qiurui
/
Centos-kernel-stream-9
mirror of https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

tools/power turbostat: Allow Zero return value for some RAPL registers 

JIRA: https://issues.redhat.com/browse/RHEL-86839

commit b312d880fb462d4759396950865ec914de9d253c
Author: Zhang Rui <rui.zhang@intel.com>
Date:   Sat Feb 8 10:44:26 2025 +0800

    tools/power turbostat: Allow Zero return value for some RAPL registers

    turbostat aborted with below messages on a dual-package system,

       turbostat: turbostat.c:3744: rapl_counter_accumulate: Assertion `dst->unit == src->unit' failed.
       Aborted

    This is because
    1. the MSR_DRAM_PERF_STATUS returns Zero for one package, and non-Zero
       for another package
    2. probe_msr() treats Zero return value as a failure so this feature is
       enabled on one package, and disabled for another package.
    3. turbostat aborts because the feature is invalid on some package

    Unlike the RAPL energy counter registers, MSR_DRAM_PERF_STATUS can
    return Zero value, and this should not be treated as a failure.

    Fix the problem by allowing Zero return value for RAPL registers other
    than the energy counters.

    Fixes: 7c6fee25bdf5 ("tools/power turbostat: Check for non-zero value when MSR probing")
    Reported-by: Artem Bityutskiy <artem.bityutskiy@intel.com>
    Signed-off-by: Zhang Rui <rui.zhang@intel.com>
    Signed-off-by: Len Brown <len.brown@intel.com>

Signed-off-by: David Arcari <darcari@redhat.com>
This commit is contained in:
David Arcari 2025-04-10 13:49:40 -04:00
parent 2a35850915
commit 647ac94d4c
1 changed files with 18 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
tools/power/x86/turbostat/turbostat.c
View File

@ -2211,7 +2211,7 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
return 0;
}
int probe_msr(int cpu, off_t offset)
int probe_rapl_msr(int cpu, off_t offset, int index)
{
ssize_t retval;
unsigned long long value;
@ -2220,13 +2220,22 @@ int probe_msr(int cpu, off_t offset)
retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset);
/*
* Expect MSRs to accumulate some non-zero value since the system was powered on.
* Treat zero as a read failure.
*/
if (retval != sizeof(value) || value == 0)
/* if the read failed, the probe fails */
if (retval != sizeof(value))
return 1;
/* If an Energy Status Counter MSR returns 0, the probe fails */
switch (index) {
case RAPL_RCI_INDEX_ENERGY_PKG:
case RAPL_RCI_INDEX_ENERGY_CORES:
case RAPL_RCI_INDEX_DRAM:
case RAPL_RCI_INDEX_GFX:
case RAPL_RCI_INDEX_ENERGY_PLATFORM:
if (value == 0)
return 1;
}
/* PKG,DRAM_PERF_STATUS MSRs, can return any value */
return 0;
}
@ -7907,7 +7916,7 @@ void rapl_perf_init(void)
rci->flags[cai->rci_index] = cai->flags;
/* Use MSR for this counter */
} else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
} else if (!no_msr && cai->msr && probe_rapl_msr(cpu, cai->msr, cai->rci_index) == 0) {
rci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
rci->msr[cai->rci_index] = cai->msr;
rci->msr_mask[cai->rci_index] = cai->msr_mask;
@ -8045,7 +8054,7 @@ void msr_perf_init_(void)
cai->present = true;
/* User MSR for this counter */
} else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
} else if (!no_msr && cai->msr && probe_rapl_msr(cpu, cai->msr, cai->rci_index) == 0) {
cci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
cci->msr[cai->rci_index] = cai->msr;
cci->msr_mask[cai->rci_index] = cai->msr_mask;
@ -8159,7 +8168,7 @@ void cstate_perf_init_(bool soft_c1)
/* User MSR for this counter */
} else if (!no_msr && cai->msr && pkg_cstate_limit >= cai->pkg_cstate_limit
&& probe_msr(cpu, cai->msr) == 0) {
&& probe_rapl_msr(cpu, cai->msr, cai->rci_index) == 0) {
cci->source[cai->rci_index] = COUNTER_SOURCE_MSR;
cci->msr[cai->rci_index] = cai->msr;
}