| /tools/testing/selftests/sgx/ |
| A D | test_encl_bootstrap.S | 13 .fill 1, 8, 0 # STATE (set by CPU) 16 .fill 1, 4, 0 # CSSA (set by CPU) 19 .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) 27 .fill 1, 8, 0 # STATE (set by CPU) 30 .fill 1, 4, 0 # CSSA (set by CPU) 33 .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) 45 # TCS #2. First make it relative by substracting __encl_base and 63 # simplify the code by not initializing ABI registers on entry or 67 # Prepare EEXIT target by popping the address of the instruction after
|
| /tools/testing/selftests/arm64/fp/ |
| A D | README | 20 The test runs until killed by the user. 30 Terminated by signal 15, no error, iterations=9467, signals=1014 33 Terminated by signal 15, no error, iterations=9448, signals=1028 36 Terminated by signal 15, no error, iterations=9436, signals=1039 39 Terminated by signal 15, no error, iterations=9421, signals=1039 42 Terminated by signal 15, no error, iterations=9403, signals=1039 45 Terminated by signal 15, no error, iterations=9385, signals=1036 48 Terminated by signal 15, no error, iterations=9376, signals=1039 51 Terminated by signal 15, no error, iterations=9361, signals=1039 54 Terminated by signal 15, no error, iterations=9350, signals=1039
|
| /tools/memory-model/scripts/ |
| A D | README | 36 followed by "--" followed by pathnames starting from the current 44 provided instead for use by other scripts. 57 instead for use by other scripts. 68 provided instead for use by other scripts. 74 provided instead for use by other scripts. 93 # Compares results to those produced by initlitmushist.sh, 104 an error in the original LKMM version that is fixed by the patch will 105 be reported both as a mismatch by checklitmushist.sh and as an error 106 by checkghlitmus.sh. One exception to this rule of thumb is when the
|
| /tools/memory-model/litmus-tests/ |
| A D | README | 11 from a given variable followed by a write to that same variable 16 to a given variable followed by a read from that same variable 28 variable by a different process? This litmus test is forbidden 29 by LKMM's propagation rule. 36 variable by a different process? 39 Tests whether the ordering provided by a lock-protected S 75 in one process, and use an acquire load followed by a pair of 80 acquire load followed by a pair of spin_is_locked() calls 85 and the first access of reader process protected by a lock. 95 and the second access of reader process protected by a lock. [all …]
|
| A D | S+poonceonces.litmus | 8 * is replaced by WRITE_ONCE() and the smp_load_acquire() replaced by
|
| A D | ISA2+poonceonces.litmus | 8 * smp_store_release() invocations are replaced by WRITE_ONCE() and all 9 * of the smp_load_acquire() invocations are replaced by READ_ONCE()?
|
| A D | Z6.0+pooncelock+pooncelock+pombonce.litmus | 6 * This example demonstrates that a pair of accesses made by different 8 * seen as ordered by a third process not holding that lock.
|
| A D | LB+unlocklockonceonce+poacquireonce.litmus | 8 * critical sections are protected by different locks. Note: Even when a 10 * the viewpoint of another CPU (the kind of reordering allowed by TSO).
|
| /tools/testing/selftests/kselftest_harness/ |
| A D | harness-selftest.expected | 13 # standalone_fail: Test terminated by assertion 24 # signal_fail: Test terminated by assertion 41 # fail: Test terminated by assertion 47 # timeout: Test terminated by timeout 60 # pass: Test terminated by assertion
|
| /tools/perf/Documentation/ |
| A D | perf-kvm.txt | 47 for use by perf report. As buildid is read from /sys/kernel/notes in os, then 101 Sorting key. Possible values: sample (default, sort by samples 102 number), percent_sample (sort by sample percentage), time 103 (sort by average time), precent_time (sort by time percentage), 104 max_t (sort by maximum time), min_t (sort by minimum time), mean_t 105 (sort by mean time). 141 Sorting key. Possible values: sample (default, sort by samples 142 number), time (sort by average time).
|
| A D | callchain-overhead-calculation.txt | 5 wall-clock overhead). The 'self' overhead is simply calculated by 10 The 'children' overhead is calculated by adding all period values of 105 Since v3.16 the 'children' overhead is shown by default and the output 106 is sorted by its values. The 'children' overhead is disabled by 107 specifying --no-children option on the command line or by adding
|
| A D | db-export.txt | 20 backward and forward compatibility, by following some simple rules: 30 backward compatibility by testing for the presence of new tables and columns 34 script will continue to work with new versions of perf) by accepting a variable 40 or optional features by checking for the existence and value of script global
|
| A D | perf-sched.txt | 47 via perf sched record. (this is done by starting up mockup threads 114 sort by key(s): runtime, switch, avg, max 115 by default it's sorted by "avg ,max ,switch ,runtime". 136 time is printed and is represented by '*-' for the given 173 Show only a summary of scheduling by thread with min, max, and average 178 Show all scheduling events followed by a summary by thread with min, 186 Show visual aid for sched switches by CPU: 'i' marks idle time, 227 by a task waiting on a runqueue but not getting the chance to run there
|
| A D | perf.data-file-format.txt | 5 This document describes the on-disk perf.data format, generated by perf record 6 or perf inject and consumed by the other perf tools. 79 assigned by the linker to an executable. 425 covered by HEADER_CPU_PMU_CAPS). Note that hybrid cpu pmu 452 describing events. This matches the format generated by the kernel. 469 by an ID. This can be either through the PERF_SAMPLE_ID or the 473 IDENTIFIER is only supported by newer Linux kernels. 554 Defines auxtrace data. Followed by the actual data. The contents of 557 by the CPU. 644 An array bound by the perf_file_section size. [all …]
|
| /tools/power/cpupower/bindings/python/ |
| A D | README | 8 * If you are building completely from upstream; please install libcpupower by 17 installed on your machine by checking the SWIG changelog on their website. 33 Install SWIG and the Python development files provided by your distribution. 35 Build the object files for libcpupower by running make in the cpupower 70 by default. You do not need to install cpupower to use the SWIG bindings.
|
| /tools/testing/selftests/rcutorture/doc/ |
| A D | TINY_RCU.txt | 19 In common code tested by TREE_RCU test cases. 38 All forced by CONFIG_TINY_RCU.
|
| /tools/scripts/ |
| A D | utilities.mak | 50 # in an `awk' program that is delimited by shell 67 # delimited by shell single-quotes, so be wary 72 # overcome by putting a space between `{' and `gsub'). 83 # embedding in a shell string that is delimited by 108 # At least GNU make gets confused by expanding a newline 113 # This function avoids the problem by producing a string 141 # (It's necessary to use `sh -c' because GNU make messes up by 151 # (It's necessary to use `sh -c' because GNU make messes up by 163 # the `command -v' is defined by POSIX, but it's not 166 # by the presence of a leading `/'.
|
| /tools/memory-model/Documentation/ |
| A D | glossary.txt | 8 based on the value returned by an earlier load, an "address 19 from the value returned by the rcu_dereference() on line 2, the 35 When an acquire load returns the value stored by a release store 55 of a value computed from a value returned by an earlier load, 64 fragile, and can be easily destroyed by optimizing compilers. 84 are all equal to zero is forbidden by LKMM. 89 on the value returned by an earlier load, a "data dependency" 97 fragile and can be easily destroyed by optimizing compilers. 106 too late to affect the value returned by another CPU's 135 Memory barriers thus tend to come in pairs, one executed by [all …]
|
| A D | locking.txt | 4 otherwise protected by a lock. 10 CPU holding a given lock sees any changes previously seen or made by any 24 or made by any CPU before it previously released that same lock. 27 given lock sees all changes made by any CPU during the time that CPU was 59 lock will not see any changes that will be made by any CPU after it 61 illustrated by the following litmus test: 145 that the ordering provided by each actually takes effect. Again, a 153 Ordering Provided by a Lock to CPUs Not Holding That Lock 156 It is not necessarily the case that accesses ordered by locking will be 157 seen as ordered by CPUs not holding that lock. Consider this example: [all …]
|
| /tools/net/sunrpc/xdrgen/ |
| A D | README | 6 SunRPC programs are typically specified using a language defined by 20 However, it is code that is repetitive and tedious to write by hand. 22 The C code generated by rpcgen makes extensive use of the facilities 38 XDR code by hand will make a measurable performance different. 54 These dependencies are typically packaged by Linux distributions: 69 specification can be derived by feeding a .txt copy of the RFC to 90 or may be used as a guide for implementing these routines by hand. 114 language. The grammar has been adapted for use by the Python Lark 179 by hand, a pragma can specify that the procedure's encoder and 193 are used only by excluded procedure. [all …]
|
| /tools/testing/selftests/arm64/signal/ |
| A D | README | 11 - The above mentioned ops are configurable on a test-by-test basis: each test 16 by receiving some kind of fatal signal from the Kernel, so it's safer 36 - Most of these tests are successfully passing if the process gets killed by 51 - a sanity mechanism to be used in 'fake_sigreturn_'-alike tests: enabled by 57 - some fatal signal sent by the Kernel to the test process
|
| /tools/testing/selftests/coredump/ |
| A D | README.rst | 9 `coredump` dumps the memory to the file named `core`, but this behavior can be changed by writing a 11 user-space program by writing the pipe symbol (`|`) followed by the command to be executed to 42 This test detects problem with reading `kstkesp` during coredump by doing the following:
|
| /tools/perf/scripts/perl/bin/ |
| A D | rw-by-pid-report | 3 perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-pid.pl
|
| A D | rw-by-file-report | 10 perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-file.pl $comm
|
| /tools/power/pm-graph/config/ |
| A D | cgskip.txt | 6 # the callgraph html file size by treating these functions 7 # as leaves with no child calls. It can be editted by
|