| /tools/perf/util/ |
| D | genelf_debug.c | 47 buffer_ext_dump(struct buffer_ext *be, const char *msg) in buffer_ext_dump() argument
51 for (i = 0 ; i < be->cur_pos; i++) in buffer_ext_dump()
52 warnx("%4zu 0x%02x", i, (((char *)be->data)[i]) & 0xff); in buffer_ext_dump()
56 buffer_ext_add(struct buffer_ext *be, void *addr, size_t sz) in buffer_ext_add() argument
59 size_t be_sz = be->max_sz; in buffer_ext_add()
62 if ((be->cur_pos + sz) < be_sz) { in buffer_ext_add()
63 memcpy(be->data + be->cur_pos, addr, sz); in buffer_ext_add()
64 be->cur_pos += sz; in buffer_ext_add()
73 tmp = realloc(be->data, be_sz); in buffer_ext_add()
77 be->data = tmp; in buffer_ext_add()
[all …]
|
| D | trace-event.c | 42 int be = traceevent_host_bigendian(); in trace_event__init2() local
50 pevent_set_file_bigendian(pevent, be); in trace_event__init2()
51 pevent_set_host_bigendian(pevent, be); in trace_event__init2()
|
| D | python-ext-sources | 4 # Each source file must be placed on its own line so that it can be
|
| /tools/perf/Documentation/ |
| D | perf-list.txt | 15 This command displays the symbolic event types which can be selected in the
33 more modifiers. Modifiers allow the user to restrict the events to be
47 The 'p' modifier can be used for specifying how precise the instruction
48 address should be. The 'p' modifier can be specified multiple times:
75 it can be encoded in a per processor specific way.
82 Note: Only the following bit fields can be set in x86 counter
84 OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT
98 raw encoding of 0x1A8 can be used:
113 The available PMUs and their raw parameters can be listed with
118 be specified as
[all …]
|
| D | perf-config.txt | 38 The file '$(sysconfdir)/perfconfig' can be used to
43 can be used to tell the command to read from or write to only that location.
50 begins. Each variable must be in a section, and have the form
58 newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
99 # Format can be man, info, web or html
168 Subcommands that can be configured here are 'top', 'report' and 'annotate'.
174 will make the TUI be the default for the 'top' subcommand. Those will be
180 content based identifier that, if available, will be inserted in a
186 and /proc/kcore files to be used at analysis time.
188 The buildid.dir variable can be used to either change this directory
[all …]
|
| D | perf-record.txt | 19 This file can then be inspected later on, using 'perf report'.
29 Select the PMU event. Selection can be:
49 These params can be used to overload default config values per event.
61 the value set by the params will be overridden.
78 be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range,
86 Each event is separated by commas and the group should be quoted to
111 - 'filter': defines a region that will be traced.
121 the start address must be a current kernel memory address.
123 <start> can also be specified by providing the name of a symbol. If the
124 symbol name is not unique, it can be disambiguated by inserting #n where
[all …]
|
| D | perf-top.txt | 30 Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
40 Select the PMU event. Selection can be a symbolic event name
70 Number of mmap data pages (must be a power of two) or size
123 Specify output field - multiple keys can be specified in CSV format.
128 By default, every sort keys not specified in --field will be appended
171 and will be sorted on the data. It requires -g/--call-graph option
176 beyond the specified depth will be ignored. This is a trade-off
193 Filters can be applied by --comms, --dsos and/or --symbols options and
197 sum of shown entries will be always 100%. "absolute" means it retains
207 a long time, because the file may be huge. A time out is needed
[all …]
|
| D | itrace.txt | 15 can be specified in units of:
24 transactions events can be specified.
27 instructions or transactions events can be specified.
|
| D | perf-report.txt | 37 Show per-thread event counters. The input data file should be recorded
69 Sort histogram entries by given key(s) - multiple keys can be specified
75 - comm: command (name) of the task which can be read via /proc/<pid>/comm
84 DWARF debugging info must be provided.
147 field will be shown only for the event has the field. The event name
150 be shortened to 'switch' as long as it's not ambiguous. Also event can
151 be specified by its index (starting from 1) preceded by the '%'.
163 Specify output field - multiple keys can be specified in CSV format.
168 By default, every sort keys not specified in -F will be appended
201 parameters is not fixed so any parement can be given in an arbitraty order.
[all …]
|
| D | perf-buildid-cache.txt | 19 record it along with the buildid-cache, which will be used by perf-probe.
34 image. Note also that files "kallsyms" and "modules" must also be in the
36 permissions for root only. kcore will not be added if there is already a
54 older entires since those may be still needed for annotating old
56 exactly same build-id, that is replaced by new one. It can be used
|
| D | intel-bts.txt | 7 Intel BTS could be regarded as a predecessor to Intel PT and has some
15 documentation and consider that the PMU 'intel_bts' can usually be used in
17 recording must also be stipulated i.e. the --per-thread option for
52 This can be further controlled by option --itrace. The --itrace option is
76 This can be further controlled by new option --itrace exactly the same as
|
| D | intel-pt.txt | 19 Trace data must be 'decoded' which involves walking the object code and matching
31 the exact flow of software execution. Intel PT can be used to understand why
33 software does not have to be recompiled, so Intel PT works with debug or release
35 environments, or with self-modified code, a challenge. Also symbols need to be
49 more data than can possibly be processed.
62 accurate image a copy of /proc/kcore needs to be made under the same conditions
75 Because samples are synthesized after-the-fact, the sampling period can be
97 An interesting field that is not printed by default is 'flags' which can be
115 Another problem that will be experienced is decoder errors. They can be caused
161 Note that the default config must be overridden for each term i.e.
[all …]
|
| D | perf-buildid-list.txt | 16 tools can be used to fetch packages with matching symbol tables for use by
19 It can also be used to show the build id of the running kernel or in an ELF
|
| D | perf-trace.txt | 21 the other perf tools. Files can be generated using the 'perf record' command
23 Alternatively, 'perf trace record' can be used as a shortcut to
70 Number of mmap data pages (must be a power of two) or size
76 Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
138 beyond the specified depth will be ignored. Note that at this point
140 not limiting, the overhead of callchains needs to be set via the
151 below the specified depth will be ignored. Disabled by default.
158 because the file may be huge. A time out is needed in such cases.
177 Please be aware that duration is currently always 0 and doesn't reflect actual
178 time it took for fault to be handled!
|
| D | perf-annotate.txt | 16 code. If the object file has debug symbols then the source code will be
56 Print matching source lines (may be slow).
80 be provided as a comma-separated list with no space: 0,1. Ranges of
101 Skip symbols that cannot be annotated.
|
| /tools/testing/selftests/futex/ |
| D | README | 11 primitives. These can be used as is in user applications or can serve as
12 examples for system libraries. These will likely be added to either a new lib/
23 o Tests should be as self contained as is practical so as to facilitate sharing
27 o Where possible, any helper functions or other package-wide code shall be
36 Test output shall be easily parsable by both human and machine. Title and
46 # FIXME: Perhaps an " INFO: informational message" option would be
48 # there may be multiple ERROR or FAIL messages
|
| /tools/perf/ |
| D | design.txt | 10 thus be used to profile the code that runs on that CPU.
28 The syscall returns the new fd. The fd can be used via the normal
29 VFS system calls: read() can be used to read the counter, fcntl()
30 can be used to set the blocking mode, etc.
32 Multiple counters can be kept open at a time, and the counters
33 can be poll()ed.
52 pinned : 1, /* must always be on PMU */
113 although there may be variations (e.g., different CPUs might count
145 tracer is available, and event_id values can be obtained from
160 * Bits that can be set in hw_event.read_format to request that
[all …]
|
| /tools/objtool/Documentation/ |
| D | stack-validation.txt | 12 that stack traces can be reliable.
35 code and debug tools to be able to walk the stack to determine the
40 CONFIG_FRAME_POINTER. For some other architectures they may be
46 But for asm code, the frame setup instructions have to be written by
50 For stack traces based on frame pointers to be reliable, all
54 of the first function will be skipped on the stack trace.
88 functions honor CONFIG_FRAME_POINTER, no functions will ever[*] be
101 (CFI) metadata can be used to walk the stack. Unlike frame pointers,
103 performance and it can be reliable even when interrupts or exceptions
108 manually placed .cfi assembler macros to be scattered throughout the
[all …]
|
| /tools/power/cpupower/ |
| D | ToDo | 9 -> Is by design racy with BIOS, but could be added
10 with a --force option and some "be careful" messages
|
| /tools/iio/ |
| D | iio_utils.h | 50 unsigned be; member
64 unsigned *shift, uint64_t *mask, unsigned *be,
|
| /tools/testing/selftests/net/ |
| D | run_afpackettests | 4 echo $msg must be run as root >&2
|
| /tools/include/asm-generic/ |
| D | bitops.h | 22 #error only <linux/bitops.h> can be included directly
|
| /tools/perf/pmu-events/ |
| D | README | 11 - Regular files with '.json' extension in the name are assumed to be
15 to be a CSV file that maps a specific CPU to its set of PMU events.
22 should be placed in a separate JSON file - where the file name identifies
25 All the topic JSON files for a CPU model/family should be in a separate
90 build to succeed even if the PMU event aliases cannot be used.
100 The mapfile.csv format is expected to be:
120 CPUID is an arch-specific char string, that can be used
|
| /tools/power/cpupower/bench/ |
| D | README-BENCH | 19 throughput is, the worse the power savings will be, but the first should
35 will be run X time in a row (cycles):
56 takes on this machine and needs to be run in a loop using the performance
111 -x, --load-step=<long int> time to be added to load time, in us
112 -y, --sleep-step=<long int> time to be added to sleep time, in us
122 Due to the high priority, the application may not be responsible for some time.
|
| /tools/scripts/ |
| D | utilities.mak | 24 # produced during the expansion; this may not be
28 # something that won't be converted, so that the
29 # information can be recovered later with
51 # single-quotes, so be wary of the characters
67 # delimited by shell single-quotes, so be wary
71 # misinterpreted as a brace expansion; this can be
117 # If the text to be wordified contains a newline, then
|