cstate support for CWF, LNL and PTL
Subsystems (2)
cover cstate support for CWF, LNL and PTL
This series resends three c-state patches that have been posted for a few months but have not yet received feedback.
On behalf of Rui, I’ve included his two patches here, so that all outstanding Intel c-state related patches can be reviewed together.
There are no code changes in this resend. Only the changelog in [PATCH 1/3] has been updated to note that the C1E counter can only be read via PMT.
Zhang Rui (2):
perf/x86/intel/cstate: Remove PC3 support from LunarLake perf/x86/intel/cstate: Add Pantherlake support
Zide Chen (1):
perf/x86/intel/cstate: Add Clearwater Forest support
arch/x86/events/intel/cstate.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
Signature · 1 line
2.51.1
PATCH RESEND 1/3 perf/x86/intel/cstate: Add Clearwater Forest support
Clearwater Forest is based on the Darkmont Atom microarchitecture. From the perspective of C-state residency profiling, it supports the same residency counters as Sierra Forest: CC1/CC6, PC2/PC6, and MC6.
Please note that the C1E residency counter can only be read via PMT, not MSR. Therefore, tools relying on the perf_event framework cannot access the C1E residency.
--- arch/x86/events/intel/cstate.c | 1 + 1 file changed, 1 insertion(+)
arch/x86/events/intel/cstate.c +1 -0
@@ -628,6 +628,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {X86_MATCH_VFM (INTEL_ATOM_GRACEMONT , &adl_cstates),X86_MATCH_VFM (INTEL_ATOM_CRESTMONT_X , &srf_cstates),X86_MATCH_VFM (INTEL_ATOM_CRESTMONT , &grr_cstates), +X86_MATCH_VFM (INTEL_ATOM_DARKMONT_X , &srf_cstates),X86_MATCH_VFM (INTEL_ICELAKE_L , &icl_cstates), X86_MATCH_VFM(INTEL_ICELAKE, &icl_cstates),
Signature · 1 line
2.51.1
[tip: perf/core] perf/x86/intel/cstate: Add Clearwater Forest support
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: e39b82f6cb0526c551d4651ba6d286b6b1f9e9c3 Gitweb: https://git.kernel.org/tip/e39b82f6cb0526c551d4651ba6d286b6b1f9e9c3 Author: Zide Chen <[email protected]> AuthorDate: Thu, 23 Oct 2025 15:37:51 -07:00 Committer: Peter Zijlstra <[email protected]> CommitterDate: Wed, 29 Oct 2025 10:29:53 +01:00
perf/x86/intel/cstate: Add Clearwater Forest support
Clearwater Forest is based on the Darkmont Atom microarchitecture.
Quoted 1 line
From the perspective of C-state residency profiling, it supports the
same residency counters as Sierra Forest: CC1/CC6, PC2/PC6, and MC6.
Please note that the C1E residency counter can only be read via PMT, not MSR. Therefore, tools relying on the perf_event framework cannot access the C1E residency.
--- arch/x86/events/intel/cstate.c | 1 + 1 file changed, 1 insertion(+)
arch/x86/events/intel/cstate.c +1 -0
@@ -628,6 +628,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {X86_MATCH_VFM (INTEL_ATOM_GRACEMONT , &adl_cstates),X86_MATCH_VFM (INTEL_ATOM_CRESTMONT_X , &srf_cstates),X86_MATCH_VFM (INTEL_ATOM_CRESTMONT , &grr_cstates), +X86_MATCH_VFM (INTEL_ATOM_DARKMONT_X , &srf_cstates),X86_MATCH_VFM (INTEL_ICELAKE_L , &icl_cstates), X86_MATCH_VFM(INTEL_ICELAKE, &icl_cstates),
Re: [PATCH RESEND 1/3] perf/x86/intel/cstate: Add Clearwater Forest support
In reply to Zide ChenQuoted 4 lines · Zide Chen
Clearwater Forest is based on the Darkmont Atom microarchitecture. From the perspective of C-state residency profiling, it supports the same residency counters as Sierra Forest: CC1/CC6, PC2/PC6, and MC6.
Quoted 8 lines
Please note that the C1E residency counter can only be read via PMT, not MSR. Therefore, tools relying on the
perf_eventframework cannot access the C1E residency.Cc Artem Bityutskiy <[email protected]>Reviewed-by Kan Liang <[email protected]>Signed-off-by Zhenyu Wang <[email protected]>Signed-off-by Zide Chen <[email protected]>
So, this is not a valid SOB chain: primary author should be the first SOB, or if it was co-developed, it should have the proper Co-developed-by tags.
Here I can see two possibilities:
(1) if Zhenyu Wang was the primary author, and Zide Chen reviewed, tested and submitted it upstream, then:
| From: Zide Chen <[email protected]>
| Subject: [PATCH 1/3] perf/x86/intel/cstate: Add Clearwater Forest support
From: Zhenyu Wang <[email protected]>
...
(I.e. add the extra From line as the first line of the changelog.)
(2) if it was co-developed, with Zhenyu Wang and Zide Chen having each written unique lines of code of their own that finally resulted in this submission, then:
| From: Zide Chen <[email protected]>
| Subject: [PATCH 1/3] perf/x86/intel/cstate: Add Clearwater Forest support
...
Which one was it? :-)
Thanks,
Ingo
Re: [PATCH RESEND 1/3] perf/x86/intel/cstate: Add Clearwater Forest support
Quoted 29 lines · Ingo Molnar
Quoted 4 lines · Zide Chen
Clearwater Forest is based on the Darkmont Atom microarchitecture. From the perspective of C-state residency profiling, it supports the same residency counters as Sierra Forest: CC1/CC6, PC2/PC6, and MC6.
Quoted 8 lines
Please note that the C1E residency counter can only be read via PMT, not MSR. Therefore, tools relying on the
perf_eventframework cannot access the C1E residency.Cc Artem Bityutskiy <[email protected]>Reviewed-by Kan Liang <[email protected]>Signed-off-by Zhenyu Wang <[email protected]>Signed-off-by Zide Chen <[email protected]>So, this is not a valid SOB chain: primary author should be the first SOB, or if it was co-developed, it should have the proper Co-developed-by tags.
Here I can see two possibilities:
(1) if Zhenyu Wang was the primary author, and Zide Chen reviewed, tested and submitted it upstream, then:
| From: Zide Chen <[email protected]>
| Subject: [PATCH 1/3] perf/x86/intel/cstate: Add Clearwater Forest support
Quoted 7 lines
From: Zhenyu Wang <[email protected]>
...Signed-off-by Zhenyu Wang <[email protected]>Signed-off-by Zide Chen <[email protected]>(I.e. add the extra From line as the first line of the changelog.)
Yes, that is the case.
Thank you very much for pointing this out! I will pay extra attention to the SoB chain going forward.
Quoted 19 lines
(2) if it was co-developed, with Zhenyu Wang and Zide Chen having each written unique lines of code of their own that finally resulted in this submission, then:
| From: Zide Chen <[email protected]>
| Subject: [PATCH 1/3] perf/x86/intel/cstate: Add Clearwater Forest support...
Co-developed-by Zide Chen <[email protected]>Signed-off-by Zide Chen <[email protected]>Co-developed-by Zhenyu Wang <[email protected]>Signed-off-by Zhenyu Wang <[email protected]>Which one was it? :-)
Thanks,
Ingo
PATCH RESEND 2/3 perf/x86/intel/cstate: Remove PC3 support from LunarLake
In reply to Zide ChenFrom: Zhang Rui <[email protected]>
LunarLake doesn't support Package C3. Remove the PC3 residency counter support from LunarLake.
--- arch/x86/events/intel/cstate.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
arch/x86/events/intel/cstate.c +1 -2
@@ -70,7 +70,7 @@* perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, -* ADL,RPL,MTL,ARL,LNL +* ADL,RPL,MTL,ARL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02
@@ -522,7 +522,6 @@ static const struct cstate_model lnl_cstates __initconst = { BIT(PERF_CSTATE_CORE_C7_RES), .pkg_events =BIT (PERF_CSTATE_PKG_C2_RES ) | -BIT (PERF_CSTATE_PKG_C3_RES ) |BIT (PERF_CSTATE_PKG_C6_RES ) | BIT(PERF_CSTATE_PKG_C10_RES), };
Signature · 1 line
2.51.1
[tip: perf/core] perf/x86/intel/cstate: Remove PC3 support from LunarLake
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 4ba45f041abe60337fdeeb68553b9ee1217d544e Gitweb: https://git.kernel.org/tip/4ba45f041abe60337fdeeb68553b9ee1217d544e Author: Zhang Rui <[email protected]> AuthorDate: Thu, 23 Oct 2025 15:37:52 -07:00 Committer: Peter Zijlstra <[email protected]> CommitterDate: Wed, 29 Oct 2025 10:29:54 +01:00
perf/x86/intel/cstate: Remove PC3 support from LunarLake
LunarLake doesn't support Package C3. Remove the PC3 residency counter support from LunarLake.
--- arch/x86/events/intel/cstate.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
arch/x86/events/intel/cstate.c +1 -2
@@ -70,7 +70,7 @@* perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, -* ADL,RPL,MTL,ARL,LNL +* ADL,RPL,MTL,ARL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02
@@ -522,7 +522,6 @@ static const struct cstate_model lnl_cstates __initconst = { BIT(PERF_CSTATE_CORE_C7_RES), .pkg_events =BIT (PERF_CSTATE_PKG_C2_RES ) | -BIT (PERF_CSTATE_PKG_C3_RES ) |BIT (PERF_CSTATE_PKG_C6_RES ) | BIT(PERF_CSTATE_PKG_C10_RES), };
PATCH RESEND 3/3 perf/x86/intel/cstate: Add Pantherlake support
In reply to Zide ChenFrom: Zhang Rui <[email protected]>
Like Lunarlake, Pantherlake supports CC1/CC6/CC7 and PC2/PC6/PC10.
--- arch/x86/events/intel/cstate.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
arch/x86/events/intel/cstate.c +8 -6
@@ -41,7 +41,7 @@* MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL -* MTL,SRF,GRR,ARL,LNL +* MTL,SRF,GRR,ARL,LNL,PTL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01
@@ -53,18 +53,19 @@* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF, -* GRR,ARL,LNL +* GRR,ARL,LNL,PTL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, -* ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL +* ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL, +* PTL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, -* RPL,SPR,MTL,ARL,LNL,SRF +* RPL,SPR,MTL,ARL,LNL,SRF,PTL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01
@@ -77,7 +78,7 @@* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF, -* ARL,LNL +* ARL,LNL,PTL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03
@@ -96,7 +97,7 @@* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, -* TNT,RKL,ADL,RPL,MTL,ARL,LNL +* TNT,RKL,ADL,RPL,MTL,ARL,LNL,PTL * Scope: Package (physical package) * MSR_MODULE_C6_RES_MS: Module C6 Residency Counter. * perf code: 0x00
@@ -652,6 +653,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {X86_MATCH_VFM (INTEL_ARROWLAKE_H , &adl_cstates),X86_MATCH_VFM (INTEL_ARROWLAKE_U , &adl_cstates),X86_MATCH_VFM (INTEL_LUNARLAKE_M , &lnl_cstates), +X86_MATCH_VFM (INTEL_PANTHERLAKE_L , &lnl_cstates), { }, };MODULE_DEVICE_TABLE (x86cpu, intel_cstates_match);
Signature · 1 line
2.51.1
[tip: perf/core] perf/x86/intel/cstate: Add Pantherlake support
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 34976eaf5f83d2bda76eeb54c5bbcafe87245e82 Gitweb: https://git.kernel.org/tip/34976eaf5f83d2bda76eeb54c5bbcafe87245e82 Author: Zhang Rui <[email protected]> AuthorDate: Thu, 23 Oct 2025 15:37:53 -07:00 Committer: Peter Zijlstra <[email protected]> CommitterDate: Wed, 29 Oct 2025 10:29:54 +01:00
perf/x86/intel/cstate: Add Pantherlake support
Like Lunarlake, Pantherlake supports CC1/CC6/CC7 and PC2/PC6/PC10.
--- arch/x86/events/intel/cstate.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
arch/x86/events/intel/cstate.c +8 -6
@@ -41,7 +41,7 @@* MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL -* MTL,SRF,GRR,ARL,LNL +* MTL,SRF,GRR,ARL,LNL,PTL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01
@@ -53,18 +53,19 @@* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF, -* GRR,ARL,LNL +* GRR,ARL,LNL,PTL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, -* ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL +* ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL, +* PTL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, -* RPL,SPR,MTL,ARL,LNL,SRF +* RPL,SPR,MTL,ARL,LNL,SRF,PTL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01
@@ -77,7 +78,7 @@* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF, -* ARL,LNL +* ARL,LNL,PTL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03
@@ -96,7 +97,7 @@* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, -* TNT,RKL,ADL,RPL,MTL,ARL,LNL +* TNT,RKL,ADL,RPL,MTL,ARL,LNL,PTL * Scope: Package (physical package) * MSR_MODULE_C6_RES_MS: Module C6 Residency Counter. * perf code: 0x00
@@ -652,6 +653,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {X86_MATCH_VFM (INTEL_ARROWLAKE_H , &adl_cstates),X86_MATCH_VFM (INTEL_ARROWLAKE_U , &adl_cstates),X86_MATCH_VFM (INTEL_LUNARLAKE_M , &lnl_cstates), +X86_MATCH_VFM (INTEL_PANTHERLAKE_L , &lnl_cstates), { }, };MODULE_DEVICE_TABLE (x86cpu, intel_cstates_match);
Quoted 14 lines · Zide Chen
This series resends three c-state patches that have been posted for a few months but have not yet received feedback.
On behalf of Rui, I’ve included his two patches here, so that all outstanding Intel c-state related patches can be reviewed together.
There are no code changes in this resend. Only the changelog in [PATCH 1/3] has been updated to note that the C1E counter can only be read via PMT.
Zhang Rui (2):
perf/x86/intel/cstate: Remove PC3 support from LunarLake perf/x86/intel/cstate: Add Pantherlake support
Quoted 5 lines
Zide Chen (1):
perf/x86/intel/cstate: Add Clearwater Forest supportarch/x86/events/intel/cstate.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
The whole patch series looks good to me.