| /tools/testing/selftests/splice/ |
| D | short_splice_read.sh | 94 full=$(cat "$filename")
100 two=$(echo "$full" | grep -m1 . | cut -c-2)
104 if ! do_splice "$filename" 4096 "$full" "full read" ; then
|
| /tools/perf/arch/powerpc/util/ |
| D | event.c | 18 weight.full = *array; in arch_perf_parse_sample_weight()
20 data->weight = weight.full; in arch_perf_parse_sample_weight()
|
| /tools/bpf/bpftool/Documentation/ |
| D | bpftool-feature.rst | 22 | **bpftool** **feature probe** [*COMPONENT*] [**full**] [**unprivileged**] [**macros** [**prefix**…
29 **bpftool feature probe** [**kernel**] [**full**] [**macros** [**prefix** *PREFIX*]]
38 and run all probes, the **full** keyword should be used.
62 **bpftool feature probe dev** *NAME* [**full**] [**macros** [**prefix** *PREFIX*]]
66 The keywords **full**, **macros** and **prefix** have the
|
| /tools/testing/selftests/kvm/x86_64/ |
| D | vmx_pmu_msrs_test.c | 34 unsigned int full; member
80 eax.full = entry_a_0->eax; in main()
122 entry_1_0->ecx = eax.full; in main()
|
| /tools/testing/selftests/bpf/progs/ |
| D | test_sysctl_prog.c | 34 #pragma clang loop unroll(full) in is_tcp_mem()
60 #pragma clang loop unroll(full) in sysctl_tcp_mem()
|
| D | test_skb_ctx.c | 12 #pragma clang loop unroll(full) in process()
|
| D | test_lwt_seg6local.c | 134 #pragma clang loop unroll(full) in is_valid_tlv_boundary()
305 #pragma clang loop unroll(full) in __encap_srh()
|
| D | xdping_kern.c | 120 #pragma clang loop unroll(full) in xdping_client()
|
| D | test_xdp.c | 142 #pragma clang loop unroll(full) in handle_ipv4()
|
| /tools/memory-model/litmus-tests/ |
| D | LB+fencembonceonce+ctrlonceonce.litmus | 9 * combination of a control dependency and a full memory barrier are enough
10 * to do the trick. (But the full memory barrier could be replaced with
|
| D | SB+fencembonceonces.litmus | 6 * This litmus test demonstrates that full memory barriers suffice to
|
| D | Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus | 13 * full barrier for each non-rf link. (Exceptions include some cases
|
| /tools/perf/arch/x86/util/ |
| D | event.c | 84 weight.full = *array; in arch_perf_parse_sample_weight()
86 data->weight = weight.full; in arch_perf_parse_sample_weight()
|
| /tools/perf/ |
| D | CREDITS | 30 The full history of the files can be found in the upstream Git commits.
|
| D | command-list.txt | 24 perf-probe mainporcelain full
|
| /tools/memory-model/Documentation/ |
| D | ordering.txt | 58 The Linux-kernel primitives that provide full ordering include:
60 o The smp_mb() full memory barrier.
67 First, the smp_mb() full memory barrier orders all of the CPU's prior
82 Second, some RMW atomic operations provide full ordering. These
88 When RMW atomic operations provide full ordering, they partition the
106 operations such as atomic_read() do not guarantee full ordering, and
113 Finally, RCU's grace-period primitives provide full ordering. These
122 to also rely on its additional full-memory-barrier semantics. Just please
132 full ordering for these primitives. One way to obtain full ordering on
141 x86, on which atomic_inc() provides full ordering all by itself.
[all …]
|
| D | recipes.txt | 40 be full sized. Variables that straddle cachelines or pages void
41 your full-ordering warranty, as do undersized accesses that load
361 control dependency paired with a full memory barrier:
378 This pairing of a control dependency in CPU0() with a full memory
384 control dependency on the kernel side and a full memory barrier on
399 and the store to data combined with the user's full memory barrier
477 first. Preserving order requires nothing less than full barriers:
495 values of 0, but providing both full barriers as shown above prevents
517 "if (@cond)". The full barriers prevent the undesirable outcome where
563 write-to-read links, then a full memory barrier is required
|
| D | cheatsheet.txt | 15 Successful full non-void RMW CP Y Y Y Y Y Y Y Y Y Y Y
|
| /tools/perf/util/ |
| D | expr.y | 23 %define api.pure full
|
| D | header.h | 136 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
|
| D | session.h | 133 void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
|
| /tools/lib/subcmd/ |
| D | parse-options.c | 699 static void print_option_help(const struct option *opts, int full) in print_option_help() argument
710 if (!full && (opts->flags & PARSE_OPT_HIDDEN)) in print_option_help()
862 const struct option *opts, int full, in usage_with_options_internal() argument
897 print_option_help(opts, full); in usage_with_options_internal()
|
| /tools/perf/Documentation/ |
| D | perf-c2c.txt | 97 --full-symbols::
98 Display full length of symbols.
120 output. But this approach is not full proof. There can be cases
|
| D | perf-script.txt | 237 When brstackinsn is specified the full assembler sequences of branch sequences for each sample
238 is printed. This is the full execution path leading to the sample. This is only supported when the
363 --full-source-path::
364 Show the full path for source files for srcline output.
490 output. But this approach is not full proof. There can be cases
|
| /tools/testing/selftests/tc-testing/ |
| D | README | 117 Run tdc.py -h to see the full list of available arguments.
127 -p PATH, --path PATH The full path to the tc executable to use
210 full command to be executed. This allows for last-minute adjustment
|