Merge tag 'perf-tools-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tools updates from Arnaldo Carvalho de Melo:
"New features:
- Introduce controlling how 'perf stat' and 'perf record' works via a
control file descriptor, allowing starting with events configured
but disabled until commands are received via the control file
descriptor. This allows, for instance for tools such as Intel VTune
to make further use of perf as its Linux platform driver.
- Improve 'perf record' to to register in a perf.data file header the
clockid used to help later correlate things like syslog files and
perf events recorded.
- Add basic syscall and find_next_bit benchmarks to 'perf bench'.
- Allow using computed metrics in calculating other metrics. For
instance:
{
.metric_expr = "l2_rqsts.demand_data_rd_hit + l2_rqsts.pf_hit + l2_rqsts.rfo_hit",
.metric_name = "DCache_L2_All_Hits",
},
{
.metric_expr = "max(l2_rqsts.all_demand_data_rd - l2_rqsts.demand_data_rd_hit, 0) + l2_rqsts.pf_miss + l2_rqsts.rfo_miss",
.metric_name = "DCache_L2_All_Miss",
},
{
.metric_expr = "dcache_l2_all_hits + dcache_l2_all_miss",
.metric_name = "DCache_L2_All",
}
- Add suport for 'd_ratio', '>' and '<' operators to the expression
resolver used in calculating metrics in 'perf stat'.
Support for new kernel features:
- Support TEXT_POKE and KSYMBOL_TYPE_OOL perf metadata events to cope
with things like ftrace, trampolines, i.e. changes in the kernel
text that gets in the way of properly decoding Intel PT hardware
traces, for instance.
Intel PT:
- Add various knobs to reduce the volume of Intel PT traces by
reducing the level of details such as decoding just some types of
packets (e.g., FUP/TIP, PSB+), also filtering by time range.
- Add new itrace options (log flags to the 'd' option, error flags to
the 'e' one, etc), controlling how Intel PT is transformed into
perf events, document some missing options (e.g., how to synthesize
callchains).
BPF:
- Properly report BPF errors when parsing events.
- Do not setup side-band events if LIBBPF is not linked, fixing a
segfault.
Libraries:
- Improvements to the libtraceevent plugin mechanism.
- Improve libtracevent support for KVM trace events SVM exit reasons.
- Add a libtracevent plugins for decoding syscalls/sys_enter_futex
and for tlb_flush.
- Ensure sample_period is set libpfm4 events in 'perf test'.
- Fixup libperf namespacing, to make sure what is in libperf has the
perf_ namespace while what is now only in tools/perf/ doesn't use
that prefix.
Arch specific:
- Improve the testing of vendor events and metrics in 'perf test'.
- Allow no ARM CoreSight hardware tracer sink to be specified on
command line.
- Fix arm_spe_x recording when mixed with other perf events.
- Add s390 idle functions 'psw_idle' and 'psw_idle_exit' to list of
idle symbols.
- List kernel supplied event aliases for arm64 in 'perf list'.
- Add support for extended register capability in PowerPC 9 and 10.
- Added nest IMC power9 metric events.
Miscellaneous:
- No need to setup sample_regs_intr/sample_regs_user for dummy
events.
- Update various copies of kernel headers, some causing perf to
handle new syscalls, MSRs, etc.
- Improve usage of flex and yacc, enabling warnings and addressing
the fallout.
- Add missing '--output' option to 'perf kmem' so that it can pass it
along to 'perf record'.
- 'perf probe' fixes related to adding multiple probes on the same
address for the same event.
- Make 'perf probe' warn if the target function is a GNU indirect
function.
- Remove //anon mmap events from 'perf inject jit' to fix supporting
both using ELF files for generated functions and the perf-PID.map
approaches"
* tag 'perf-tools-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (144 commits)
perf record: Skip side-band event setup if HAVE_LIBBPF_SUPPORT is not set
perf tools powerpc: Add support for extended regs in power10
perf tools powerpc: Add support for extended register capability
tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
tools arch x86: Sync asm/cpufeatures.h with the kernel sources
tools arch x86: Sync the msr-index.h copy with the kernel sources
tools headers UAPI: update linux/in.h copy
tools headers API: Update close_range affected files
perf script: Add 'tod' field to display time of day
perf script: Change the 'enum perf_output_field' enumerators to be 64 bits
perf data: Add support to store time of day in CTF data conversion
perf tools: Move clockid_res_ns under clock struct
perf header: Store clock references for -k/--clockid option
perf tools: Add clockid_name function
perf clockid: Move parse_clockid() to new clockid object
tools lib traceevent: Handle possible strdup() error in tep_add_plugin_path() API
libtraceevent: Fixed description of tep_add_plugin_path() API
libtraceevent: Fixed type in PRINT_FMT_STING
libtraceevent: Fixed broken indentation in parse_ip4_print_args()
libtraceevent: Improve error handling of tep_plugin_add_option() API
...
This commit is contained in:
Linus Torvalds
@@ -850,6 +850,8 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
|
||||
#define __NR_clone3 435
|
||||
__SYSCALL(__NR_clone3, sys_clone3)
|
||||
#endif
|
||||
#define __NR_close_range 436
|
||||
__SYSCALL(__NR_close_range, sys_close_range)
|
||||
|
||||
#define __NR_openat2 437
|
||||
__SYSCALL(__NR_openat2, sys_openat2)
|
||||
|
||||
@@ -55,7 +55,7 @@ extern "C" {
|
||||
* cause the related events to not be seen.
|
||||
*
|
||||
* I915_RESET_UEVENT - Event is generated just before an attempt to reset the
|
||||
* the GPU. The value supplied with the event is always 1. NOTE: Disable
|
||||
* GPU. The value supplied with the event is always 1. NOTE: Disable
|
||||
* reset via module parameter will cause this event to not be seen.
|
||||
*/
|
||||
#define I915_L3_PARITY_UEVENT "L3_PARITY_ERROR"
|
||||
@@ -1934,7 +1934,7 @@ enum drm_i915_perf_property_id {
|
||||
|
||||
/**
|
||||
* The value specifies which set of OA unit metrics should be
|
||||
* be configured, defining the contents of any OA unit reports.
|
||||
* configured, defining the contents of any OA unit reports.
|
||||
*
|
||||
* This property is available in perf revision 1.
|
||||
*/
|
||||
|
||||
@@ -123,6 +123,7 @@ struct in_addr {
|
||||
#define IP_CHECKSUM 23
|
||||
#define IP_BIND_ADDRESS_NO_PORT 24
|
||||
#define IP_RECVFRAGSIZE 25
|
||||
#define IP_RECVERR_RFC4884 26
|
||||
|
||||
/* IP_MTU_DISCOVER values */
|
||||
#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
|
||||
|
||||
@@ -383,7 +383,8 @@ struct perf_event_attr {
|
||||
bpf_event : 1, /* include bpf events */
|
||||
aux_output : 1, /* generate AUX records instead of events */
|
||||
cgroup : 1, /* include cgroup events */
|
||||
__reserved_1 : 31;
|
||||
text_poke : 1, /* include text poke events */
|
||||
__reserved_1 : 30;
|
||||
|
||||
union {
|
||||
__u32 wakeup_events; /* wakeup every n events */
|
||||
@@ -1041,12 +1042,35 @@ enum perf_event_type {
|
||||
*/
|
||||
PERF_RECORD_CGROUP = 19,
|
||||
|
||||
/*
|
||||
* Records changes to kernel text i.e. self-modified code. 'old_len' is
|
||||
* the number of old bytes, 'new_len' is the number of new bytes. Either
|
||||
* 'old_len' or 'new_len' may be zero to indicate, for example, the
|
||||
* addition or removal of a trampoline. 'bytes' contains the old bytes
|
||||
* followed immediately by the new bytes.
|
||||
*
|
||||
* struct {
|
||||
* struct perf_event_header header;
|
||||
* u64 addr;
|
||||
* u16 old_len;
|
||||
* u16 new_len;
|
||||
* u8 bytes[];
|
||||
* struct sample_id sample_id;
|
||||
* };
|
||||
*/
|
||||
PERF_RECORD_TEXT_POKE = 20,
|
||||
|
||||
PERF_RECORD_MAX, /* non-ABI */
|
||||
};
|
||||
|
||||
enum perf_record_ksymbol_type {
|
||||
PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0,
|
||||
PERF_RECORD_KSYMBOL_TYPE_BPF = 1,
|
||||
/*
|
||||
* Out of line code such as kprobe-replaced instructions or optimized
|
||||
* kprobes or ftrace trampolines.
|
||||
*/
|
||||
PERF_RECORD_KSYMBOL_TYPE_OOL = 2,
|
||||
PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */
|
||||
};
|
||||
|
||||
|
||||
Reference in New Issue
Block a user