From 8a96f454f566857290867fb3943ffc37ea7d50d2 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Sun, 27 Mar 2022 23:24:13 -0700
Subject: [PATCH 01/15] perf stat: Avoid SEGV if core.cpus isn't set
Passing NULL to perf_cpu_map__max doesn't make sense as there is no
valid max. Avoid this problem by null checking in
perf_stat_init_aggr_mode.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: John Garry <john.garry@huawei.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20220328062414.1893550-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4ee40de698a4..b81ae5053218 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1472,7 +1472,10 @@ static int perf_stat_init_aggr_mode(void)
* taking the highest cpu number to be the size of
* the aggregation translate cpumap.
*/
- nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
+ if (evsel_list->core.cpus)
+ nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
+ else
+ nr = 0;
stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
}
From 4d4d00dd321f2c9c1ce35ec2a1d32515371af009 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 19 Oct 2020 12:26:45 -0300
Subject: [PATCH 02/15] perf tools: Update copy of libbpf's hashmap.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
To pick the changes in:
fba60b171a032283 ("libbpf: Use IS_ERR_OR_NULL() in hashmap__free()")
That don't entail any changes in tools/perf.
This addresses this perf build warning:
Warning: Kernel ABI header at 'tools/perf/util/hashmap.h' differs from latest version at 'tools/lib/bpf/hashmap.h'
diff -u tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h
Not a kernel ABI, its just that this uses the mechanism in place for
checking kernel ABI files drift.
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mauricio Vásquez <mauricio@kinvolk.io>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/YkMb2SAIai2VeuUD@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/hashmap.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index 3c20b126d60d..aeb09c288716 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map)
void hashmap__free(struct hashmap *map)
{
- if (!map)
+ if (IS_ERR_OR_NULL(map))
return;
hashmap__clear(map);
@@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key,
return true;
}
-
From 9a195da42feca3948d7f1ee8a689e2b9d2406fb5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 6 Sep 2021 11:57:46 -0300
Subject: [PATCH 03/15] perf beauty: Update copy of linux/socket.h with the
kernel sources
To pick the changes in:
a6a6fe27bab48f0d ("net/smc: Dynamic control handshake limitation by socket options")
This automagically adds support for the SOL_MNC socket level:
$ diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h
--- tools/perf/trace/beauty/include/linux/socket.h 2022-03-14 17:55:22.277148656 -0300
+++ include/linux/socket.h 2022-03-27 19:12:48.908250063 -0300
@@ -366,6 +366,7 @@
#define SOL_XDP 283
#define SOL_MPTCP 284
#define SOL_MCTP 285
+#define SOL_SMC 286
/* IPX options */
#define IPX_TYPE 1
$ tools/perf/trace/beauty/socket.sh > before
$ cp include/linux/socket.h tools/perf/trace/beauty/include/linux/socket.h
$ tools/perf/trace/beauty/socket.sh > after
$ diff -u before after
--- before 2022-03-29 11:47:56.390258780 -0300
+++ after 2022-03-29 11:48:03.158436189 -0300
@@ -67,6 +67,7 @@
[283] = "XDP",
[284] = "MPTCP",
[285] = "MCTP",
+ [286] = "SMC",
};
DEFINE_STRARRAY(socket_level, "SOL_");
$
This will allow 'perf trace' to translate 286 into "SMC" as is done with
the other socket levels:
# perf trace -e setsockopt --max-events 4
344.916 ( 0.003 ms): Socket Thread/3816 setsockopt(fd: 168, level: TCP, optname: 5, optval: 0x7f5797b9c4f8, optlen: 4) = 0
344.920 ( 0.002 ms): Socket Thread/3816 setsockopt(fd: 168, level: TCP, optname: 6, optval: 0x7f5797b9c4f4, optlen: 4) = 0
1246.974 ( 0.010 ms): systemd-resolv/1128 setsockopt(fd: 22, level: IP, optname: 11, optval: 0x7ffc96cd7244, optlen: 4) = 0
1246.986 ( 0.002 ms): systemd-resolv/1128 setsockopt(fd: 22, level: IP, optname: 8, optval: 0x7ffc96cd7264, optlen: 4) = 0
This addresses this perf build warning:
Warning: Kernel ABI header at 'tools/perf/trace/beauty/include/linux/socket.h' differs from latest version at 'include/linux/socket.h'
diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: D. Wythe <alibuda@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/YkMdpzzjPu5VZtW3@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/trace/beauty/include/linux/socket.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 8ef26d89ef49..6f85f5d957ef 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -366,6 +366,7 @@ struct ucred {
#define SOL_XDP 283
#define SOL_MPTCP 284
#define SOL_MCTP 285
+#define SOL_SMC 286
/* IPX options */
#define IPX_TYPE 1
From 6d05e1398507fc3509debc397bb9dfa18fc5230e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Sep 2019 11:30:30 -0300
Subject: [PATCH 04/15] tools headers UAPI: Sync asm-generic/mman-common.h with
the kernel
To pick the changes from:
9457056ac426e5ed ("mm: madvise: MADV_DONTNEED_LOCKED")
That result in these changes in the tools:
$ diff -u tools/include/uapi/asm-generic/mman-common.h include/uapi/asm-generic/mman-common.h
--- tools/include/uapi/asm-generic/mman-common.h 2022-03-29 16:17:50.461694991 -0300
+++ include/uapi/asm-generic/mman-common.h 2022-03-27 19:12:48.923250468 -0300
@@ -75,6 +75,8 @@
#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */
#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */
+#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */
+
/* compatibility flags */
#define MAP_FILE 0
$ tools/perf/trace/beauty/madvise_behavior.sh > before
$ cp include/uapi/asm-generic/mman-common.h tools/include/uapi/asm-generic/mman-common.h
$ tools/perf/trace/beauty/madvise_behavior.sh > after
$ diff -u before after
--- before 2022-03-29 16:18:04.091044244 -0300
+++ after 2022-03-29 16:18:11.692238906 -0300
@@ -20,6 +20,7 @@
[21] = "PAGEOUT",
[22] = "POPULATE_READ",
[23] = "POPULATE_WRITE",
+ [24] = "DONTNEED_LOCKED",
[100] = "HWPOISON",
[101] = "SOFT_OFFLINE",
};
$
I.e. now when madvise gets those behaviours as args, 'perf trace' will
be able to translate from the number to a human readable string and to
use the strings in tracepoint filter expressions.
This addresses the following perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/mman-common.h' differs from latest version at 'include/uapi/asm-generic/mman-common.h'
diff -u tools/include/uapi/asm-generic/mman-common.h include/uapi/asm-generic/mman-common.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/YkNcUfeh795yqGMV@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/asm-generic/mman-common.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 1567a3294c3d..6c1aa92a92e4 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -75,6 +75,8 @@
#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */
#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */
+#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */
+
/* compatibility flags */
#define MAP_FILE 0
From 672b259fed48cca4210c4e2329861ed63a036f8b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 7 Aug 2020 08:45:47 -0300
Subject: [PATCH 05/15] tools arch x86: Sync the msr-index.h copy with the
kernel sources
To pick up the changes in:
991625f3dd2cbc4b ("x86/ibt: Add IBT feature, MSR and #CP handling")
Addressing these tools/perf build warnings:
diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h'
That makes the beautification scripts to pick some new entries:
$ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before
$ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h
$ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after
$ diff -u before after
--- before 2022-03-29 16:23:07.678740040 -0300
+++ after 2022-03-29 16:23:16.960978524 -0300
@@ -220,6 +220,13 @@
[0x00000669] = "MC6_DEMOTION_POLICY_CONFIG",
[0x00000680] = "LBR_NHM_FROM",
[0x00000690] = "CORE_PERF_LIMIT_REASONS",
+ [0x000006a0] = "IA32_U_CET",
+ [0x000006a2] = "IA32_S_CET",
+ [0x000006a4] = "IA32_PL0_SSP",
+ [0x000006a5] = "IA32_PL1_SSP",
+ [0x000006a6] = "IA32_PL2_SSP",
+ [0x000006a7] = "IA32_PL3_SSP",
+ [0x000006a8] = "IA32_INT_SSP_TAB",
[0x000006B0] = "GFX_PERF_LIMIT_REASONS",
[0x000006B1] = "RING_PERF_LIMIT_REASONS",
[0x000006c0] = "LBR_NHM_TO",
$
And this gets rebuilt:
CC /tmp/build/perf/trace/beauty/tracepoints/x86_msr.o
LD /tmp/build/perf/trace/beauty/tracepoints/perf-in.o
LD /tmp/build/perf/trace/beauty/perf-in.o
CC /tmp/build/perf/util/amd-sample-raw.o
LD /tmp/build/perf/util/perf-in.o
LD /tmp/build/perf/perf-in.o
LINK /tmp/build/perf/perf
Now one can trace systemwide asking to see backtraces to where those
MSRs are being read/written with:
# perf trace -e msr:*_msr/max-stack=32/ --filter="msr>=IA32_U_CET && msr<=IA32_INT_SSP_TAB"
^C#
If we use -v (verbose mode) we can see what it does behind the scenes:
# perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr>=IA32_U_CET && msr<=IA32_INT_SSP_TAB"
Using CPUID AuthenticAMD-25-21-0
0x6a0
0x6a8
New filter for msr:read_msr: (msr>=0x6a0 && msr<=0x6a8) && (common_pid != 597499 && common_pid != 3313)
0x6a0
0x6a8
New filter for msr:write_msr: (msr>=0x6a0 && msr<=0x6a8) && (common_pid != 597499 && common_pid != 3313)
mmap size 528384B
^C#
Example with a frequent msr:
# perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr==IA32_SPEC_CTRL" --max-events 2
Using CPUID AuthenticAMD-25-21-0
0x48
New filter for msr:read_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841)
0x48
New filter for msr:write_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841)
mmap size 528384B
Looking at the vmlinux_path (8 entries long)
symsrc__init: build id mismatch for vmlinux.
Using /proc/kcore for kernel data
Using /proc/kallsyms for symbols
0.000 Timer/2525383 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
do_trace_write_msr ([kernel.kallsyms])
do_trace_write_msr ([kernel.kallsyms])
__switch_to_xtra ([kernel.kallsyms])
__switch_to ([kernel.kallsyms])
__schedule ([kernel.kallsyms])
schedule ([kernel.kallsyms])
futex_wait_queue_me ([kernel.kallsyms])
futex_wait ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
__futex_abstimed_wait_common64 (/usr/lib64/libpthread-2.33.so)
0.030 :0/0 msr:write_msr(msr: IA32_SPEC_CTRL, val: 2)
do_trace_write_msr ([kernel.kallsyms])
do_trace_write_msr ([kernel.kallsyms])
__switch_to_xtra ([kernel.kallsyms])
__switch_to ([kernel.kallsyms])
__schedule ([kernel.kallsyms])
schedule_idle ([kernel.kallsyms])
do_idle ([kernel.kallsyms])
cpu_startup_entry ([kernel.kallsyms])
secondary_startup_64_no_verify ([kernel.kallsyms])
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/YkNd7Ky+vi7H2Zl2@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/asm/msr-index.h | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 0e7f303542bf..0eb90d21049e 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -205,6 +205,8 @@
#define RTIT_CTL_DISRETC BIT(11)
#define RTIT_CTL_PTW_EN BIT(12)
#define RTIT_CTL_BRANCH_EN BIT(13)
+#define RTIT_CTL_EVENT_EN BIT(31)
+#define RTIT_CTL_NOTNT BIT_ULL(55)
#define RTIT_CTL_MTC_RANGE_OFFSET 14
#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
#define RTIT_CTL_CYC_THRESH_OFFSET 19
@@ -360,11 +362,29 @@
#define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c
#define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d
-
#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690
#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0
#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1
+/* Control-flow Enforcement Technology MSRs */
+#define MSR_IA32_U_CET 0x000006a0 /* user mode cet */
+#define MSR_IA32_S_CET 0x000006a2 /* kernel mode cet */
+#define CET_SHSTK_EN BIT_ULL(0)
+#define CET_WRSS_EN BIT_ULL(1)
+#define CET_ENDBR_EN BIT_ULL(2)
+#define CET_LEG_IW_EN BIT_ULL(3)
+#define CET_NO_TRACK_EN BIT_ULL(4)
+#define CET_SUPPRESS_DISABLE BIT_ULL(5)
+#define CET_RESERVED (BIT_ULL(6) | BIT_ULL(7) | BIT_ULL(8) | BIT_ULL(9))
+#define CET_SUPPRESS BIT_ULL(10)
+#define CET_WAIT_ENDBR BIT_ULL(11)
+
+#define MSR_IA32_PL0_SSP 0x000006a4 /* ring-0 shadow stack pointer */
+#define MSR_IA32_PL1_SSP 0x000006a5 /* ring-1 shadow stack pointer */
+#define MSR_IA32_PL2_SSP 0x000006a6 /* ring-2 shadow stack pointer */
+#define MSR_IA32_PL3_SSP 0x000006a7 /* ring-3 shadow stack pointer */
+#define MSR_IA32_INT_SSP_TAB 0x000006a8 /* exception shadow stack table */
+
/* Hardware P state interface */
#define MSR_PPERF 0x0000064e
#define MSR_PERF_LIMIT_REASONS 0x0000064f
From 8db38afd12ef2134a033f9d266a9493b9c2cb7c8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 21 Dec 2020 12:53:44 -0300
Subject: [PATCH 06/15] tools kvm headers arm64: Update KVM headers from the
kernel sources
To pick the changes from:
34739fd95fab3a5e ("KVM: arm64: Indicate SYSTEM_RESET2 in kvm_run::system_event flags field")
583cda1b0e7d5d49 ("KVM: arm64: Refuse to run VCPU if the PMU doesn't match the physical CPU")
That don't causes any changes in tooling (when built on x86), only
addresses this perf build warning:
Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h'
diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h
Cc: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/lkml/YkSB4Q7kWmnaqeZU@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/arm64/include/uapi/asm/kvm.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 490d489d0ee8..c1b6ddc02d2f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -419,6 +419,16 @@ struct kvm_arm_copy_mte_tags {
#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS
#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED
+/* arm64-specific kvm_run::system_event flags */
+/*
+ * Reset caused by a PSCI v1.1 SYSTEM_RESET2 call.
+ * Valid only when the system event has a type of KVM_SYSTEM_EVENT_RESET.
+ */
+#define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0)
+
+/* run->fail_entry.hardware_entry_failure_reason codes. */
+#define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0)
+
#endif
#endif /* __ARM_KVM_H__ */
From 7ceda0cfcafee15e377ab532b37625bacda5eb84 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sun, 9 May 2021 09:39:02 -0300
Subject: [PATCH 07/15] tools headers UAPI: Sync linux/kvm.h with the kernel
sources
To pick the changes in:
6d8491910fcd3324 ("KVM: x86: Introduce KVM_CAP_DISABLE_QUIRKS2")
ef11c9463ae00630 ("KVM: s390: Add vm IOCTL for key checked guest absolute memory access")
e9e9feebcbc14b17 ("KVM: s390: Add optional storage key checking to MEMOP IOCTL")
That just rebuilds perf, as these patches don't add any new KVM ioctl to
be harvested for the the 'perf trace' ioctl syscall argument
beautifiers.
This is also by now used by tools/testing/selftests/kvm/, a simple test
build succeeded.
This silences this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lore.kernel.org/lkml/YkSCOWHQdir1lhdJ@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/kvm.h | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index bbc6b7c2dc1b..91a6fe4e02c0 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -562,9 +562,12 @@ struct kvm_s390_mem_op {
__u32 op; /* type of operation */
__u64 buf; /* buffer in userspace */
union {
- __u8 ar; /* the access register number */
+ struct {
+ __u8 ar; /* the access register number */
+ __u8 key; /* access key, ignored if flag unset */
+ };
__u32 sida_offset; /* offset into the sida */
- __u8 reserved[32]; /* should be set to 0 */
+ __u8 reserved[32]; /* ignored */
};
};
/* types for kvm_s390_mem_op->op */
@@ -572,9 +575,12 @@ struct kvm_s390_mem_op {
#define KVM_S390_MEMOP_LOGICAL_WRITE 1
#define KVM_S390_MEMOP_SIDA_READ 2
#define KVM_S390_MEMOP_SIDA_WRITE 3
+#define KVM_S390_MEMOP_ABSOLUTE_READ 4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
/* flags for kvm_s390_mem_op->flags */
#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
+#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
/* for KVM_INTERRUPT */
struct kvm_interrupt {
@@ -1137,6 +1143,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_PPC_AIL_MODE_3 210
#define KVM_CAP_S390_MEM_OP_EXTENSION 211
#define KVM_CAP_PMU_CAPABILITY 212
+#define KVM_CAP_DISABLE_QUIRKS2 213
#ifdef KVM_CAP_IRQ_ROUTING
From f444b2d15f7a025416ace9ec298f0b93ef68be68 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 13 Nov 2021 11:08:31 -0300
Subject: [PATCH 08/15] tools headers UAPI: Sync drm/i915_drm.h with the kernel
sources
To pick up the changes in:
caa574ffc4aaf4f2 ("drm/i915/uapi: document behaviour for DG2 64K support")
That don't add any new ioctl, so no changes in tooling.
This silences this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h'
diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: http://lore.kernel.org/lkml/YkSChHqaOApscFQ0@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/drm/i915_drm.h | 45 +++++++++++++++++++++++++++----
1 file changed, 40 insertions(+), 5 deletions(-)
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 914ebd9290e5..05c3642aaece 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1118,10 +1118,16 @@ struct drm_i915_gem_exec_object2 {
/**
* When the EXEC_OBJECT_PINNED flag is specified this is populated by
* the user with the GTT offset at which this object will be pinned.
+ *
* When the I915_EXEC_NO_RELOC flag is specified this must contain the
* presumed_offset of the object.
+ *
* During execbuffer2 the kernel populates it with the value of the
* current GTT offset of the object, for future presumed_offset writes.
+ *
+ * See struct drm_i915_gem_create_ext for the rules when dealing with
+ * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with
+ * minimum page sizes, like DG2.
*/
__u64 offset;
@@ -3144,11 +3150,40 @@ struct drm_i915_gem_create_ext {
*
* The (page-aligned) allocated size for the object will be returned.
*
- * Note that for some devices we have might have further minimum
- * page-size restrictions(larger than 4K), like for device local-memory.
- * However in general the final size here should always reflect any
- * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS
- * extension to place the object in device local-memory.
+ *
+ * DG2 64K min page size implications:
+ *
+ * On discrete platforms, starting from DG2, we have to contend with GTT
+ * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE
+ * objects. Specifically the hardware only supports 64K or larger GTT
+ * page sizes for such memory. The kernel will already ensure that all
+ * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page
+ * sizes underneath.
+ *
+ * Note that the returned size here will always reflect any required
+ * rounding up done by the kernel, i.e 4K will now become 64K on devices
+ * such as DG2.
+ *
+ * Special DG2 GTT address alignment requirement:
+ *
+ * The GTT alignment will also need to be at least 2M for such objects.
+ *
+ * Note that due to how the hardware implements 64K GTT page support, we
+ * have some further complications:
+ *
+ * 1) The entire PDE (which covers a 2MB virtual address range), must
+ * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same
+ * PDE is forbidden by the hardware.
+ *
+ * 2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM
+ * objects.
+ *
+ * To keep things simple for userland, we mandate that any GTT mappings
+ * must be aligned to and rounded up to 2MB. The kernel will internally
+ * pad them out to the next 2MB boundary. As this only wastes virtual
+ * address space and avoids userland having to copy any needlessly
+ * complicated PDE sharing scheme (coloring) and only affects DG2, this
+ * is deemed to be a good compromise.
*/
__u64 size;
/**
From 5ced81243593dd84f46ee3e7bb3cb8a69ede0276 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 1 Jul 2021 13:39:15 -0300
Subject: [PATCH 09/15] tools headers cpufeatures: Sync with the kernel sources
To pick the changes from:
991625f3dd2cbc4b ("x86/ibt: Add IBT feature, MSR and #CP handling")
This only causes these perf files to be rebuilt:
CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o
And addresses this perf build warning:
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h'
diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/YkSCx2kr4ambH+Qe@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/asm/cpufeatures.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 3edf05e98e58..73e643ae94b6 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -388,6 +388,7 @@
#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */
+#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */
#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */
#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */
#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */
From d4ff92659244a4783e424fa41b6f83645d8920c1 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 30 Mar 2022 18:22:54 +0800
Subject: [PATCH 10/15] perf tools: Stop depending on .git files for building
PERF-VERSION-FILE
This essentially reverts commit c72e3f04b45fb2e5 ("tools/perf/build:
Speed up git-version test on re-make") and commit 4e666cdb06eede20
("perf tools: Fix dependency for version file creation")
In commit c72e3f04b45fb2e5 ("tools/perf/build: Speed up git-version test
on re-make"), a makefile dependency on .git/HEAD was added. The
background is that running PERF-VERSION-FILE is relatively slow, and
commands like "git describe" are particularly slow.
In commit 4e666cdb06eede20 ("perf tools: Fix dependency for version file
creation"), an additional dependency on .git/ORIG_HEAD was added, as
.git/HEAD may not change for "git reset --hard HEAD^" command. However,
depending on whether we're on a branch or not, a "git cherry-pick" may
not lead to the version being updated.
As discussed with the git community in [0], using git internal files for
dependencies is not reliable. Commit 4e666cdb06ee also breaks some build
scenarios [1].
As mentioned, c72e3f04b45fb2e5 ("tools/perf/build: Speed up git-version
test on re-make") was added to speed up the build. However in commit
7572733b84997d23 ("perf tools: Fix version kernel tag") we removed the
call to "git describe", so just revert Makefile.perf back to same as pre
c72e3f04b45fb2e5 ("tools/perf/build: Speed up git-version test on
re-make") and the build should not be so slow, as below:
Pre 7572733b8499:
$> time util/PERF-VERSION-GEN
PERF_VERSION = 5.17.rc8.g4e666cdb06ee
real 0m0.110s
user 0m0.091s
sys 0m0.019s
Post 7572733b8499:
$> time util/PERF-VERSION-GEN
PERF_VERSION = 5.17.rc8.g7572733b8499
real 0m0.039s
user 0m0.036s
sys 0m0.007s
[0] https://lore.kernel.org/git/87wngkpddp.fsf@igel.home/T/#m4a4dd6de52fdbe21179306cd57b3761eb07f45f8
[1] https://lore.kernel.org/linux-perf-users/20220329093120.4173283-1-matthieu.baerts@tessares.net/T/#u
Committer testing:
After a fresh rebuild using 'make -C tools/perf O=/tmp/build/perf install-bin':
$ perf -v
perf version 5.17.g162f9db407b6
$ git log --oneline -1
162f9db407b6a6e5 (HEAD -> perf/core) perf tools: Stop depending on .git files for building PERF-VERSION-FILE
$
Now using a detached tarball, i.e. outside the kernel source tree:
$ ls -la perf*tar
ls: cannot access 'perf*tar': No such file or directory
$ make perf-tar-src-pkg
TAR
PERF_VERSION = 5.17.g31d10b3ef133
$ ls -la perf*tar
-rw-r--r--. 1 acme acme 22241280 Mar 30 13:26 perf-5.17.0.tar
$ mv perf-5.17.0.tar /tmp
$ cd /tmp
$ tar xf perf-5.17.0.tar
$ cd perf-5.17.0/
$ make -C tools/perf |& tail
CC util/pmu.o
CC util/pmu-flex.o
CC util/expr-flex.o
CC util/expr.o
LD util/scripting-engines/perf-in.o
LD util/intel-pt-decoder/perf-in.o
LD util/perf-in.o
LD perf-in.o
LINK perf
make: Leaving directory '/tmp/perf-5.17.0/tools/perf'
$ tools/perf/perf -v
perf version 5.17.g31d10b3ef133
$ pwd
/tmp/perf-5.17.0
$ cat PERF-VERSION-FILE
#define PERF_VERSION "5.17.g31d10b3ef133"
$
Fixes: 4e666cdb06eede20 ("perf tools: Fix dependency for version file creation")
Reported-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/1648635774-14581-1-git-send-email-john.garry@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.perf | 14 ++------------
1 file changed, 2 insertions(+), 12 deletions(-)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0520c8635d18..69473a836bae 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -691,9 +691,8 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
$(SCRIPTS) : % : %.sh
$(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
-$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD ../../.git/ORIG_HEAD
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
- $(Q)touch $(OUTPUT)PERF-VERSION-FILE
# These can record PERF_VERSION
perf.spec $(SCRIPTS) \
@@ -1139,21 +1138,12 @@ else
@echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP"
endif
-#
-# Trick: if ../../.git does not exist - we are building out of tree for example,
-# then force version regeneration:
-#
-ifeq ($(wildcard ../../.git/HEAD),)
- GIT-HEAD-PHONY = ../../.git/HEAD ../../.git/ORIG_HEAD
-else
- GIT-HEAD-PHONY =
-endif
FORCE:
.PHONY: all install clean config-clean strip install-gtk
.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
-.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare
+.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope FORCE prepare
.PHONY: libtraceevent_plugins archheaders
endif # force_fixdep
From 0df6ade7119daa40904b0c18871169e753663e14 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 28 Mar 2022 16:26:44 -0700
Subject: [PATCH 11/15] perf evlist: Rename cpus to user_requested_cpus
evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps
of all evsels.
For non-task targets, cpus is set to be cpus requested from the command
line, defaulting to all online cpus if no cpus are specified.
For an uncore event, all_cpus may be just CPU 0 or every online CPU.
This causes all_cpus to have fewer values than the cpus variable which
is confusing given the 'all' in the name.
To try to make the behavior clearer, rename cpus to user_requested_cpus
and add comments on the two struct variables.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: John Garry <john.garry@huawei.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20220328232648.2127340-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/perf/evlist.c | 28 ++++++++++++------------
tools/lib/perf/include/internal/evlist.h | 7 +++++-
tools/perf/arch/arm/util/cs-etm.c | 8 +++----
tools/perf/arch/arm64/util/arm-spe.c | 2 +-
tools/perf/arch/x86/util/intel-bts.c | 2 +-
tools/perf/arch/x86/util/intel-pt.c | 4 ++--
tools/perf/bench/evlist-open-close.c | 2 +-
tools/perf/builtin-ftrace.c | 2 +-
tools/perf/builtin-record.c | 6 ++---
tools/perf/builtin-stat.c | 10 ++++-----
tools/perf/builtin-top.c | 2 +-
tools/perf/util/auxtrace.c | 2 +-
tools/perf/util/bpf_ftrace.c | 4 ++--
tools/perf/util/evlist.c | 15 +++++++------
tools/perf/util/record.c | 6 ++---
tools/perf/util/sideband_evlist.c | 3 ++-
tools/perf/util/stat-display.c | 2 +-
tools/perf/util/synthetic-events.c | 2 +-
tools/perf/util/top.c | 8 ++++---
19 files changed, 62 insertions(+), 53 deletions(-)
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 9a770bfdc804..1b15ba13c477 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -41,10 +41,10 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
*/
if (!evsel->own_cpus || evlist->has_user_cpus) {
perf_cpu_map__put(evsel->cpus);
- evsel->cpus = perf_cpu_map__get(evlist->cpus);
- } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) {
+ evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
+ } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
perf_cpu_map__put(evsel->cpus);
- evsel->cpus = perf_cpu_map__get(evlist->cpus);
+ evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
} else if (evsel->cpus != evsel->own_cpus) {
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
@@ -123,10 +123,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
void perf_evlist__exit(struct perf_evlist *evlist)
{
- perf_cpu_map__put(evlist->cpus);
+ perf_cpu_map__put(evlist->user_requested_cpus);
perf_cpu_map__put(evlist->all_cpus);
perf_thread_map__put(evlist->threads);
- evlist->cpus = NULL;
+ evlist->user_requested_cpus = NULL;
evlist->all_cpus = NULL;
evlist->threads = NULL;
fdarray__exit(&evlist->pollfd);
@@ -155,9 +155,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist,
* original reference count of 1. If that is not the case it is up to
* the caller to increase the reference count.
*/
- if (cpus != evlist->cpus) {
- perf_cpu_map__put(evlist->cpus);
- evlist->cpus = perf_cpu_map__get(cpus);
+ if (cpus != evlist->user_requested_cpus) {
+ perf_cpu_map__put(evlist->user_requested_cpus);
+ evlist->user_requested_cpus = perf_cpu_map__get(cpus);
}
if (threads != evlist->threads) {
@@ -294,7 +294,7 @@ add:
int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
{
- int nr_cpus = perf_cpu_map__nr(evlist->cpus);
+ int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus);
int nr_threads = perf_thread_map__nr(evlist->threads);
int nfds = 0;
struct perf_evsel *evsel;
@@ -426,7 +426,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
int idx, struct perf_mmap_param *mp, int cpu_idx,
int thread, int *_output, int *_output_overwrite)
{
- struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+ struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx);
struct perf_evsel *evsel;
int revent;
@@ -536,7 +536,7 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
struct perf_mmap_param *mp)
{
int nr_threads = perf_thread_map__nr(evlist->threads);
- int nr_cpus = perf_cpu_map__nr(evlist->cpus);
+ int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus);
int cpu, thread;
for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -564,8 +564,8 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
{
int nr_mmaps;
- nr_mmaps = perf_cpu_map__nr(evlist->cpus);
- if (perf_cpu_map__empty(evlist->cpus))
+ nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus);
+ if (perf_cpu_map__empty(evlist->user_requested_cpus))
nr_mmaps = perf_thread_map__nr(evlist->threads);
return nr_mmaps;
@@ -576,7 +576,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
struct perf_mmap_param *mp)
{
struct perf_evsel *evsel;
- const struct perf_cpu_map *cpus = evlist->cpus;
+ const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 4cefade540bd..e3e64f37db7b 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -19,7 +19,12 @@ struct perf_evlist {
int nr_entries;
int nr_groups;
bool has_user_cpus;
- struct perf_cpu_map *cpus;
+ /**
+ * The cpus passed from the command line or all online CPUs by
+ * default.
+ */
+ struct perf_cpu_map *user_requested_cpus;
+ /** The union of all evsel cpu maps. */
struct perf_cpu_map *all_cpus;
struct perf_thread_map *threads;
int nr_mmaps;
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index cbc555245959..11c71aa219f7 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -199,7 +199,7 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
struct evsel *evsel, u32 option)
{
int i, err = -EINVAL;
- struct perf_cpu_map *event_cpus = evsel->evlist->core.cpus;
+ struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
/* Set option of each CPU we have */
@@ -299,7 +299,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
container_of(itr, struct cs_etm_recording, itr);
struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
struct evsel *evsel, *cs_etm_evsel = NULL;
- struct perf_cpu_map *cpus = evlist->core.cpus;
+ struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
bool privileged = perf_event_paranoid_check(-1);
int err = 0;
@@ -522,7 +522,7 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
{
int i;
int etmv3 = 0, etmv4 = 0, ete = 0;
- struct perf_cpu_map *event_cpus = evlist->core.cpus;
+ struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
/* cpu map is not empty, we have specific CPUs to work with */
@@ -713,7 +713,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
u32 offset;
u64 nr_cpu, type;
struct perf_cpu_map *cpu_map;
- struct perf_cpu_map *event_cpus = session->evlist->core.cpus;
+ struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus;
struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 5860bbaea95a..86e2e926aa0e 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -144,7 +144,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
container_of(itr, struct arm_spe_recording, itr);
struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
struct evsel *evsel, *arm_spe_evsel = NULL;
- struct perf_cpu_map *cpus = evlist->core.cpus;
+ struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
bool privileged = perf_event_paranoid_check(-1);
struct evsel *tracking_evsel;
int err;
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 4a76d49d25d6..d68a0f48e41e 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -110,7 +110,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
container_of(itr, struct intel_bts_recording, itr);
struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
struct evsel *evsel, *intel_bts_evsel = NULL;
- const struct perf_cpu_map *cpus = evlist->core.cpus;
+ const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
bool privileged = perf_event_paranoid_check(-1);
if (opts->auxtrace_sample_mode) {
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 8c31578d6f4a..38ec2666ec12 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -382,7 +382,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
ui__warning("Intel Processor Trace: TSC not available\n");
}
- per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus);
+ per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus);
auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
@@ -632,7 +632,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
bool have_timing_info, need_immediate = false;
struct evsel *evsel, *intel_pt_evsel = NULL;
- const struct perf_cpu_map *cpus = evlist->core.cpus;
+ const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
bool privileged = perf_event_paranoid_check(-1);
u64 tsc_bit;
int err;
diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c
index de56601f69ee..5a27691469ed 100644
--- a/tools/perf/bench/evlist-open-close.c
+++ b/tools/perf/bench/evlist-open-close.c
@@ -151,7 +151,7 @@ static int bench_evlist_open_close__run(char *evstr)
init_stats(&time_stats);
- printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.cpus));
+ printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.user_requested_cpus));
printf(" Number of threads:\t%d\n", evlist->core.threads->nr);
printf(" Number of events:\t%d (%d fds)\n",
evlist->core.nr_entries, evlist__count_evsel_fds(evlist));
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index ad9ce1bfffa1..7de07bb16d23 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -301,7 +301,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap)
static int set_tracing_cpu(struct perf_ftrace *ftrace)
{
- struct perf_cpu_map *cpumap = ftrace->evlist->core.cpus;
+ struct perf_cpu_map *cpumap = ftrace->evlist->core.user_requested_cpus;
if (!target__has_cpu(&ftrace->target))
return 0;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0b4abed555d8..ba74fab02e62 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -987,7 +987,7 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
int m, tm, nr_mmaps = evlist->core.nr_mmaps;
struct mmap *mmap = evlist->mmap;
struct mmap *overwrite_mmap = evlist->overwrite_mmap;
- struct perf_cpu_map *cpus = evlist->core.cpus;
+ struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
thread_data->mask->maps.nbits);
@@ -1881,7 +1881,7 @@ static int record__synthesize(struct record *rec, bool tail)
return err;
}
- err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.cpus,
+ err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus,
process_synthesized_event, NULL);
if (err < 0) {
pr_err("Couldn't synthesize cpu map.\n");
@@ -3675,7 +3675,7 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu
static int record__init_thread_masks(struct record *rec)
{
int ret = 0;
- struct perf_cpu_map *cpus = rec->evlist->core.cpus;
+ struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus;
if (!record__threads_enabled(rec))
return record__init_thread_default_masks(rec, cpus);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b81ae5053218..a96f106dc93a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -804,7 +804,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
if (group)
evlist__set_leader(evsel_list);
- if (!cpu_map__is_dummy(evsel_list->core.cpus)) {
+ if (!cpu_map__is_dummy(evsel_list->core.user_requested_cpus)) {
if (affinity__setup(&saved_affinity) < 0)
return -1;
affinity = &saved_affinity;
@@ -1458,7 +1458,7 @@ static int perf_stat_init_aggr_mode(void)
aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode);
if (get_id) {
- stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus,
+ stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus,
get_id, /*data=*/NULL);
if (!stat_config.aggr_map) {
pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
@@ -1472,8 +1472,8 @@ static int perf_stat_init_aggr_mode(void)
* taking the highest cpu number to be the size of
* the aggregation translate cpumap.
*/
- if (evsel_list->core.cpus)
- nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
+ if (evsel_list->core.user_requested_cpus)
+ nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
else
nr = 0;
stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
@@ -1630,7 +1630,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
if (!get_id)
return 0;
- stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env);
+ stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, env);
if (!stat_config.aggr_map) {
pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
return -1;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 9b08e44a31d9..fd8fd913c533 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1021,7 +1021,7 @@ static int perf_top__start_counters(struct perf_top *top)
evlist__for_each_entry(evlist, counter) {
try_again:
- if (evsel__open(counter, top->evlist->core.cpus,
+ if (evsel__open(counter, top->evlist->core.user_requested_cpus,
top->evlist->core.threads) < 0) {
/*
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9e48652662d4..df1c5bbbaa0d 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
mp->idx = idx;
if (per_cpu) {
- mp->cpu = perf_cpu_map__cpu(evlist->core.cpus, idx);
+ mp->cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, idx);
if (evlist->core.threads)
mp->tid = perf_thread_map__pid(evlist->core.threads, 0);
else
diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c
index 4f4d3aaff37c..7a4297d8fd2c 100644
--- a/tools/perf/util/bpf_ftrace.c
+++ b/tools/perf/util/bpf_ftrace.c
@@ -38,7 +38,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
/* don't need to set cpu filter for system-wide mode */
if (ftrace->target.cpu_list) {
- ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus);
+ ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus);
bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
}
@@ -63,7 +63,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
fd = bpf_map__fd(skel->maps.cpu_filter);
for (i = 0; i < ncpus; i++) {
- cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu;
+ cpu = perf_cpu_map__cpu(ftrace->evlist->core.user_requested_cpus, i).cpu;
bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
}
}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 9bb79e049957..cb2cf4463c08 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -440,7 +440,7 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name)
bool has_imm = false;
// See explanation in evlist__close()
- if (!cpu_map__is_dummy(evlist->core.cpus)) {
+ if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
if (affinity__setup(&saved_affinity) < 0)
return;
affinity = &saved_affinity;
@@ -500,7 +500,7 @@ static void __evlist__enable(struct evlist *evlist, char *evsel_name)
struct affinity saved_affinity, *affinity = NULL;
// See explanation in evlist__close()
- if (!cpu_map__is_dummy(evlist->core.cpus)) {
+ if (!cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
if (affinity__setup(&saved_affinity) < 0)
return;
affinity = &saved_affinity;
@@ -565,7 +565,7 @@ static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel,
static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread)
{
int cpu;
- int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
+ int nr_cpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
if (!evsel->core.fd)
return -EINVAL;
@@ -580,7 +580,7 @@ static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evse
int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
{
- bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus);
+ bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
if (per_cpu_mmaps)
return evlist__enable_event_cpu(evlist, evsel, idx);
@@ -1301,10 +1301,11 @@ void evlist__close(struct evlist *evlist)
struct affinity affinity;
/*
- * With perf record core.cpus is usually NULL.
+ * With perf record core.user_requested_cpus is usually NULL.
* Use the old method to handle this for now.
*/
- if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) {
+ if (!evlist->core.user_requested_cpus ||
+ cpu_map__is_dummy(evlist->core.user_requested_cpus)) {
evlist__for_each_entry_reverse(evlist, evsel)
evsel__close(evsel);
return;
@@ -1367,7 +1368,7 @@ int evlist__open(struct evlist *evlist)
* Default: one fd per CPU, all threads, aka systemwide
* as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
*/
- if (evlist->core.threads == NULL && evlist->core.cpus == NULL) {
+ if (evlist->core.threads == NULL && evlist->core.user_requested_cpus == NULL) {
err = evlist__create_syswide_maps(evlist);
if (err < 0)
goto out_err;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 007a64681416..5b09ecbb05dc 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call
if (opts->group)
evlist__set_leader(evlist);
- if (perf_cpu_map__cpu(evlist->core.cpus, 0).cpu < 0)
+ if (perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0).cpu < 0)
opts->no_inherit = true;
use_comm_exec = perf_can_comm_exec();
@@ -244,7 +244,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
evsel = evlist__last(temp_evlist);
- if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) {
+ if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) {
struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
if (cpus)
@@ -252,7 +252,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
perf_cpu_map__put(cpus);
} else {
- cpu = perf_cpu_map__cpu(evlist->core.cpus, 0);
+ cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, 0);
}
while (1) {
diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c
index 748371ac22be..388846f17bc1 100644
--- a/tools/perf/util/sideband_evlist.c
+++ b/tools/perf/util/sideband_evlist.c
@@ -114,7 +114,8 @@ int evlist__start_sb_thread(struct evlist *evlist, struct target *target)
}
evlist__for_each_entry(evlist, counter) {
- if (evsel__open(counter, evlist->core.cpus, evlist->core.threads) < 0)
+ if (evsel__open(counter, evlist->core.user_requested_cpus,
+ evlist->core.threads) < 0)
goto out_delete_evlist;
}
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 9cbe351b141f..138e3ab9d638 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -929,7 +929,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
int all_idx;
struct perf_cpu cpu;
- perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) {
+ perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) {
struct evsel *counter;
bool first = true;
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index b654de0841f8..27acdc5e5723 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -2127,7 +2127,7 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p
return err;
}
- err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL);
+ err = perf_event__synthesize_cpu_map(tool, evlist->core.user_requested_cpus, process, NULL);
if (err < 0) {
pr_err("Couldn't synthesize thread map.\n");
return err;
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index c1ebfc5d2e0c..b8b32431d2f7 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -95,15 +95,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
if (target->cpu_list)
ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
- perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "",
+ perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
+ ? "s" : "",
target->cpu_list);
else {
if (target->tid)
ret += SNPRINTF(bf + ret, size - ret, ")");
else
ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
- perf_cpu_map__nr(top->evlist->core.cpus),
- perf_cpu_map__nr(top->evlist->core.cpus) > 1 ? "s" : "");
+ perf_cpu_map__nr(top->evlist->core.user_requested_cpus),
+ perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
+ ? "s" : "");
}
perf_top__reset_sample_counters(top);
From c3ad8d23bc0e8cacd8ea2e6615b53c6a7811cb66 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 28 Mar 2022 16:26:45 -0700
Subject: [PATCH 12/15] perf cpumap: Add is_subset function
Returns true if the second argument is a subset of the first.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: John Garry <john.garry@huawei.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20220328232648.2127340-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/perf/cpumap.c | 20 ++++++++++++++++++++
tools/lib/perf/include/internal/cpumap.h | 1 +
2 files changed, 21 insertions(+)
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index ee66760f1e63..23701024e0c0 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -319,6 +319,26 @@ struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
return map->nr > 0 ? map->map[map->nr - 1] : result;
}
+/** Is 'b' a subset of 'a'. */
+bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b)
+{
+ if (a == b || !b)
+ return true;
+ if (!a || b->nr > a->nr)
+ return false;
+
+ for (int i = 0, j = 0; i < a->nr; i++) {
+ if (a->map[i].cpu > b->map[j].cpu)
+ return false;
+ if (a->map[i].cpu == b->map[j].cpu) {
+ j++;
+ if (j == b->nr)
+ return true;
+ }
+ }
+ return false;
+}
+
/*
* Merge two cpumaps
*
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 1973a18c096b..35dd29642296 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -25,5 +25,6 @@ struct perf_cpu_map {
#endif
int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
+bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
#endif /* __LIBPERF_INTERNAL_CPUMAP_H */
From da0bfb9fdf1fef8d2329efb215abfd94ba262b49 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 28 Mar 2022 16:26:46 -0700
Subject: [PATCH 13/15] perf cpumap: More cpu map reuse by merge.
perf_cpu_map__merge() will reuse one of its arguments if they are equal or
the other argument is NULL.
The arguments could be reused if it is known one set of values is a
subset of the other.
For example, a map of 0-1 and a map of just 0 when merged yields the map
of 0-1.
Currently a new map is created rather than adding a reference count to
the original 0-1 map.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: German Gomez <german.gomez@arm.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: John Garry <john.garry@huawei.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20220328232648.2127340-5-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/perf/cpumap.c | 15 +++++----------
1 file changed, 5 insertions(+), 10 deletions(-)
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 23701024e0c0..384d5e076ee4 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -355,17 +355,12 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
int i, j, k;
struct perf_cpu_map *merged;
- if (!orig && !other)
- return NULL;
- if (!orig) {
- perf_cpu_map__get(other);
- return other;
+ if (perf_cpu_map__is_subset(orig, other))
+ return orig;
+ if (perf_cpu_map__is_subset(other, orig)) {
+ perf_cpu_map__put(orig);
+ return perf_cpu_map__get(other);
}
- if (!other)
- return orig;
- if (orig->nr == other->nr &&
- !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
- return orig;
tmp_len = orig->nr + other->nr;
tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
From f717d89a2b20dd9201a3ed798cff6b8f09c77e01 Mon Sep 17 00:00:00 2001
From: Haowen Bai <baihaowen@meizu.com>
Date: Mon, 28 Mar 2022 09:55:32 +0800
Subject: [PATCH 14/15] perf evlist: Directly return instead of using local ret
variable
Addresses this coccinelle warning:
./tools/perf/util/evlist.c:1333:5-8: Unneeded variable: "err". Return
"- ENOMEM" on line 1358
Signed-off-by: Haowen Bai <baihaowen@meizu.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/1648432532-23151-1-git-send-email-baihaowen@meizu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evlist.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cb2cf4463c08..52ea004ba01e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1331,7 +1331,6 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
{
struct perf_cpu_map *cpus;
struct perf_thread_map *threads;
- int err = -ENOMEM;
/*
* Try reading /sys/devices/system/cpu/online to get
@@ -1356,7 +1355,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
out_put:
perf_cpu_map__put(cpus);
out:
- return err;
+ return -ENOMEM;
}
int evlist__open(struct evlist *evlist)
From 7e2022af7921978ce37bb8fc1a35239b81cbc1af Mon Sep 17 00:00:00 2001
From: Tanu M <tanu235m@gmail.com>
Date: Sun, 27 Mar 2022 23:08:46 -0700
Subject: [PATCH 15/15] perf python: Convert tracepoint.py example to python3
Convert the tracepoint.py file to python3 as many of the files in
tools/perf are already written in python3.
Committer testing:
# export PYTHONPATH=/tmp/build/perf/python/
# python3 ~acme/git/perf/tools/perf/python/tracepoint.py | head
time 67394457376909 prev_comm=swapper/12 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=gnome-terminal- next_pid=3313 next_prio=120
time 67394457807669 prev_comm=python3 prev_pid=1485930 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/13 next_pid=0 next_prio=120
time 67394457811859 prev_comm=swapper/13 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=python3 next_pid=1485930 next_prio=120
time 67394457824929 prev_comm=python3 prev_pid=1485930 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/13 next_pid=0 next_prio=120
time 67394457831899 prev_comm=swapper/13 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=python3 next_pid=1485930 next_prio=120
time 67394457842299 prev_comm=python3 prev_pid=1485930 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/13 next_pid=0 next_prio=120
time 67394457844179 prev_comm=swapper/13 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=python3 next_pid=1485930 next_prio=120
time 67394457853879 prev_comm=python3 prev_pid=1485930 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/13 next_pid=0 next_prio=120
time 67394457856339 prev_comm=swapper/13 prev_pid=0 prev_prio=120 prev_state=0x0 ==> next_comm=python3 next_pid=1485930 next_prio=120
time 67394457865659 prev_comm=python3 prev_pid=1485930 prev_prio=120 prev_state=0x1 ==> next_comm=swapper/13 next_pid=0 next_prio=120
Traceback (most recent call last):
File "/var/home/acme/git/perf/tools/perf/python/tracepoint.py", line 48, in <module>
main()
File "/var/home/acme/git/perf/tools/perf/python/tracepoint.py", line 37, in main
print("time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % (
BrokenPipeError: [Errno 32] Broken pipe
#
Signed-off-by: Tanu M <tanu235m@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/linux-perf-users/CAPS78prawYzRZnyhWjgOnGw4EwoswNwztvfZFdCOPOydFzVwzQ@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/python/tracepoint.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py
index 461848c7f57d..bba68a6d4515 100755
--- a/tools/perf/python/tracepoint.py
+++ b/tools/perf/python/tracepoint.py
@@ -34,7 +34,7 @@ def main():
if not isinstance(event, perf.sample_event):
continue
- print "time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % (
+ print("time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % (
event.sample_time,
event.prev_comm,
event.prev_pid,
@@ -42,7 +42,7 @@ def main():
event.prev_state,
event.next_comm,
event.next_pid,
- event.next_prio)
+ event.next_prio))
if __name__ == '__main__':
main()