summaryrefslogtreecommitdiffstats
path: root/tools/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-01-18 06:32:11 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-18 06:32:11 +0200
commit57d17378a4a042401b0c2fe211e5a0e3a276cb3d (patch)
treebe65e51a7b11cccb903b44708b98b3af47477304 /tools/arch
parentf0033681f0fe8421baf8db125e57fa6157824c2d (diff)
parent9bce13ea88f85344b765abe5d3dabdd0f44dc177 (diff)
downloadlinux-57d17378a4a042401b0c2fe211e5a0e3a276cb3d.tar.bz2
Merge tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tool updates from Arnaldo Carvalho de Melo: "New features: - Add 'trace' subcommand for 'perf ftrace', setting the stage for more 'perf ftrace' subcommands. Not using a subcommand yields the previous behaviour of 'perf ftrace'. - Add 'latency' subcommand to 'perf ftrace', that can use the function graph tracer or a BPF optimized one, via the -b/--use-bpf option. E.g.: $ sudo perf ftrace latency -a -T mutex_lock sleep 1 # DURATION | COUNT | GRAPH | 0 - 1 us | 4596 | ######################## | 1 - 2 us | 1680 | ######### | 2 - 4 us | 1106 | ##### | 4 - 8 us | 546 | ## | 8 - 16 us | 562 | ### | 16 - 32 us | 1 | | 32 - 64 us | 0 | | 64 - 128 us | 0 | | 128 - 256 us | 0 | | 256 - 512 us | 0 | | 512 - 1024 us | 0 | | 1 - 2 ms | 0 | | 2 - 4 ms | 0 | | 4 - 8 ms | 0 | | 8 - 16 ms | 0 | | 16 - 32 ms | 0 | | 32 - 64 ms | 0 | | 64 - 128 ms | 0 | | 128 - 256 ms | 0 | | 256 - 512 ms | 0 | | 512 - 1024 ms | 0 | | 1 - ... s | 0 | | The original implementation of this command was in the bcc tool. - Support --cputype option for hybrid events in 'perf stat'. Improvements: - Call chain improvements for ARM64. - No need to do any affinity setup when profiling pids. - Reduce multiplexing with duration_time in 'perf stat' metrics. - Improve error message for uncore events, stating that some event groups are can only be used in system wide (-a) mode. - perf stat metric group leader fixes/improvements, including arch specific changes to better support Intel topdown events. - Probe non-deprecated sysfs path first, i.e. try the path /sys/devices/system/cpu/cpuN/topology/thread_siblings first, then the old /sys/devices/system/cpu/cpuN/topology/core_cpus. - Disable debuginfod by default in 'perf record', to avoid stalls on distros such as Fedora 35. - Use unbuffered output in 'perf bench' when pipe/tee'ing to a file. - Enable ignore_missing_thread in 'perf trace' Fixes: - Avoid TUI crash when navigating in the annotation of recursive functions. - Fix hex dump character output in 'perf script'. - Fix JSON indentation to 4 spaces standard in the ARM vendor event files. - Fix use after free in metric__new(). - Fix IS_ERR_OR_NULL() usage in the perf BPF loader. - Fix up cross-arch register support, i.e. when printing register names take into account the architecture where the perf.data file was collected. - Fix SMT fallback with large core counts. - Don't lower case MetricExpr when parsing JSON files so as not to lose info such as the ":G" event modifier in metrics. perf test: - Add basic stress test for sigtrap handling to 'perf test'. - Fix 'perf test' failures on s/390 - Enable system wide for metricgroups test in 'perf test´. - Use 3 digits for test numbering now we can have more tests. Arch specific: - Add events for Arm Neoverse N2 in the ARM JSON vendor event files - Support PERF_MEM_LVLNUM encodings in powerpc, that came from a single patch series, where I incorrectly merged the kernel bits, that were then reverted after coordination with Michael Ellerman and Stephen Rothwell. - Add ARM SPE total latency as PERF_SAMPLE_WEIGHT. - Update AMD documentation, with info on raw event encoding. - Add support for global and local variants of the "p_stage_cyc" sort key, applicable to perf.data files collected on powerpc. - Remove duplicate and incorrect aux size checks in the ARM CoreSight ETM code. Refactorings: - Add a perf_cpu abstraction to disambiguate CPUs and CPU map indexes, fixing problems along the way. - Document CPU map methods. UAPI sync: - Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' - Sync UAPI files with the kernel sources: drm, msr-index, cpufeatures. Build system - Enable warnings through HOSTCFLAGS. - Drop requirement for libstdc++.so for libopencsd check libperf: - Make libperf adopt perf_counts_values__scale() from tools/perf/util/. - Add a stat multiplexing test to libperf" * tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (115 commits) perf record: Disable debuginfod by default perf evlist: No need to do any affinity setup when profiling pids perf cpumap: Add is_dummy() method perf metric: Fix metric_leader perf cputopo: Fix CPU topology reading on s/390 perf metricgroup: Fix use after free in metric__new() libperf tests: Update a use of the new cpumap API perf arm: Fix off-by-one directory path tools arch x86: Sync the msr-index.h copy with the kernel sources tools headers cpufeatures: Sync with the kernel sources tools headers UAPI: Update tools's copy of drm.h header tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' perf pmu-events: Don't lower case MetricExpr perf expr: Add debug logging for literals perf tools: Probe non-deprecated sysfs path 1st perf tools: Fix SMT fallback with large core counts perf cpumap: Give CPUs their own type perf stat: Correct first_shadow_cpu to return index perf script: Fix flipped index and cpu perf c2c: Use more intention revealing iterator ...
Diffstat (limited to 'tools/arch')
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h1
-rw-r--r--tools/arch/x86/include/asm/msr-index.h17
-rw-r--r--tools/arch/x86/lib/memcpy_64.S12
-rw-r--r--tools/arch/x86/lib/memset_64.S6
4 files changed, 27 insertions, 9 deletions
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d5b5f2ab87a0..18de5f76f198 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -315,6 +315,7 @@
#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 01e2650b9585..3faf0f97edb1 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -486,6 +486,23 @@
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+/* AMD Collaborative Processor Performance Control MSRs */
+#define MSR_AMD_CPPC_CAP1 0xc00102b0
+#define MSR_AMD_CPPC_ENABLE 0xc00102b1
+#define MSR_AMD_CPPC_CAP2 0xc00102b2
+#define MSR_AMD_CPPC_REQ 0xc00102b3
+#define MSR_AMD_CPPC_STATUS 0xc00102b4
+
+#define AMD_CPPC_LOWEST_PERF(x) (((x) >> 0) & 0xff)
+#define AMD_CPPC_LOWNONLIN_PERF(x) (((x) >> 8) & 0xff)
+#define AMD_CPPC_NOMINAL_PERF(x) (((x) >> 16) & 0xff)
+#define AMD_CPPC_HIGHEST_PERF(x) (((x) >> 24) & 0xff)
+
+#define AMD_CPPC_MAX_PERF(x) (((x) & 0xff) << 0)
+#define AMD_CPPC_MIN_PERF(x) (((x) & 0xff) << 8)
+#define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16)
+#define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24)
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 1cc9da6e29c7..59cf2343f3d9 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -39,7 +39,7 @@ SYM_FUNC_START_WEAK(memcpy)
rep movsq
movl %edx, %ecx
rep movsb
- ret
+ RET
SYM_FUNC_END(memcpy)
SYM_FUNC_END_ALIAS(__memcpy)
EXPORT_SYMBOL(memcpy)
@@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms)
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
- ret
+ RET
SYM_FUNC_END(memcpy_erms)
SYM_FUNC_START_LOCAL(memcpy_orig)
@@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movq %r9, 1*8(%rdi)
movq %r10, -2*8(%rdi, %rdx)
movq %r11, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_16bytes:
cmpl $8, %edx
@@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movq -1*8(%rsi, %rdx), %r9
movq %r8, 0*8(%rdi)
movq %r9, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_8bytes:
cmpl $4, %edx
@@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movl -4(%rsi, %rdx), %r8d
movl %ecx, (%rdi)
movl %r8d, -4(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_3bytes:
subl $1, %edx
@@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
movb %cl, (%rdi)
.Lend:
- retq
+ RET
SYM_FUNC_END(memcpy_orig)
.popsection
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 9827ae267f96..d624f2bc42f1 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
movl %edx,%ecx
rep stosb
movq %r9,%rax
- ret
+ RET
SYM_FUNC_END(__memset)
SYM_FUNC_END_ALIAS(memset)
EXPORT_SYMBOL(memset)
@@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms)
movq %rdx,%rcx
rep stosb
movq %r9,%rax
- ret
+ RET
SYM_FUNC_END(memset_erms)
SYM_FUNC_START_LOCAL(memset_orig)
@@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig)
.Lende:
movq %r10,%rax
- ret
+ RET
.Lbad_alignment:
cmpq $7,%rdx