diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-02-10 09:48:18 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-02-10 09:48:18 -0800 |
commit | 212146f0800e151bd61b98fb6fe4b8b6778a649a (patch) | |
tree | 1b7eb90fe90c4bb37520f649583117a1f23fb72e | |
parent | d2a6aae99f5fa2f1e7e400bd2f17c1d42c50312a (diff) | |
parent | 3bb2600657dac78580e5b8fecc202eaaff5d4ced (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"A couple of kernel side fixes:
- Fix the Intel uncore driver on certain hardware configurations
- Fix a CPU hotplug related memory allocation bug
- Remove a spurious WARN()
... plus also a handful of perf tooling fixes"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf script python: Add Python3 support to tests/attr.py
perf trace: Support multiple "vfs_getname" probes
perf symbols: Filter out hidden symbols from labels
perf symbols: Add fallback definitions for GELF_ST_VISIBILITY()
tools headers uapi: Sync linux/in.h copy from the kernel sources
perf clang: Do not use 'return std::move(something)'
perf mem/c2c: Fix perf_mem_events to support powerpc
perf tests evsel-tp-sched: Fix bitwise operator
perf/core: Don't WARN() for impossible ring-buffer sizes
perf/x86/intel: Delay memory deallocation until x86_pmu_dead_cpu()
perf/x86/intel/uncore: Add Node ID mask
-rw-r--r-- | arch/x86/events/intel/core.c | 16 | ||||
-rw-r--r-- | arch/x86/events/intel/uncore_snbep.c | 4 | ||||
-rw-r--r-- | kernel/events/ring_buffer.c | 3 | ||||
-rw-r--r-- | tools/include/uapi/linux/in.h | 2 | ||||
-rw-r--r-- | tools/perf/Documentation/perf-c2c.txt | 16 | ||||
-rw-r--r-- | tools/perf/Documentation/perf-mem.txt | 2 | ||||
-rw-r--r-- | tools/perf/arch/powerpc/util/Build | 1 | ||||
-rw-r--r-- | tools/perf/arch/powerpc/util/mem-events.c | 11 | ||||
-rw-r--r-- | tools/perf/builtin-trace.c | 25 | ||||
-rw-r--r-- | tools/perf/tests/attr.py | 32 | ||||
-rw-r--r-- | tools/perf/tests/evsel-tp-sched.c | 2 | ||||
-rw-r--r-- | tools/perf/util/c++/clang.cpp | 2 | ||||
-rw-r--r-- | tools/perf/util/mem-events.c | 2 | ||||
-rw-r--r-- | tools/perf/util/symbol-elf.c | 23 |
14 files changed, 105 insertions, 36 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 40e12cfc87f6..daafb893449b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,6 +3559,14 @@ static void free_excl_cntrs(int cpu) static void intel_pmu_cpu_dying(int cpu) { + fini_debug_store_on_cpu(cpu); + + if (x86_pmu.counter_freezing) + disable_counter_freeze(); +} + +static void intel_pmu_cpu_dead(int cpu) +{ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; @@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu) } free_excl_cntrs(cpu); - - fini_debug_store_on_cpu(cpu); - - if (x86_pmu.counter_freezing) - disable_counter_freeze(); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -3663,6 +3666,7 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, }; static struct attribute *intel_pmu_attrs[]; @@ -3703,6 +3707,8 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, + .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index c07bee31abe8..b10e04387f38 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = { .id_table = snbep_uncore_pci_ids, }; +#define NODE_ID_MASK 0x7 + /* * build pci bus to socket mapping */ @@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); if (err) break; - nodeid = config; + nodeid = config & NODE_ID_MASK; /* get the Node ID mapping */ err = pci_read_config_dword(ubox_dev, idmap_loc, &config); if (err) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4a9937076331..309ef5a64af5 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct ring_buffer); size += nr_pages * sizeof(void *); + if (order_base_2(size) >= MAX_ORDER) + goto fail; + rb = kzalloc(size, GFP_KERNEL); if (!rb) goto fail; diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index f6052e70bf40..a55cb8b10165 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -268,7 +268,7 @@ struct sockaddr_in { #define IN_MULTICAST(a) IN_CLASSD(a) #define IN_MULTICAST_NET 0xe0000000 -#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) #define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) #define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 095aebdc5bb7..e6150f21267d 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -19,8 +19,11 @@ C2C stands for Cache To Cache. The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows you to track down the cacheline contentions. -The tool is based on x86's load latency and precise store facility events -provided by Intel CPUs. These events provide: +On x86, the tool is based on load latency and precise store facility events +provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling +with thresholding feature. + +These events provide: - memory address of the access - type of the access (load and store details) - latency (in cycles) of the load access @@ -46,7 +49,7 @@ RECORD OPTIONS -l:: --ldlat:: - Configure mem-loads latency. + Configure mem-loads latency. (x86 only) -k:: --all-kernel:: @@ -119,11 +122,16 @@ Following perf record options are configured by default: -W,-d,--phys-data,--sample-cpu Unless specified otherwise with '-e' option, following events are monitored by -default: +default on x86: cpu/mem-loads,ldlat=30/P cpu/mem-stores/P +and following on PowerPC: + + cpu/mem-loads/ + cpu/mem-stores/ + User can pass any 'perf record' option behind '--' mark, like (to enable callchains and system wide monitoring): diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index f8d2167cf3e7..199ea0f0a6c0 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -82,7 +82,7 @@ RECORD OPTIONS Be more verbose (show counter open errors, etc) --ldlat <n>:: - Specify desired latency for loads event. + Specify desired latency for loads event. (x86 only) In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 2e6595310420..ba98bd006488 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -2,6 +2,7 @@ libperf-y += header.o libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-y += perf_regs.o +libperf-y += mem-events.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c new file mode 100644 index 000000000000..d08311f04e95 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "mem-events.h" + +/* PowerPC does not support 'ldlat' parameter. */ +char *perf_mem_events__name(int i) +{ + if (i == PERF_MEM_EVENTS__LOAD) + return (char *) "cpu/mem-loads/"; + + return (char *) "cpu/mem-stores/"; +} diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ed4583128b9c..b36061cd1ab8 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) { - struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname"); + bool found = false; + struct perf_evsel *evsel, *tmp; + struct parse_events_error err = { .idx = 0, }; + int ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (IS_ERR(evsel)) + if (ret) return false; - if (perf_evsel__field(evsel, "pathname") == NULL) { + evlist__for_each_entry_safe(evlist, evsel, tmp) { + if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname")) + continue; + + if (perf_evsel__field(evsel, "pathname")) { + evsel->handler = trace__vfs_getname; + found = true; + continue; + } + + list_del_init(&evsel->node); + evsel->evlist = NULL; perf_evsel__delete(evsel); - return false; } - evsel->handler = trace__vfs_getname; - perf_evlist__add(evlist, evsel); - return true; + return found; } static struct perf_evsel *perf_evsel__new_pgfault(u64 config) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 44090a9a19f3..e952127e4fb0 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -1,6 +1,8 @@ #! /usr/bin/python # SPDX-License-Identifier: GPL-2.0 +from __future__ import print_function + import os import sys import glob @@ -8,7 +10,11 @@ import optparse import tempfile import logging import shutil -import ConfigParser + +try: + import configparser +except ImportError: + import ConfigParser as configparser def data_equal(a, b): # Allow multiple values in assignment separated by '|' @@ -100,20 +106,20 @@ class Event(dict): def equal(self, other): for t in Event.terms: log.debug(" [%s] %s %s" % (t, self[t], other[t])); - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: return False if not data_equal(self[t], other[t]): return False return True def optional(self): - if self.has_key('optional') and self['optional'] == '1': + if 'optional' in self and self['optional'] == '1': return True return False def diff(self, other): for t in Event.terms: - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: continue if not data_equal(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) @@ -134,7 +140,7 @@ class Event(dict): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = ConfigParser.SafeConfigParser() + parser = configparser.SafeConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -193,7 +199,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = ConfigParser.SafeConfigParser() + parser_event = configparser.SafeConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -207,7 +213,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = ConfigParser.SafeConfigParser() + parser_base = configparser.SafeConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') @@ -322,9 +328,9 @@ def run_tests(options): for f in glob.glob(options.test_dir + '/' + options.test): try: Test(f, options).run() - except Unsup, obj: + except Unsup as obj: log.warning("unsupp %s" % obj.getMsg()) - except Notest, obj: + except Notest as obj: log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): @@ -363,7 +369,7 @@ def main(): parser.add_option("-p", "--perf", action="store", type="string", dest="perf") parser.add_option("-v", "--verbose", - action="count", dest="verbose") + default=0, action="count", dest="verbose") options, args = parser.parse_args() if args: @@ -373,7 +379,7 @@ def main(): setup_log(options.verbose) if not options.test_dir: - print 'FAILED no -d option specified' + print('FAILED no -d option specified') sys.exit(-1) if not options.test: @@ -382,8 +388,8 @@ def main(): try: run_tests(options) - except Fail, obj: - print "FAILED %s" % obj.getMsg(); + except Fail as obj: + print("FAILED %s" % obj.getMsg()) sys.exit(-1) sys.exit(0) diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 5f8501c68da4..5cbba70bcdd0 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return -1; } - is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED); + is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED); if (should_be_signed && !is_signed) { pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", evsel->name, name, is_signed, should_be_signed); diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 89512504551b..39c0004f2886 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module) } PM.run(*Module); - return std::move(Buffer); + return Buffer; } } diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 93f74d8d3cdd..42c3e5a229d2 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; -char *perf_mem_events__name(int i) +char * __weak perf_mem_events__name(int i) { if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66a84d5846c8..dca7dfae69ad 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -19,6 +19,20 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +#ifndef ELF32_ST_VISIBILITY +#define ELF32_ST_VISIBILITY(o) ((o) & 0x03) +#endif + +/* For ELF64 the definitions are the same. */ +#ifndef ELF64_ST_VISIBILITY +#define ELF64_ST_VISIBILITY(o) ELF32_ST_VISIBILITY (o) +#endif + +/* How to extract information held in the st_other field. */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(val) ELF64_ST_VISIBILITY (val) +#endif + typedef Elf64_Nhdr GElf_Nhdr; #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT @@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +static inline uint8_t elf_sym__visibility(const GElf_Sym *sym) +{ + return GELF_ST_VISIBILITY(sym->st_other); +} + #ifndef STT_GNU_IFUNC #define STT_GNU_IFUNC 10 #endif @@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) return elf_sym__type(sym) == STT_NOTYPE && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; + sym->st_shndx != SHN_ABS && + elf_sym__visibility(sym) != STV_HIDDEN && + elf_sym__visibility(sym) != STV_INTERNAL; } static bool elf_sym__filter(GElf_Sym *sym) |