mirror of
https://github.com/torvalds/linux.git
synced 2026-05-12 16:18:45 +02:00
Turbostat Fixes
Fix a memory allocation issue that could corrupt output values or SEGV Fix a perf initilization issue that could exit on some HW + kernels. Minor fixes. -----BEGIN PGP SIGNATURE----- iQJIBAABCgAyFiEE67dNfPFP+XUaA73mB9BFOha3NhcFAmnY/PkUHGxlbi5icm93 bkBpbnRlbC5jb20ACgkQB9BFOha3NhcTIA//QsbmJV7qddOe/kOhS7izRyVjuaLQ QIyIrSLSa5+49oT4uRhZxuzDm6N6zVykFf+yxK5E2TSf+JfvzfwjZJQEgUPqHtkt vietoJheI4voMgmDQk39oxQmYyxmXuD3TRgvY+EN+QEIuWFA3/J9YaOulQMICrRy TX3juoZ3mxUpO8LC6+t3Yd8Kl1JEl3cKj3LdX7cMIchLM2cSTlbVFGSP0y5f0mu/ m54+JLSeSCFyqfin8rkgLYar8+AIIrHVak57rQ3qKBUOfoJlMaJEgXC4/sKdEzAW zKld2cFfzzXd2LnShN9Su7L9VCF09POKpD7P9bk9rDcp/MfsOmlKRctRvnY4T7Bq si+AflAYzYtHlq0LQbw2tHsKLFnqIJziDzz+YHl9UxcK0X17Gkp32NSQOX7Djvdu g/HDMHudnyoq0dAObieQgevYAWYmfKTNeQpJk+d+27X9HTzNXCDe70D774+DhM73 ViDU5zPrFBc1Z9ScQmgbe4z2N3MvzWGkodJRseb1v44ClH+Z6sCG4RYxYpxj0Zyu 0rR5GBb6ymuDUAQYEVuk2/F05bgmp3oXhoaddC+bO115XGEfe9sR7PBk3p9LYSM5 KirznZsjE8qI8GUXdL4EztTtIUJ5sx9CWb5FqP6k7XovrPCoMhSsbbo0vUbLCK4C eh0+iPh3sAf0NZs= =xJLy -----END PGP SIGNATURE----- Merge tag 'turbostat-fixes-for-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux Pull turbostat fixes from Len Brown: - Fix a memory allocation issue that could corrupt output values or SEGV - Fix a perf initilization issue that could exit on some HW + kernels - Minor fixes * tag 'turbostat-fixes-for-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux: tools/power turbostat: Allow execution to continue after perf_l2_init() failure tools/power turbostat: Fix delimiter bug in print functions tools/power turbostat: Fix --show/--hide for individual cpuidle counters tools/power turbostat: Fix incorrect format variable tools/power turbostat: Consistently use print_float_value() tools/power/turbostat: Fix microcode patch level output for AMD/Hygon tools/power turbostat: Eliminate unnecessary data structure allocation tools/power turbostat: Fix swidle header vs data display tools/power turbostat: Fix illegal memory access when SMT is present and disabled
This commit is contained in:
Linus Torvalds
commit
96463e4e02
|
|
@ -2409,7 +2409,7 @@ struct topo_params {
|
|||
int max_l3_id;
|
||||
int max_node_num;
|
||||
int nodes_per_pkg;
|
||||
int cores_per_node;
|
||||
int cores_per_pkg;
|
||||
int threads_per_core;
|
||||
} topo;
|
||||
|
||||
|
|
@ -2837,30 +2837,29 @@ static inline int print_name(int width, int *printed, char *delim, char *name, e
|
|||
UNUSED(type);
|
||||
|
||||
if (format == FORMAT_RAW && width >= 64)
|
||||
return (sprintf(outp, "%s%-8s", (*printed++ ? delim : ""), name));
|
||||
return (sprintf(outp, "%s%-8s", ((*printed)++ ? delim : ""), name));
|
||||
else
|
||||
return (sprintf(outp, "%s%s", (*printed++ ? delim : ""), name));
|
||||
return (sprintf(outp, "%s%s", ((*printed)++ ? delim : ""), name));
|
||||
}
|
||||
|
||||
static inline int print_hex_value(int width, int *printed, char *delim, unsigned long long value)
|
||||
{
|
||||
if (width <= 32)
|
||||
return (sprintf(outp, "%s%08x", (*printed++ ? delim : ""), (unsigned int)value));
|
||||
return (sprintf(outp, "%s%08x", ((*printed)++ ? delim : ""), (unsigned int)value));
|
||||
else
|
||||
return (sprintf(outp, "%s%016llx", (*printed++ ? delim : ""), value));
|
||||
return (sprintf(outp, "%s%016llx", ((*printed)++ ? delim : ""), value));
|
||||
}
|
||||
|
||||
static inline int print_decimal_value(int width, int *printed, char *delim, unsigned long long value)
|
||||
{
|
||||
if (width <= 32)
|
||||
return (sprintf(outp, "%s%d", (*printed++ ? delim : ""), (unsigned int)value));
|
||||
else
|
||||
return (sprintf(outp, "%s%-8lld", (*printed++ ? delim : ""), value));
|
||||
UNUSED(width);
|
||||
|
||||
return (sprintf(outp, "%s%lld", ((*printed)++ ? delim : ""), value));
|
||||
}
|
||||
|
||||
static inline int print_float_value(int *printed, char *delim, double value)
|
||||
{
|
||||
return (sprintf(outp, "%s%0.2f", (*printed++ ? delim : ""), value));
|
||||
return (sprintf(outp, "%s%0.2f", ((*printed)++ ? delim : ""), value));
|
||||
}
|
||||
|
||||
void print_header(char *delim)
|
||||
|
|
@ -3469,7 +3468,7 @@ int format_counters(PER_THREAD_PARAMS)
|
|||
for (i = 0, pp = sys.perf_tp; pp; ++i, pp = pp->next) {
|
||||
if (pp->format == FORMAT_RAW)
|
||||
outp += print_hex_value(pp->width, &printed, delim, t->perf_counter[i]);
|
||||
else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE)
|
||||
else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE)
|
||||
outp += print_decimal_value(pp->width, &printed, delim, t->perf_counter[i]);
|
||||
else if (pp->format == FORMAT_PERCENT) {
|
||||
if (pp->type == COUNTER_USEC)
|
||||
|
|
@ -3490,12 +3489,12 @@ int format_counters(PER_THREAD_PARAMS)
|
|||
|
||||
case PMT_TYPE_XTAL_TIME:
|
||||
value_converted = pct(value_raw / crystal_hz, interval_float);
|
||||
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
|
||||
outp += print_float_value(&printed, delim, value_converted);
|
||||
break;
|
||||
|
||||
case PMT_TYPE_TCORE_CLOCK:
|
||||
value_converted = pct(value_raw / tcore_clock_freq_hz, interval_float);
|
||||
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
|
||||
outp += print_float_value(&printed, delim, value_converted);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -3539,7 +3538,7 @@ int format_counters(PER_THREAD_PARAMS)
|
|||
for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) {
|
||||
if (pp->format == FORMAT_RAW)
|
||||
outp += print_hex_value(pp->width, &printed, delim, c->perf_counter[i]);
|
||||
else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE)
|
||||
else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE)
|
||||
outp += print_decimal_value(pp->width, &printed, delim, c->perf_counter[i]);
|
||||
else if (pp->format == FORMAT_PERCENT)
|
||||
outp += print_float_value(&printed, delim, pct(c->perf_counter[i], tsc));
|
||||
|
|
@ -3695,7 +3694,7 @@ int format_counters(PER_THREAD_PARAMS)
|
|||
outp += print_hex_value(pp->width, &printed, delim, p->perf_counter[i]);
|
||||
else if (pp->type == COUNTER_K2M)
|
||||
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->perf_counter[i] / 1000);
|
||||
else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE)
|
||||
else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE)
|
||||
outp += print_decimal_value(pp->width, &printed, delim, p->perf_counter[i]);
|
||||
else if (pp->format == FORMAT_PERCENT)
|
||||
outp += print_float_value(&printed, delim, pct(p->perf_counter[i], tsc));
|
||||
|
|
@ -9122,10 +9121,13 @@ void process_cpuid()
|
|||
cpuid_has_hv = ecx_flags & (1 << 31);
|
||||
|
||||
if (!no_msr) {
|
||||
if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
|
||||
if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) {
|
||||
warnx("get_msr(UCODE)");
|
||||
else
|
||||
} else {
|
||||
ucode_patch_valid = true;
|
||||
if (!authentic_amd && !hygon_genuine)
|
||||
ucode_patch >>= 32;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -9139,7 +9141,7 @@ void process_cpuid()
|
|||
if (!quiet) {
|
||||
fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)", family, model, stepping, family, model, stepping);
|
||||
if (ucode_patch_valid)
|
||||
fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
|
||||
fprintf(outf, " microcode 0x%x", (unsigned int)ucode_patch);
|
||||
fputc('\n', outf);
|
||||
|
||||
fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level);
|
||||
|
|
@ -9403,13 +9405,13 @@ void perf_l2_init(void)
|
|||
if (!is_hybrid) {
|
||||
fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.uniform, perf_model_support->first.refs, -1, PERF_FORMAT_GROUP);
|
||||
if (fd_l2_percpu[cpu] == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.refs);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.refs);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
retval = open_perf_counter(cpu, perf_pmu_types.uniform, perf_model_support->first.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
|
||||
if (retval == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.hits);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.hits);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
|
|
@ -9418,39 +9420,39 @@ void perf_l2_init(void)
|
|||
if (perf_pcore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_pcore_set)) {
|
||||
fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.pcore, perf_model_support->first.refs, -1, PERF_FORMAT_GROUP);
|
||||
if (fd_l2_percpu[cpu] == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.refs);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.refs);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
retval = open_perf_counter(cpu, perf_pmu_types.pcore, perf_model_support->first.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
|
||||
if (retval == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.hits);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.hits);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
} else if (perf_ecore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_ecore_set)) {
|
||||
fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.ecore, perf_model_support->second.refs, -1, PERF_FORMAT_GROUP);
|
||||
if (fd_l2_percpu[cpu] == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->second.refs);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.ecore, perf_model_support->second.refs);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
retval = open_perf_counter(cpu, perf_pmu_types.ecore, perf_model_support->second.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
|
||||
if (retval == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->second.hits);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.ecore, perf_model_support->second.hits);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
} else if (perf_lcore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_lcore_set)) {
|
||||
fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.lcore, perf_model_support->third.refs, -1, PERF_FORMAT_GROUP);
|
||||
if (fd_l2_percpu[cpu] == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->third.refs);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.lcore, perf_model_support->third.refs);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
retval = open_perf_counter(cpu, perf_pmu_types.lcore, perf_model_support->third.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
|
||||
if (retval == -1) {
|
||||
err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->third.hits);
|
||||
warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.lcore, perf_model_support->third.hits);
|
||||
free_fd_l2_percpu();
|
||||
return;
|
||||
}
|
||||
|
|
@ -9634,9 +9636,9 @@ void topology_probe(bool startup)
|
|||
topo.max_core_id = max_core_id; /* within a package */
|
||||
topo.max_package_id = max_package_id;
|
||||
|
||||
topo.cores_per_node = max_core_id + 1;
|
||||
topo.cores_per_pkg = max_core_id + 1;
|
||||
if (debug > 1)
|
||||
fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_node);
|
||||
fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_pkg);
|
||||
if (!summary_only)
|
||||
BIC_PRESENT(BIC_Core);
|
||||
|
||||
|
|
@ -9701,14 +9703,13 @@ void allocate_counters_1(struct counters *counters)
|
|||
void allocate_counters(struct counters *counters)
|
||||
{
|
||||
int i;
|
||||
int num_cores = topo.cores_per_node * topo.nodes_per_pkg * topo.num_packages;
|
||||
int num_threads = topo.threads_per_core * num_cores;
|
||||
int num_cores = topo.cores_per_pkg * topo.num_packages;
|
||||
|
||||
counters->threads = calloc(num_threads, sizeof(struct thread_data));
|
||||
counters->threads = calloc(topo.max_cpu_num + 1, sizeof(struct thread_data));
|
||||
if (counters->threads == NULL)
|
||||
goto error;
|
||||
|
||||
for (i = 0; i < num_threads; i++)
|
||||
for (i = 0; i < topo.max_cpu_num + 1; i++)
|
||||
(counters->threads)[i].cpu_id = -1;
|
||||
|
||||
counters->cores = calloc(num_cores, sizeof(struct core_data));
|
||||
|
|
@ -11284,6 +11285,14 @@ void probe_cpuidle_residency(void)
|
|||
}
|
||||
}
|
||||
|
||||
static bool cpuidle_counter_wanted(char *name)
|
||||
{
|
||||
if (is_deferred_skip(name))
|
||||
return false;
|
||||
|
||||
return DO_BIC(BIC_cpuidle) || is_deferred_add(name);
|
||||
}
|
||||
|
||||
void probe_cpuidle_counts(void)
|
||||
{
|
||||
char path[64];
|
||||
|
|
@ -11293,7 +11302,7 @@ void probe_cpuidle_counts(void)
|
|||
int min_state = 1024, max_state = 0;
|
||||
char *sp;
|
||||
|
||||
if (!DO_BIC(BIC_cpuidle))
|
||||
if (!DO_BIC(BIC_cpuidle) && !deferred_add_index)
|
||||
return;
|
||||
|
||||
for (state = 10; state >= 0; --state) {
|
||||
|
|
@ -11308,12 +11317,6 @@ void probe_cpuidle_counts(void)
|
|||
|
||||
remove_underbar(name_buf);
|
||||
|
||||
if (!DO_BIC(BIC_cpuidle) && !is_deferred_add(name_buf))
|
||||
continue;
|
||||
|
||||
if (is_deferred_skip(name_buf))
|
||||
continue;
|
||||
|
||||
/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
|
||||
sp = strchr(name_buf, '-');
|
||||
if (!sp)
|
||||
|
|
@ -11328,16 +11331,19 @@ void probe_cpuidle_counts(void)
|
|||
* Add 'C1+' for C1, and so on. The 'below' sysfs file always contains 0 for
|
||||
* the last state, so do not add it.
|
||||
*/
|
||||
|
||||
*sp = '+';
|
||||
*(sp + 1) = '\0';
|
||||
sprintf(path, "cpuidle/state%d/below", state);
|
||||
add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
|
||||
if (cpuidle_counter_wanted(name_buf)) {
|
||||
sprintf(path, "cpuidle/state%d/below", state);
|
||||
add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
|
||||
}
|
||||
}
|
||||
|
||||
*sp = '\0';
|
||||
sprintf(path, "cpuidle/state%d/usage", state);
|
||||
add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
|
||||
if (cpuidle_counter_wanted(name_buf)) {
|
||||
sprintf(path, "cpuidle/state%d/usage", state);
|
||||
add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
|
||||
}
|
||||
|
||||
/*
|
||||
* The 'above' sysfs file always contains 0 for the shallowest state (smallest
|
||||
|
|
@ -11346,8 +11352,10 @@ void probe_cpuidle_counts(void)
|
|||
if (state != min_state) {
|
||||
*sp = '-';
|
||||
*(sp + 1) = '\0';
|
||||
sprintf(path, "cpuidle/state%d/above", state);
|
||||
add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
|
||||
if (cpuidle_counter_wanted(name_buf)) {
|
||||
sprintf(path, "cpuidle/state%d/above", state);
|
||||
add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user