symbol: Set binary_type of dso when loading For the kernel dso, it sets the binary type of dso when loading the symbol table. But it seems not to do that for user DSOs. Actually it sets the symtab type only. It's not clear why we want to maintain the two separately but it uses the binary type info before getting the disassembly. Let's use the symtab type as binary type too if it's not set. I think it's ok to set the binary type when it founds a symsrc whether or not it has actual symbols. Signed-off-by: Namhyung Kim Tested-by: Alexander Monakov Link: https://lore.kernel.org/r/20240426215139.1271039-1-namhyung@kernel.org Cc: Ian Rogers Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Ingo Molnar Cc: Kan Liang Cc: LKML Cc: Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a18927d792af..3bbf173ad822 100644 --- a/tools/perf/util/symbol.c +++ b/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 { -- cgit v1.2.3-70-g09d2 From 424aafb61a0b98d7d242f447fdb84bb8b323e8a8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 12 Sep 2024 11:27:57 -0700 Subject: perf vdso: Missed put on 32-bit dsos If the dso type doesn't match then NULL is returned but the dso should be put first. Fixes: f649ed80f3cabbf1 ("perf dsos: Tidy reference counting and locking") Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240912182757.762369-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/vdso.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 1b6f8f6db7aa..c12f5d8c4bf6 100644 --- a/tools/perf/util/vdso.c +++ b/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: -- cgit v1.2.3-70-g09d2 From c850897b6cc275aea01c068732894b286bca44d1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 12:15:18 -0300 Subject: tools include UAPI: Sync sound/asound.h copy with the kernel sources Picking the changes from: 37745918e0e7575b ("ALSA: timer: Introduce virtual userspace-driven timers") Which entails no changes in the tooling side as it only introduces new SNDRV_TIMER_IOCTL_ ioctls, and the ones tracked by scripts in tools/perf/trace/beauty/ are only SNDRV_PCM_IOCTL_ and SNDRV_CTL_IOCTL_, we still need to support SNDRV_TIMER_IOCTL_ ones, but that probably will be one of the first for a BTF enumeration based approach :-) This silences this perf tools build warning: diff -u tools/perf/trace/beauty/include/uapi/sound/asound.h include/uapi/sound/asound.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Ivan Orlov Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Takashi Iwai Link: https://lore.kernel.org/lkml/ZvrB-g_E7g2ArlYW@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/uapi/sound/asound.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h index 8bf7e8a0eb6f..4cd513215bcd 100644 --- a/tools/perf/trace/beauty/include/uapi/sound/asound.h +++ b/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 -- cgit v1.2.3-70-g09d2 From 7ae76b32f9796449a5653c88847c6d784f38b7d3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 12:15:18 -0300 Subject: tools include UAPI: Sync linux/sched.h copy with the kernel sources Picking the changes from: f0e1a0643a59bf1f ("sched_ext: Implement BPF extensible scheduler class") The inclusion of the SCHED_EXT define doesn't cause any change in behaviour in tools/perf. This just silences this perf tools build warning: diff -u tools/perf/trace/beauty/include/uapi/sound/asound.h include/uapi/sound/asound.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Tejun Heo Link: https://lore.kernel.org/lkml/ZvrDShNVXotZpiwk@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/uapi/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf') diff --git a/tools/perf/trace/beauty/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h index 3bac0a8ceab2..359a14cc76a4 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/sched.h +++ b/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 -- cgit v1.2.3-70-g09d2 From 58f969b7a83e3680f1de5f1f0d382d783cc15f6c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 12:15:18 -0300 Subject: tools include UAPI: Sync linux/fcntl.h copy with the kernel sources Picking the changes from: 4356d575ef0f39a3 ("fhandle: expose u64 mount id to name_to_handle_at(2)") b4fef22c2fb97fa2 ("uapi: explain how per-syscall AT_* flags should be allocated") 820a185896b77814 ("fcntl: add F_CREATED_QUERY") It just moves AT_REMOVEDIR around, and adds a bunch more AT_ for renameat2() and name_to_handle_at(). We need to improve this situation, as not all AT_ defines are applicable to all fs flags... This adds support for those new AT_ defines, addressing this build warning: diff -u tools/perf/trace/beauty/include/uapi/sound/asound.h include/uapi/sound/asound.h Reviewed-by: Aleksa Sarai Cc: Adrian Hunter Cc: Christian Brauner Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Tejun Heo Link: https://lore.kernel.org/lkml/ZvrIKL3cREoRHIQd@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/fs_at_flags.sh | 5 ++ tools/perf/trace/beauty/include/uapi/linux/fcntl.h | 84 +++++++++++++++------- 2 files changed, 65 insertions(+), 24 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh index 456f59addf74..e3f13f96a27c 100755 --- a/tools/perf/trace/beauty/fs_at_flags.sh +++ b/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" diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index c0bcc185fa48..87e2dec79fea 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/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 -- cgit v1.2.3-70-g09d2 From c94cd9508b1335b949fd13ebd269313c65492df0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 12:54:57 -0300 Subject: perf trace beauty: Update the arch/x86/include/asm/irq_vectors.h copy with the kernel sources To pick up the change in: a1fab3e69d9d0e9b ("x86/irq: Fix comment on IRQ vector layout") That just adds some comments, so no changes in perf tooling, just silences this build warning: diff -u tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h arch/x86/include/asm/irq_vectors.h Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Cc: Sohil Mehta Cc: Thomas Gleixner Link: https://lore.kernel.org/lkml/ZvrKT7oQc1AOv6Vk@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h index 13aea8fc3d45..47051871b436 100644 --- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h +++ b/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. * -- cgit v1.2.3-70-g09d2 From d1648688799dd14075c43e2d091be815c794f331 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 13:14:30 -0300 Subject: perf beauty: Update copy of linux/socket.h with the kernel sources To pick the changes in: 8f0b3cc9a4c102c2 ("tcp: RX path for devmem TCP") That don't result in any changes in the tables generated from that header. But while updating I noticed we need to support the new MSG_SOCK_DEVMEM flag in the hard coded table for the msg flags table, add it. This silences this perf build warning: Warning: Kernel ABI header differences: diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h Please see tools/include/uapi/README for details. Cc: Adrian Hunter Cc: Ian Rogers Cc: Jakub Kicinski Cc: Jiri Olsa Cc: Kan Liang Cc: Mina Almasry Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZvrO_eT9e_41xrNv@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/include/linux/socket.h | 1 + tools/perf/trace/beauty/msg_flags.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index df9cdb8bbfb8..d18cc47e89bd 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/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 */ diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c index ed3ff969b546..2da581ff0c80 100644 --- a/tools/perf/trace/beauty/msg_flags.c +++ b/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); -- cgit v1.2.3-70-g09d2 From cd46ea5ab48667e9522608533b9a24e3028fa368 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 17:07:28 -0300 Subject: tools check_headers.sh: Add check variant that excludes some hunks With 6d74e1e371d43a7b ("tools/lib/list_sort: remove redundant code for cond_resched handling") we end up with a multi-line variation in the merge_final() implementation, one that the simple line based exceptions we had so far can't cope. Thus this check has been failing: Warning: Kernel ABI header differences: diff -u tools/lib/list_sort.c lib/list_sort.c So add a new check routine that uses grep -vf to exclude some hunks that we store in the tools/perf/check-header_ignore_hunks/ directory. This first patch is just the new check routine, the next one will use it to check lib/list_sort.c. Acked-by: Kuan-Wei Chiu Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Andrew Morton Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Link: https://lore.kernel.org/lkml/20240930202136.16904-2-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/check-headers.sh | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 714c78e5da07..55aba47e5aec 100755 --- a/tools/perf/check-headers.sh +++ b/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. -- cgit v1.2.3-70-g09d2 From 36110669ddf832e6c9ceba4dd203749d5be31d31 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 30 Sep 2024 17:13:48 -0300 Subject: perf tools: Cope with differences for lib/list_sort.c copy from the kernel With 6d74e1e371d43a7b ("tools/lib/list_sort: remove redundant code for cond_resched handling") we need to use the newly added hunk based exceptions when comparing the copy we carry in tools/lib/ to the original file, do it by adding the hunks that we know will be the expected diff. If at some point the original file is updated in other parts, then we should flag and check the file for update. Acked-by: Kuan-Wei Chiu Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Andrew Morton Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Link: https://lore.kernel.org/lkml/20240930202136.16904-3-acme@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/check-header_ignore_hunks/lib/list_sort.c | 31 ++++++++++++++++++++++ tools/perf/check-headers.sh | 5 +++- 2 files changed, 35 insertions(+), 1 deletion(-) create mode 100644 tools/perf/check-header_ignore_hunks/lib/list_sort.c (limited to 'tools/perf') diff --git a/tools/perf/check-header_ignore_hunks/lib/list_sort.c b/tools/perf/check-header_ignore_hunks/lib/list_sort.c new file mode 100644 index 000000000000..32d98cb34f80 --- /dev/null +++ b/tools/perf/check-header_ignore_hunks/lib/list_sort.c @@ -0,0 +1,31 @@ +@@ -1,5 +1,6 @@ + // SPDX-License-Identifier: GPL-2.0 + #include ++#include + #include + #include + #include +@@ -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; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 55aba47e5aec..f1080d409666 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -193,7 +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 " -B' -check lib/list_sort.c '-I "^#include "' # diff non-symmetric files check_2 tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl @@ -211,6 +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 ] -- cgit v1.2.3-70-g09d2 From 008979cc6911987152eb7485943c85b9c92c1e9b Mon Sep 17 00:00:00 2001 From: James Clark Date: Tue, 1 Oct 2024 13:36:25 +0100 Subject: perf dwarf-aux: Fix build with !HAVE_DWARF_GETLOCATIONS_SUPPORT The linked fixes commit added an #include "dwarf-aux.h" to disasm.h which gets picked up in a lot of places. Without HAVE_DWARF_GETLOCATIONS_SUPPORT the stubs return an errno, so include errno.h to fix the following build error: In file included from util/disasm.h:8, from util/annotate.h:16, from builtin-top.c:23: util/dwarf-aux.h: In function 'die_get_var_range': util/dwarf-aux.h:183:10: error: 'ENOTSUP' undeclared (first use in this function) 183 | return -ENOTSUP; | ^~~~~~~ Fixes: 782959ac248ac3cb ("perf annotate: Add "update_insn_state" callback function to handle arch specific instruction tracking") Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20241001123625.1063153-1-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/dwarf-aux.h | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf') diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 336a3a183a78..bd7505812569 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -9,6 +9,7 @@ #include #include #include +#include struct strbuf; -- cgit v1.2.3-70-g09d2 From 43f6564f18bf5b27e1675ef6f4baf68e786396b2 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Thu, 19 Sep 2024 09:35:11 +0800 Subject: perf build: Fix static compilation error when libdw is not installed If libdw is not installed in build environment, the output of 'pkg-config --modversion libdw' is empty, causing LIBDW_VERSION_2 to be empty and the shell test will have the following error: /bin/sh: 1: test: -lt: unexpected operator Before: $ pkg-config --modversion libdw Package libdw was not found in the pkg-config search path. Perhaps you should add the directory containing `libdw.pc' to the PKG_CONFIG_PATH environment variable No package 'libdw' found $ make LDFLAGS=-static -j16 BUILD: Doing 'make -j20' parallel build Package libdw was not found in the pkg-config search path. Perhaps you should add the directory containing `libdw.pc' to the PKG_CONFIG_PATH environment variable No package 'libdw' found /bin/sh: 1: test: -lt: unexpected operator After: 1. libdw is not installed: $ pkg-config --modversion libdw Package libdw was not found in the pkg-config search path. Perhaps you should add the directory containing `libdw.pc' to the PKG_CONFIG_PATH environment variable No package 'libdw' found $ make LDFLAGS=-static -j16 BUILD: Doing 'make -j20' parallel build Package libdw was not found in the pkg-config search path. Perhaps you should add the directory containing `libdw.pc' to the PKG_CONFIG_PATH environment variable No package 'libdw' found Makefile.config:473: No libdw DWARF unwind found, Please install elfutils-devel/libdw-dev >= 0.158 and/or set LIBDW_DIR 2. libdw version is lower than 0.177 $ pkg-config --modversion libdw 0.176 $ make LDFLAGS=-static -j16 BUILD: Doing 'make -j20' parallel build Auto-detecting system features: ... dwarf: [ on ] INSTALL libsubcmd_headers INSTALL libapi_headers INSTALL libperf_headers INSTALL libsymbol_headers INSTALL libbpf_headers LINK perf 3. libdw version is higher than 0.177 $ pkg-config --modversion libdw 0.186 $ make LDFLAGS=-static -j16 BUILD: Doing 'make -j20' parallel build Auto-detecting system features: ... dwarf: [ on ] CC util/bpf-utils.o CC util/pfm.o LD util/perf-util-in.o LD perf-util-in.o AR libperf-util.a LINK perf Fixes: 536661da6ea18fe6 ("perf: build: Only link libebl.a for old libdw") Reviewed-by: Leo Yan Signed-off-by: Yang Jihong Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240919013513.118527-2-yangjihong@bytedance.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/feature/Makefile | 2 +- tools/perf/Makefile.config | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 5938cf799dc6..6f1c961f0ede 100644 --- a/tools/build/feature/Makefile +++ b/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))) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4dcf7a0fd235..0049fd41cf57 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -149,7 +149,7 @@ DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) DWARFLIBS += -lelf -ldl -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))) -- cgit v1.2.3-70-g09d2 From a530337ba9ef601c93ec378fd941be43f587d563 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Thu, 19 Sep 2024 09:35:12 +0800 Subject: perf build: Fix build feature-dwarf_getlocations fail for old libdw For libdw versions below 0.177, need to link libdl.a in addition to libbebl.a during static compilation, otherwise feature-dwarf_getlocations compilation will fail. Before: $ make LDFLAGS=-static BUILD: Doing 'make -j20' parallel build Makefile.config:483: Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157 $ cat ../build/feature/test-dwarf_getlocations.make.output /usr/bin/ld: /usr/lib/gcc/x86_64-linux-gnu/9/../../../x86_64-linux-gnu/libebl.a(eblclosebackend.o): in function `ebl_closebackend': (.text+0x20): undefined reference to `dlclose' collect2: error: ld returned 1 exit status After: $ make LDFLAGS=-static Auto-detecting system features: ... dwarf: [ on ] $ ./perf probe Usage: perf probe [] 'PROBEDEF' ['PROBEDEF' ...] or: perf probe [] --add 'PROBEDEF' [--add 'PROBEDEF' ...] or: perf probe [] --del '[GROUP:]EVENT' ... or: perf probe --list [GROUP:]EVENT ... Fixes: 536661da6ea18fe6 ("perf: build: Only link libebl.a for old libdw") Reviewed-by: Leo Yan Signed-off-by: Yang Jihong Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240919013513.118527-3-yangjihong@bytedance.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/feature/Makefile | 3 +++ tools/perf/Makefile.config | 5 ++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 6f1c961f0ede..1658596188bf 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -181,6 +181,9 @@ ifeq ($(findstring -static,${LDFLAGS}),-static) ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) DWARFLIBS += -lebl endif + + # Must put -ldl after -lebl for dependency + DWARFLIBS += -ldl endif $(OUTPUT)test-dwarf.bin: diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0049fd41cf57..4ddb27a48eed 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -147,7 +147,7 @@ ifdef LIBDW_DIR endif DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -ldl -lz -llzma -lbz2 -lzstd + DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0 LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) @@ -158,6 +158,9 @@ ifeq ($(findstring -static,${LDFLAGS}),-static) ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),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) -- cgit v1.2.3-70-g09d2 From e934a35e3cc1fe0bfb1bc771e64f3ba6e70c40e2 Mon Sep 17 00:00:00 2001 From: Ilkka Koskinen Date: Tue, 24 Sep 2024 16:39:30 -0700 Subject: perf cs-etm: Fix the assert() to handle captured and unprocessed cpu trace If one builds perf with DEBUG=1, captures data on multiple CPUs and finally runs 'perf report -C ' for only one of the cpus, assert() aborts the program. This happens because there are empty queues with format set. This patch changes the condition to abort only if a queue is not empty and if the format is unset. $ make -C tools/perf DEBUG=1 CORESIGHT=1 CSLIBS=/usr/lib CSINCLUDES=/usr/include install $ perf record -o kcore --kcore -e cs_etm/timestamp/k -s -C 0-1 dd if=/dev/zero of=/dev/null bs=1M count=1 $ perf report --input kcore/data --vmlinux=/home/ikoskine/projects/linux/vmlinux -C 1 Aborted (core dumped) Fixes: 57880a7966be510c ("perf: cs-etm: Allocate queues for all CPUs") Reviewed-by: James Clark Signed-off-by: Ilkka Koskinen Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Link: https://lore.kernel.org/r/20240924233930.5193-1-ilkka@os.amperecomputing.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 90f32f327b9b..40f047baef81 100644 --- a/tools/perf/util/cs-etm.c +++ b/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; -- cgit v1.2.3-70-g09d2 From 39c6a356201ebbd7e1db5be53fbb46ef4bfc70a4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 11 Oct 2024 16:10:01 -0300 Subject: perf trace: The return from 'write' isn't a pid When adding a explicit beautifier for the 'write' syscall when the BPF based buffer collector was introduced there was a cut'n'paste error that carried the syscall_fmt->errpid setting from a nearby syscall (waitid) that returns a pid. So the write return was being suppressed by the return pretty printer, remove that field, reverting it back to the default return handler, that prints positive numbers as-is and interpret negative values as errnos. I actually introduced the problem while making Howard's original patch work just with the 'write' syscall, as we couldn't just look for any buffers, the ones that are filled in by the kernel couldn't use the same sys_enter BPF collector. Fixes: b257fac12f38d7f5 ("perf trace: Pretty print buffer data") Reported-by: James Clark Link: https://lore.kernel.org/lkml/bcf50648-3c7e-4513-8717-0d14492c53b9@linaro.org Link: https://lore.kernel.org/all/Zt8jTfzDYgBPvFCd@x1/#t Cc: Adrian Hunter Cc: Alan Maguire Cc: Howard Chu Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f6e847529073..d3f11b90d025 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1399,7 +1399,7 @@ static const struct syscall_fmt syscall_fmts[] = { .arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, { .name = "waitid", .errpid = true, .arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, - { .name = "write", .errpid = true, + { .name = "write", .arg = { [1] = { .scnprintf = SCA_BUF /* buf */, .from_user = true, }, }, }, }; -- cgit v1.2.3-70-g09d2 From ecabac70ff919580324b407818ee3e6c0004dcf8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 15 Oct 2024 17:03:37 -0300 Subject: perf trace augmented_raw_syscalls: Add extra array index bounds checking to satisfy some BPF verifiers In a RHEL8 kernel (4.18.0-513.11.1.el8_9.x86_64), that, as enterprise kernels go, have backports from modern kernels, the verifier complains about lack of bounds check for the index into the array of syscall arguments, on a BPF bytecode generated by clang 17, with: ; } else if (size < 0 && size >= -6) { /* buffer */ 116: (b7) r1 = -6 117: (2d) if r1 > r6 goto pc-30 R0=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=inv-6 R2=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3=inv(id=0) R5=inv40 R6=inv(id=0,umin_value=18446744073709551610,var_off=(0xffffffff00000000; 0xffffffff)) R7=map_value(id=0,off=56,ks=4,vs=8272,imm=0) R8=invP6 R9=map_value(id=0,off=20,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16=map_value fp-24=map_value fp-32=inv40 fp-40=ctx fp-48=map_value fp-56=inv1 fp-64=map_value fp-72=map_value fp-80=map_value ; index = -(size + 1); 118: (a7) r6 ^= -1 119: (67) r6 <<= 32 120: (77) r6 >>= 32 ; aug_size = args->args[index]; 121: (67) r6 <<= 3 122: (79) r1 = *(u64 *)(r10 -24) 123: (0f) r1 += r6 last_idx 123 first_idx 116 regs=40 stack=0 before 122: (79) r1 = *(u64 *)(r10 -24) regs=40 stack=0 before 121: (67) r6 <<= 3 regs=40 stack=0 before 120: (77) r6 >>= 32 regs=40 stack=0 before 119: (67) r6 <<= 32 regs=40 stack=0 before 118: (a7) r6 ^= -1 regs=40 stack=0 before 117: (2d) if r1 > r6 goto pc-30 regs=42 stack=0 before 116: (b7) r1 = -6 R0_w=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=inv1 R2_w=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3_w=inv(id=0) R5_w=inv40 R6_rw=invP(id=0,smin_value=-2147483648,smax_value=0) R7_w=map_value(id=0,off=56,ks=4,vs=8272,imm=0) R8_w=invP6 R9_w=map_value(id=0,off=20,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16_w=map_value fp-24_r=map_value fp-32_w=inv40 fp-40=ctx fp-48=map_value fp-56_w=inv1 fp-64_w=map_value fp-72=map_value fp-80=map_value parent didn't have regs=40 stack=0 marks last_idx 110 first_idx 98 regs=40 stack=0 before 110: (6d) if r1 s> r6 goto pc+5 regs=42 stack=0 before 109: (b7) r1 = 1 regs=40 stack=0 before 108: (65) if r6 s> 0x1000 goto pc+7 regs=40 stack=0 before 98: (55) if r6 != 0x1 goto pc+9 R0_w=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=invP12 R2_w=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3_rw=inv(id=0) R5_w=inv24 R6_rw=invP(id=0,smin_value=-2147483648,smax_value=2147483647) R7_w=map_value(id=0,off=40,ks=4,vs=8272,imm=0) R8_rw=invP4 R9_w=map_value(id=0,off=12,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16_rw=map_value fp-24_r=map_value fp-32_rw=invP24 fp-40_r=ctx fp-48_r=map_value fp-56_w=invP1 fp-64_rw=map_value fp-72_r=map_value fp-80_r=map_value parent already had regs=40 stack=0 marks 124: (79) r6 = *(u64 *)(r1 +16) R0=map_value(id=0,off=0,ks=4,vs=24688,imm=0) R1_w=map_value(id=0,off=0,ks=4,vs=8272,umax_value=34359738360,var_off=(0x0; 0x7fffffff8),s32_max_value=2147483640,u32_max_value=-8) R2=map_value(id=0,off=16,ks=4,vs=8272,imm=0) R3=inv(id=0) R5=inv40 R6_w=invP(id=0,umax_value=34359738360,var_off=(0x0; 0x7fffffff8),s32_max_value=2147483640,u32_max_value=-8) R7=map_value(id=0,off=56,ks=4,vs=8272,imm=0) R8=invP6 R9=map_value(id=0,off=20,ks=4,vs=24,imm=0) R10=fp0 fp-8=mmmmmmmm fp-16=map_value fp-24=map_value fp-32=inv40 fp-40=ctx fp-48=map_value fp-56=inv1 fp-64=map_value fp-72=map_value fp-80=map_value R1 unbounded memory access, make sure to bounds check any such access processed 466 insns (limit 1000000) max_states_per_insn 2 total_states 20 peak_states 20 mark_read 3 If we add this line, as used in other BPF programs, to cap that index: index &= 7; The generated BPF program is considered safe by that version of the BPF verifier, allowing perf to collect the syscall args in one more kernel using the BPF based pointer contents collector. With the above one-liner it works with that kernel: [root@dell-per740-01 ~]# uname -a Linux dell-per740-01.khw.eng.rdu2.dc.redhat.com 4.18.0-513.11.1.el8_9.x86_64 #1 SMP Thu Dec 7 03:06:13 EST 2023 x86_64 x86_64 x86_64 GNU/Linux [root@dell-per740-01 ~]# ~acme/bin/perf trace -e *sleep* sleep 1.234567890 0.000 (1234.704 ms): sleep/3863610 nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 234567890 }) = 0 [root@dell-per740-01 ~]# As well as with the one in Fedora 40: root@number:~# uname -a Linux number 6.11.3-200.fc40.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Oct 10 22:31:19 UTC 2024 x86_64 GNU/Linux root@number:~# perf trace -e *sleep* sleep 1.234567890 0.000 (1234.722 ms): sleep/14873 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 234567890 }, rmtp: 0x7ffe87311a40) = 0 root@number:~# Song Liu reported that this one-liner was being optimized out by clang 18, so I suggested and he tested that adding a compiler barrier before it made clang v18 to keep it and the verifier in the kernel in Song's case (Meta's 5.12 based kernel) also was happy with the resulting bytecode. I'll investigate using virtme-ng[1] to have all the perf BPF based functionality thoroughly tested over multiple kernels and clang versions. [1] https://kernel-recipes.org/en/2024/virtme-ng/ Cc: Adrian Hunter Cc: Alan Maguire Cc: Alexander Shishkin Cc: Andrea Righi Cc: Howard Chu Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Link: https://lore.kernel.org/lkml/Zw7JgJc0LOwSpuvx@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index b2f17cca014b..31df5f0cb14b 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -477,6 +477,8 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) augmented = true; } else if (size < 0 && size >= -6) { /* buffer */ index = -(size + 1); + barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. + index &= 7; // Satisfy the bounds checking with the verifier in some kernels. aug_size = args->args[index]; if (aug_size > TRACE_AUG_MAX_BUF) -- cgit v1.2.3-70-g09d2 From 395d38419f1853decab84acc16176b3fa5c96690 Mon Sep 17 00:00:00 2001 From: Howard Chu Date: Thu, 10 Oct 2024 19:14:02 -0700 Subject: perf trace augmented_raw_syscalls: Add more checks to pass the verifier Add some more checks to pass the verifier in more kernels. Signed-off-by: Howard Chu Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alan Maguire Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20241011021403.4089793-3-howardchu95@gmail.com [ Reduced the patch removing things that can be done later ] Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/util/bpf_skel/augmented_raw_syscalls.bpf.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 31df5f0cb14b..4a62ed593e84 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -288,6 +288,10 @@ int sys_enter_rename(struct syscall_enter_args *args) augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64)); len += augmented_args->arg.size; + /* Every read from userspace is limited to value size */ + if (augmented_args->arg.size > sizeof(augmented_args->arg.value)) + return 1; /* Failure: don't filter */ + struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size; newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value)); @@ -315,6 +319,10 @@ int sys_enter_renameat2(struct syscall_enter_args *args) augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64)); len += augmented_args->arg.size; + /* Every read from userspace is limited to value size */ + if (augmented_args->arg.size > sizeof(augmented_args->arg.value)) + return 1; /* Failure: don't filter */ + struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size; newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value)); @@ -423,8 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, output = 0, + int zero = 0, size, aug_size, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -490,10 +499,17 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } } + /* Augmented data size is limited to sizeof(augmented_arg->unnamed union with value field) */ + if (aug_size > value_size) + aug_size = value_size; + /* write data to payload */ if (augmented) { int written = offsetof(struct augmented_arg, value) + aug_size; + if (written < 0 || written > sizeof(struct augmented_arg)) + return 1; + ((struct augmented_arg *)payload_offset)->size = aug_size; output += written; payload_offset += written; @@ -501,7 +517,7 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } } - if (!do_output) + if (!do_output || (sizeof(struct syscall_enter_args) + output) > sizeof(struct beauty_payload_enter)) return 1; return augmented__beauty_output(ctx, payload, sizeof(struct syscall_enter_args) + output); -- cgit v1.2.3-70-g09d2 From 7fbff3c0e085745b99f220ad56fcee3ea9643d87 Mon Sep 17 00:00:00 2001 From: Howard Chu Date: Thu, 10 Oct 2024 19:14:01 -0700 Subject: perf build: Change the clang check back to 12.0.1 This serves as a revert for this patch: https://lore.kernel.org/linux-perf-users/ZuGL9ROeTV2uXoSp@x1/ Signed-off-by: Howard Chu Tested-by: James Clark Cc: Adrian Hunter Cc: Alan Maguire Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20241011021403.4089793-2-howardchu95@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4ddb27a48eed..d4332675babb 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -704,8 +704,8 @@ ifeq ($(BUILD_BPF_SKEL),1) BUILD_BPF_SKEL := 0 else CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g') - ifeq ($(call version-lt3,$(CLANG_VERSION),16.0.6),1) - $(warning Warning: Disabled BPF skeletons as at least $(CLANG) version 16.0.6 is reported to be a working setup with the current of BPF based perf features) + ifeq ($(call version-lt3,$(CLANG_VERSION),12.0.1),1) + $(warning Warning: Disabled BPF skeletons as reliable BTF generation needs at least $(CLANG) version 12.0.1) BUILD_BPF_SKEL := 0 endif endif -- cgit v1.2.3-70-g09d2 From 5d35634ecc2d2c3938bd7dc23df0ad046da1b303 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 22 Oct 2024 17:22:36 -0300 Subject: perf trace: Fix non-listed archs in the syscalltbl routines This fixes a build breakage on 32-bit arm, where the syscalltbl__id_at_idx() function was missing. Committer notes: Generating a proper syscall table from a copy of arch/arm/tools/syscall.tbl ends up being too big a patch for this rc stage, I started doing it but while testing noticed some other problems with using BPF to collect pointer args on arm7 (32-bit) will maybe continue trying to make it work on the next cycle... Fixes: 7a2fb5619cc1fb53 ("perf trace: Fix iteration of syscall ids in syscalltbl->entries") Suggested-by: Howard Chu Signed-off-by: Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Howard Chu Cc: Ian Rogers Cc: Jiri Olsa Link: https://lore.kernel.org/lkml/3a592835-a14f-40be-8961-c0cee7720a94@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/syscalltbl.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 7c15dec6900d..6c45ded922b6 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -46,6 +46,11 @@ static const char *const *syscalltbl_native = syscalltbl_mips_n64; #include const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; static const char *const *syscalltbl_native = syscalltbl_loongarch; +#else +const int syscalltbl_native_max_id = 0; +static const char *const syscalltbl_native[] = { + [0] = "unknown", +}; #endif struct syscall { @@ -182,6 +187,11 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) return audit_name_to_syscall(name, tbl->audit_machine); } +int syscalltbl__id_at_idx(struct syscalltbl *tbl __maybe_unused, int idx) +{ + return idx; +} + int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, const char *syscall_glob __maybe_unused, int *idx __maybe_unused) { -- cgit v1.2.3-70-g09d2 From 06a130e42a5bfc84795464bff023bff4c16f58c5 Mon Sep 17 00:00:00 2001 From: Veronika Molnarova Date: Thu, 17 Oct 2024 18:15:55 +0200 Subject: perf test: Handle perftool-testsuite_probe failure due to broken DWARF Test case test_adding_blacklisted ends in failure if the blacklisted probe is of an assembler function with no DWARF available. At the same time, probing the blacklisted function with ASM DWARF doesn't test the blacklist itself as the failure is a result of the broken DWARF. When the broken DWARF output is encountered, check if the probed function was compiled by the assembler. If so, the broken DWARF message is expected and does not report a perf issue, else report a failure. If the ASM DWARF affected the probe, try the next probe on the blacklist. If the first 5 probes are defective due to broken DWARF, skip the test case. Fixes: def5480d63c1e847 ("perf testsuite probe: Add test for blacklisted kprobes handling") Signed-off-by: Veronika Molnarova Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Veronika Molnarova Link: https://lore.kernel.org/r/20241017161555.236769-1-vmolnaro@redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- .../shell/base_probe/test_adding_blacklisted.sh | 69 +++++++++++++++++----- 1 file changed, 54 insertions(+), 15 deletions(-) (limited to 'tools/perf') diff --git a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh index b5dc10b2a738..bead723e34af 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh @@ -19,35 +19,74 @@ TEST_RESULT=0 # skip if not supported -BLACKFUNC=`head -n 1 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` -if [ -z "$BLACKFUNC" ]; then +BLACKFUNC_LIST=`head -n 5 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` +if [ -z "$BLACKFUNC_LIST" ]; then print_overall_skipped exit 0 fi +# try to find vmlinux with DWARF debug info +VMLINUX_FILE=$(perf probe -v random_probe |& grep "Using.*for symbols" | sed -r 's/^Using (.*) for symbols$/\1/') + # remove all previously added probes clear_all_probes ### adding blacklisted function - -# functions from blacklist should be skipped by perf probe -! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err -PERF_EXIT_CODE=$? - REGEX_SCOPE_FAIL="Failed to find scope of probe point" REGEX_SKIP_MESSAGE=" is blacklisted function, skip it\." -REGEX_NOT_FOUND_MESSAGE="Probe point \'$BLACKFUNC\' not found." +REGEX_NOT_FOUND_MESSAGE="Probe point \'$RE_EVENT\' not found." REGEX_ERROR_MESSAGE="Error: Failed to add events." REGEX_INVALID_ARGUMENT="Failed to write event: Invalid argument" REGEX_SYMBOL_FAIL="Failed to find symbol at $RE_ADDRESS" -REGEX_OUT_SECTION="$BLACKFUNC is out of \.\w+, skip it" -../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err -CHECK_EXIT_CODE=$? - -print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC" -(( TEST_RESULT += $? )) - +REGEX_OUT_SECTION="$RE_EVENT is out of \.\w+, skip it" +REGEX_MISSING_DECL_LINE="A function DIE doesn't have decl_line. Maybe broken DWARF?" + +BLACKFUNC="" +SKIP_DWARF=0 + +for BLACKFUNC in $BLACKFUNC_LIST; do + echo "Probing $BLACKFUNC" + + # functions from blacklist should be skipped by perf probe + ! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err + PERF_EXIT_CODE=$? + + # check for bad DWARF polluting the result + ../common/check_all_patterns_found.pl "$REGEX_MISSING_DECL_LINE" >/dev/null < $LOGS_DIR/adding_blacklisted.err + + if [ $? -eq 0 ]; then + SKIP_DWARF=1 + echo "Result polluted by broken DWARF, trying another probe" + + # confirm that the broken DWARF comes from assembler + if [ -n "$VMLINUX_FILE" ]; then + readelf -wi "$VMLINUX_FILE" | + awk -v probe="$BLACKFUNC" '/DW_AT_language/ { comp_lang = $0 } + $0 ~ probe { if (comp_lang) { print comp_lang }; exit }' | + grep -q "MIPS assembler" + + CHECK_EXIT_CODE=$? + if [ $CHECK_EXIT_CODE -ne 0 ]; then + SKIP_DWARF=0 # broken DWARF while available + break + fi + fi + else + ../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err + CHECK_EXIT_CODE=$? + + SKIP_DWARF=0 + break + fi +done + +if [ $SKIP_DWARF -eq 1 ]; then + print_testcase_skipped "adding blacklisted function $BLACKFUNC" +else + print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC" + (( TEST_RESULT += $? )) +fi ### listing not-added probe -- cgit v1.2.3-70-g09d2 From 758f18158952a6287ac23679ec04c32d44ca5368 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 23 Oct 2024 16:12:57 -0300 Subject: perf python: Fix up the build on architectures without HAVE_KVM_STAT_SUPPORT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while building on a raspbian arm 32-bit system. There was also this other case, fixed by adding a missing util/stat.h with the prototypes: /tmp/tmp.MbiSHoF3dj/perf-6.12.0-rc3/tools/perf/util/python.c:1396:6: error: no previous prototype for ‘perf_stat__set_no_csv_summary’ [-Werror=missing-prototypes] 1396 | void perf_stat__set_no_csv_summary(int set __maybe_unused) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /tmp/tmp.MbiSHoF3dj/perf-6.12.0-rc3/tools/perf/util/python.c:1400:6: error: no previous prototype for ‘perf_stat__set_big_num’ [-Werror=missing-prototypes] 1400 | void perf_stat__set_big_num(int set __maybe_unused) | ^~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors In other architectures this must be building due to some lucky indirect inclusion of that header. Fixes: 9dabf4003423c8d3 ("perf python: Switch module to linking libraries from building source") Reviewed-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZxllAtpmEw5fg9oy@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/python.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 31a223eaf8e6..ee3d43a7ba45 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -19,6 +19,7 @@ #include "util/bpf-filter.h" #include "util/env.h" #include "util/kvm-stat.h" +#include "util/stat.h" #include "util/kwork.h" #include "util/sample.h" #include "util/lock-contention.h" @@ -1355,6 +1356,7 @@ error: unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; +#ifdef HAVE_KVM_STAT_SUPPORT bool kvm_entry_event(struct evsel *evsel __maybe_unused) { return false; @@ -1384,6 +1386,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, char *decode __maybe_unused) { } +#endif // HAVE_KVM_STAT_SUPPORT int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused, int num __maybe_unused, int pathlen __maybe_unused) -- cgit v1.2.3-70-g09d2 From 55f1b540d893da740a81200450014c45a8103f54 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 28 Oct 2024 12:24:37 -0300 Subject: tools headers: Update the linux/unaligned.h copy with the kernel sources To pick up the changes in: 7f053812dab3946c ("random: vDSO: minimize and simplify header includes") That required adding a copy of include/vdso/unaligned.h and its checking in tools/perf/check-headers.h. Addressing this perf tools build warning: Warning: Kernel ABI header differences: diff -u tools/include/linux/unaligned.h include/linux/unaligned.h Please see tools/include/uapi/README for further details. Cc: Adrian Hunter Cc: Christophe Leroy Cc: Ian Rogers Cc: Jason A. Donenfeld Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/Zx-uHvAbPAESofEN@x1 Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/unaligned.h | 11 +---------- tools/include/vdso/unaligned.h | 15 +++++++++++++++ tools/perf/check-headers.sh | 1 + 3 files changed, 17 insertions(+), 10 deletions(-) create mode 100644 tools/include/vdso/unaligned.h (limited to 'tools/perf') diff --git a/tools/include/linux/unaligned.h b/tools/include/linux/unaligned.h index bc0633bc4650..395a4464fe73 100644 --- a/tools/include/linux/unaligned.h +++ b/tools/include/linux/unaligned.h @@ -9,16 +9,7 @@ #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wpacked" #pragma GCC diagnostic ignored "-Wattributes" - -#define __get_unaligned_t(type, ptr) ({ \ - const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ - __pptr->x; \ -}) - -#define __put_unaligned_t(type, val, ptr) do { \ - struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ - __pptr->x = (val); \ -} while (0) +#include #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h new file mode 100644 index 000000000000..eee3d2a4dbe4 --- /dev/null +++ b/tools/include/vdso/unaligned.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_UNALIGNED_H +#define __VDSO_UNALIGNED_H + +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define __put_unaligned_t(type, val, ptr) do { \ + struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x = (val); \ +} while (0) + +#endif /* __VDSO_UNALIGNED_H */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 29adbb423327..a05c1c105c51 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -22,6 +22,7 @@ FILES=( "include/vdso/bits.h" "include/linux/const.h" "include/vdso/const.h" + "include/vdso/unaligned.h" "include/linux/hash.h" "include/linux/list-sort.h" "include/uapi/linux/hw_breakpoint.h" -- cgit v1.2.3-70-g09d2 From a5384c426744ebe41dafc6e5fa3acecc05e43462 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 25 Oct 2024 22:54:48 -0700 Subject: perf cap: Add __NR_capget to arch/x86 unistd As there are duplicated kernel headers in tools/include libc can pick up the wrong definitions. This was causing the wrong system call for capget in perf. Reported-by: Adrian Hunter Fixes: e25ebda78e230283 ("perf cap: Tidy up and improve capability testing") Closes: https://lore.kernel.org/lkml/cc7d6bdf-1aeb-4179-9029-4baf50b59342@intel.com/ Signed-off-by: Ian Rogers Tested-by: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20241026055448.312247-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/unistd_32.h | 3 +++ tools/arch/x86/include/uapi/asm/unistd_64.h | 3 +++ tools/perf/util/cap.c | 10 +++------- 3 files changed, 9 insertions(+), 7 deletions(-) (limited to 'tools/perf') diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 9de35df1afc3..63182a023e9d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -11,6 +11,9 @@ #ifndef __NR_getpgid #define __NR_getpgid 132 #endif +#ifndef __NR_capget +#define __NR_capget 184 +#endif #ifndef __NR_gettid #define __NR_gettid 224 #endif diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index d0f2043d7132..77311e8d1b5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -11,6 +11,9 @@ #ifndef __NR_getpgid #define __NR_getpgid 121 #endif +#ifndef __NR_capget +#define __NR_capget 125 +#endif #ifndef __NR_gettid #define __NR_gettid 186 #endif diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c index 7574a67651bc..69d9a2bcd40b 100644 --- a/tools/perf/util/cap.c +++ b/tools/perf/util/cap.c @@ -7,13 +7,9 @@ #include "debug.h" #include #include -#include #include #include - -#ifndef SYS_capget -#define SYS_capget 90 -#endif +#include #define MAX_LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 @@ -21,9 +17,9 @@ bool perf_cap__capable(int cap, bool *used_root) { struct __user_cap_header_struct header = { .version = _LINUX_CAPABILITY_VERSION_3, - .pid = getpid(), + .pid = 0, }; - struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S] = {}; __u32 cap_val; *used_root = false; -- cgit v1.2.3-70-g09d2