summaryrefslogtreecommitdiff
path: root/tools/arch
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2019-05-18 10:24:43 +0200
committerIngo Molnar <mingo@kernel.org>2019-05-18 10:24:43 +0200
commit62e1c09418fc16d27720b128275cac61367e2c1b (patch)
tree4759aa6662b1398e2b93696ace58f6f309722b06 /tools/arch
parent01be377c62210a8d8fef35be906f9349591bb7cd (diff)
parent4fc4d8dfa056dfd48afe73b9ea3b7570ceb80b9c (diff)
Merge tag 'perf-core-for-mingo-5.2-20190517' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: perf.data: Alexey Budankov: - Streaming compression of perf ring buffer into PERF_RECORD_COMPRESSED user space records, resulting in ~3-5x perf.data file size reduction on variety of tested workloads what saves storage space on larger server systems where perf.data size can easily reach several tens or even hundreds of GiBs, especially when profiling with DWARF-based stacks and tracing of context switches. perf record: Arnaldo Carvalho de Melo - Improve -user-regs/intr-regs suggestions to overcome errors. perf annotate: Jin Yao: - Remove hist__account_cycles() from callback, speeding up branch processing (perf record -b). perf stat: - Add a 'percore' event qualifier, e.g.: -e cpu/event=0,umask=0x3,percore=1/, that sums up the event counts for both hardware threads in a core. We can already do this with --per-core, but it's often useful to do this together with other metrics that are collected per hardware thread. I.e. now its possible to do this per-event, and have it mixed with other events not aggregated by core. core libraries: Donald Yandt: - Check for errors when doing fgets(/proc/version). Jiri Olsa: - Speed up report for perf compiled with linbunwind. tools headers: Arnaldo Carvalho de Melo - Update memcpy_64.S, x86's kvm.h and pt_regs.h. arm64: Florian Fainelli: - Map Brahma-B53 CPUID to cortex-a53 events. - Add Cortex-A57 and Cortex-A72 events. csky: Mao Han: - Add DWARF register mappings for libdw, allowing --call-graph=dwarf to work on the C-SKY arch. x86: Andi Kleen/Kan Liang: - Add support for recording and printing XMM registers, available, for instance, on Icelake. Kan Liang: - Add uncore_upi (Intel's "Ultra Path Interconnect" events) JSON support. UPI replaced the Intel QuickPath Interconnect (QPI) in Xeon Skylake-SP. Intel PT: Adrian Hunter . Fix instructions sampling rate. . Timestamp fixes. . Improve exported-sql-viewer GUI, allowing, for instance, to copy'n'paste the trees, useful for e-mailing. Documentation: Thomas Richter: - Add description for 'perf --debug stderr=1', which redirects stderr to stdout. libtraceevent: Tzvetomir Stoyanov: - Add man pages for the various APIs. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'tools/arch')
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h1
-rw-r--r--tools/arch/x86/include/uapi/asm/perf_regs.h23
-rw-r--r--tools/arch/x86/lib/memcpy_64.S3
3 files changed, 25 insertions, 2 deletions
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index dabfcf7c3941..7a0e64ccd6ff 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -381,6 +381,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 100644
--- a/tools/arch/x86/include/uapi/asm/perf_regs.h
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,8 +27,29 @@ enum perf_event_x86_regs {
PERF_REG_X86_R13,
PERF_REG_X86_R14,
PERF_REG_X86_R15,
-
+ /* These are the limits for the GPRs. */
PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+ /* These all need two bits set because they are 128bit */
+ PERF_REG_X86_XMM0 = 32,
+ PERF_REG_X86_XMM1 = 34,
+ PERF_REG_X86_XMM2 = 36,
+ PERF_REG_X86_XMM3 = 38,
+ PERF_REG_X86_XMM4 = 40,
+ PERF_REG_X86_XMM5 = 42,
+ PERF_REG_X86_XMM6 = 44,
+ PERF_REG_X86_XMM7 = 46,
+ PERF_REG_X86_XMM8 = 48,
+ PERF_REG_X86_XMM9 = 50,
+ PERF_REG_X86_XMM10 = 52,
+ PERF_REG_X86_XMM11 = 54,
+ PERF_REG_X86_XMM12 = 56,
+ PERF_REG_X86_XMM13 = 58,
+ PERF_REG_X86_XMM14 = 60,
+ PERF_REG_X86_XMM15 = 62,
+
+ /* These include both GPRs and XMMX registers */
+ PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
};
#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 3b24dc05251c..9d05572370ed 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe)
/* Copy successful. Return zero */
.L_done_memcpy_trap:
xorl %eax, %eax
+.L_done:
ret
ENDPROC(__memcpy_mcsafe)
EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
@@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
addl %edx, %ecx
.E_trailing_bytes:
mov %ecx, %eax
- ret
+ jmp .L_done
/*
* For write fault handling, given the destination is unaligned,