Skip to contentSkip to conversation

x86/CPU: Add more Icelake model number

PATCH In review [email protected] 5 participants 13 messages Jun 3, 2019 – Jun 17, 2019

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/3 x86/CPU: Add more Icelake model number

From: Kan Liang <[email protected]>

Add the CPUID model number of Icelake (ICL) desktop and server processors to the Intel family list.

---
 arch/x86/include/asm/intel-family.h | 3 +++
 1 file changed, 3 insertions(+)
arch/x86/include/asm/intel-family.h +3 -0
index 9f15384c504a..310118805f57 100644
@@ -52,6 +52,9 @@
 
 #define INTEL_FAM6_CANNONLAKE_MOBILE	0x66
 
+#define INTEL_FAM6_ICELAKE_X		0x6A
+#define INTEL_FAM6_ICELAKE_XEON_D	0x6C
+#define INTEL_FAM6_ICELAKE_DESKTOP	0x7D
 #define INTEL_FAM6_ICELAKE_MOBILE	0x7E
 
 /* "Small Core" Processors (Atom) */
Signature · 1 line
2.14.5
#1 lore raw

PATCH 2/3 perf/x86/intel: Add more Icelake CPUIDs

From: Kan Liang <[email protected]>

Add new model number for Icelake desktop and server to perf.

The data source encoding for Icelake server is the same as Skylake server.

---
 arch/x86/events/intel/core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
arch/x86/events/intel/core.c +6 -1
index 546d13e436aa..c915afdaaba6 100644
@@ -4940,6 +4940,9 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ICELAKE_MOBILE:
+	case INTEL_FAM6_ICELAKE_DESKTOP:
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_XEON_D:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4962,7 +4965,9 @@ __init int intel_pmu_init(void)
 		x86_pmu.cpu_events = get_icl_events_attrs();
 		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
 		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_X) ||
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_XEON_D));
 		pr_cont("Icelake events, ");
 		name = "icelake";
 		break;
Signature · 1 line
2.14.5
maintainer
#2 lore raw

Re: [PATCH 2/3] perf/x86/intel: Add more Icelake CPUIDs

Review __init int intel_pmu_init(void) · line 4970

Quoted 8 lines · On Mon, Jun 03, 2019 at 06:41:21AM -0700, [email protected] wrote:
(quoted diff) +3 -1
@@ -4962,7 +4965,9 @@ __init int intel_pmu_init(void)
 		x86_pmu.cpu_events = get_icl_events_attrs();
 		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
 		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_X) ||
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_XEON_D));

That's pretty sad, a model switch inside a model switch :/

Review __init int intel_pmu_init(void) · line 4973

Quoted 3 lines
(quoted diff) +0 -0
 		pr_cont("Icelake events, ");
 		name = "icelake";
 		break;

Would something like so not be nicer?

---

arch/x86/events/intel/core.c +9 -4
@@ -4485,6 +4485,7 @@ __init int intel_pmu_init(void)
 	struct event_constraint *c;
 	unsigned int unused;
 	struct extra_reg *er;
+	bool pmem = false;
 	int version, i;
 	char *name;
 
@@ -4936,9 +4937,10 @@ __init int intel_pmu_init(void)
 		name = "knights-landing";
 		break;
 
+	case INTEL_FAM6_SKYLAKE_X:
+		pmem = true;
 	case INTEL_FAM6_SKYLAKE_MOBILE:
 	case INTEL_FAM6_SKYLAKE_DESKTOP:
-	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		x86_add_quirk(intel_pebs_isolation_quirk);
@@ -4970,8 +4972,7 @@ __init int intel_pmu_init(void)
 		td_attr  = hsw_events_attrs;
 		mem_attr = hsw_mem_events_attrs;
 		tsx_attr = hsw_tsx_events_attrs;
-		intel_pmu_pebs_data_source_skl(
-			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+		intel_pmu_pebs_data_source_skl(pmem);
 
 		if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
 			x86_pmu.flags |= PMU_FL_TFA;
@@ -4985,7 +4986,11 @@ __init int intel_pmu_init(void)
 		name = "skylake";
 		break;
 
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_XEON_D:
+		pmem = true;
 	case INTEL_FAM6_ICELAKE_MOBILE:
+	case INTEL_FAM6_ICELAKE_DESKTOP:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -5009,7 +5014,7 @@ __init int intel_pmu_init(void)
 		tsx_attr = icl_tsx_events_attrs;
 		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
 		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(pmem);
 		pr_cont("Icelake events, ");
 		name = "icelake";
 		break;
author
#3 lore raw

Re: [PATCH 2/3] perf/x86/intel: Add more Icelake CPUIDs

Quoted 12 lines · Peter Zijlstra

Review __init int intel_pmu_init(void) · line 4970

Quoted 8 lines · On Mon, Jun 03, 2019 at 06:41:21AM -0700, [email protected] wrote:
(quoted diff) +3 -1
@@ -4962,7 +4965,9 @@ __init int intel_pmu_init(void)
  		x86_pmu.cpu_events = get_icl_events_attrs();
  		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
  		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_X) ||
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_XEON_D));

That's pretty sad, a model switch inside a model switch :/

Quoted 5 lines

arch/x86/events/intel/core.c __init int intel_pmu_init(void) · line 5020

Quoted 3 lines
arch/x86/events/intel/core.c +0 -0
  		pr_cont("Icelake events, ");
  		name = "icelake";
  		break;

Would something like so not be nicer?

Yes, it looks better. Thanks.

Should I combine your patch with mine, and send out V2? Or are you prefer to add your patch on top of this patch set?

Thanks,
Kan

Quoted 56 lines

---

arch/x86/events/intel/core.c +9 -4
@@ -4485,6 +4485,7 @@ __init int intel_pmu_init(void)
  	struct event_constraint *c;
  	unsigned int unused;
  	struct extra_reg *er;
+	bool pmem = false;
  	int version, i;
  	char *name;
 
@@ -4936,9 +4937,10 @@ __init int intel_pmu_init(void)
  		name = "knights-landing";
  		break;
 
+	case INTEL_FAM6_SKYLAKE_X:
+		pmem = true;
  	case INTEL_FAM6_SKYLAKE_MOBILE:
  	case INTEL_FAM6_SKYLAKE_DESKTOP:
-	case INTEL_FAM6_SKYLAKE_X:
  	case INTEL_FAM6_KABYLAKE_MOBILE:
  	case INTEL_FAM6_KABYLAKE_DESKTOP:
  		x86_add_quirk(intel_pebs_isolation_quirk);
@@ -4970,8 +4972,7 @@ __init int intel_pmu_init(void)
  		td_attr  = hsw_events_attrs;
  		mem_attr = hsw_mem_events_attrs;
  		tsx_attr = hsw_tsx_events_attrs;
-		intel_pmu_pebs_data_source_skl(
-			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+		intel_pmu_pebs_data_source_skl(pmem);
 
  		if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
  			x86_pmu.flags |= PMU_FL_TFA;
@@ -4985,7 +4986,11 @@ __init int intel_pmu_init(void)
  		name = "skylake";
  		break;
 
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_XEON_D:
+		pmem = true;
  	case INTEL_FAM6_ICELAKE_MOBILE:
+	case INTEL_FAM6_ICELAKE_DESKTOP:
  		x86_pmu.late_ack = true;
  		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
  		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -5009,7 +5014,7 @@ __init int intel_pmu_init(void)
  		tsx_attr = icl_tsx_events_attrs;
  		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
  		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(pmem);
  		pr_cont("Icelake events, ");
  		name = "icelake";
  		break;
maintainer
#4 lore raw

Re: [PATCH 2/3] perf/x86/intel: Add more Icelake CPUIDs

Quoted 19 lines · Kan
Quoted 16 lines · Peter Zijlstra

Review __init int intel_pmu_init(void) · line 4970

Quoted 8 lines · On Mon, Jun 03, 2019 at 06:41:21AM -0700, [email protected] wrote:
(quoted diff) +3 -1
@@ -4962,7 +4965,9 @@ __init int intel_pmu_init(void)
  		x86_pmu.cpu_events = get_icl_events_attrs();
  		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
  		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_X) ||
+			(boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_XEON_D));

That's pretty sad, a model switch inside a model switch :/

Quoted 3 lines
arch/x86/events/intel/core.c +0 -0
  		pr_cont("Icelake events, ");
  		name = "icelake";
  		break;
Quoted 6 lines
Quoted 1 line

Would something like so not be nicer?

Yes, it looks better. Thanks.

Should I combine your patch with mine, and send out V2? Or are you prefer to add your patch on top of this patch set?

I'll frob it. Thanks!

#5 lore raw

[tip:perf/core] perf/x86/intel: Add more Icelake CPUIDs

In reply to [email protected]
perf/x86/intel: Add more Icelake CPUIDs
Commit-ID:  faaeff98666c24376cebd0b106504d05a36881d1
Gitweb:     https://git.kernel.org/tip/faaeff98666c24376cebd0b106504d05a36881d1
Author:     Kan Liang <[email protected]>
AuthorDate: Mon, 3 Jun 2019 06:41:21 -0700
Committer:  Ingo Molnar <[email protected]>
CommitDate: Mon, 17 Jun 2019 12:36:16 +0200

perf/x86/intel: Add more Icelake CPUIDs

Add new model number for Icelake desktop and server to perf.

The data source encoding for Icelake server is the same as Skylake server.

---
 arch/x86/events/intel/core.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)
arch/x86/events/intel/core.c +9 -4
index 71001f005bfe..4377bf6a6f82 100644
@@ -4485,6 +4485,7 @@ __init int intel_pmu_init(void)
 	struct event_constraint *c;
 	unsigned int unused;
 	struct extra_reg *er;
+	bool pmem = false;
 	int version, i;
 	char *name;
 
@@ -4936,9 +4937,10 @@ __init int intel_pmu_init(void)
 		name = "knights-landing";
 		break;
 
+	case INTEL_FAM6_SKYLAKE_X:
+		pmem = true;
 	case INTEL_FAM6_SKYLAKE_MOBILE:
 	case INTEL_FAM6_SKYLAKE_DESKTOP:
-	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		x86_add_quirk(intel_pebs_isolation_quirk);
@@ -4970,8 +4972,7 @@ __init int intel_pmu_init(void)
 		td_attr  = hsw_events_attrs;
 		mem_attr = hsw_mem_events_attrs;
 		tsx_attr = hsw_tsx_events_attrs;
-		intel_pmu_pebs_data_source_skl(
-			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+		intel_pmu_pebs_data_source_skl(pmem);
 
 		if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
 			x86_pmu.flags |= PMU_FL_TFA;
@@ -4985,7 +4986,11 @@ __init int intel_pmu_init(void)
 		name = "skylake";
 		break;
 
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_XEON_D:
+		pmem = true;
 	case INTEL_FAM6_ICELAKE_MOBILE:
+	case INTEL_FAM6_ICELAKE_DESKTOP:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -5009,7 +5014,7 @@ __init int intel_pmu_init(void)
 		tsx_attr = icl_tsx_events_attrs;
 		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
 		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(false);
+		intel_pmu_pebs_data_source_skl(pmem);
 		pr_cont("Icelake events, ");
 		name = "icelake";
 		break;
#6 lore raw

PATCH 3/3 perf/x86/intel: Add Icelake desktop CPUID

In reply to [email protected]

From: Kan Liang <[email protected]>

Add new Icelake desktop CPUID for RAPL, CSTATE and UNCORE.

---
 arch/x86/events/intel/cstate.c | 1 +
 arch/x86/events/intel/rapl.c   | 1 +
 arch/x86/events/intel/uncore.c | 1 +
 3 files changed, 3 insertions(+)
arch/x86/events/intel/cstate.c +1 -0
index 6072f92cb8ea..e6dc61fcfd97 100644
@@ -580,6 +580,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_DESKTOP, snb_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
arch/x86/events/intel/rapl.c +1 -0
index 37ebf6fc5415..6892e38cfdaf 100644
@@ -777,6 +777,7 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE,  skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, skl_rapl_init),
 	{},
 };
 
arch/x86/events/intel/uncore.c +1 -0
index fc40a1473058..56b2cbc0ddaf 100644
@@ -1399,6 +1399,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, icl_uncore_init),
 	{},
 };
 
Signature · 1 line
2.14.5
#7 lore raw

[tip:perf/core] perf/x86/intel: Add Icelake desktop CPUID

perf/x86/intel: Add Icelake desktop CPUID
Commit-ID:  2a538fda82824a7722e296be656bb5d11d91a9cb
Gitweb:     https://git.kernel.org/tip/2a538fda82824a7722e296be656bb5d11d91a9cb
Author:     Kan Liang <[email protected]>
AuthorDate: Mon, 3 Jun 2019 06:41:22 -0700
Committer:  Ingo Molnar <[email protected]>
CommitDate: Mon, 17 Jun 2019 12:36:14 +0200

perf/x86/intel: Add Icelake desktop CPUID

Add new Icelake desktop CPUID for RAPL, CSTATE and UNCORE.

---
 arch/x86/events/intel/cstate.c | 1 +
 arch/x86/events/intel/rapl.c   | 1 +
 arch/x86/events/intel/uncore.c | 1 +
 3 files changed, 3 insertions(+)
arch/x86/events/intel/cstate.c +1 -0
index 267d7f8e12ab..e1caa0b49d63 100644
@@ -580,6 +580,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_DESKTOP, snb_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
arch/x86/events/intel/rapl.c +1 -0
index 8c7ecde3ba70..798135419a62 100644
@@ -778,6 +778,7 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE,  skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, skl_rapl_init),
 	{},
 };
 
arch/x86/events/intel/uncore.c +1 -0
index 6094c8db949d..d37bb2c657b0 100644
@@ -1403,6 +1403,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_DESKTOP, icl_uncore_init),
 	{},
 };
 
maintainer
#8 lore raw
In reply to [email protected]
Quoted 7 lines · On Mon, Jun 03, 2019 at 06:41:20AM -0700, [email protected] wrote:

From: Kan Liang <[email protected]>

Add the CPUID model number of Icelake (ICL) desktop and server processors to the Intel family list.

You're sending this patch but it has Qiuxu's SOB too. What's that supposed to mean?

Signature · 4 lines
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.
#9 lore raw
Quoted 11 lines

From: Borislav Petkov [mailto:[email protected]]
...

Quoted 7 lines

From: Kan Liang <[email protected]>

Add the CPUID model number of Icelake (ICL) desktop and server processors to the Intel family list.

You're sending this patch but it has Qiuxu's SOB too. What's that supposed to mean?

Hi Boris,

During internal co-work, based on Kan's original patch, I got the "#define" in the Ice Lake group sorted by model number(the header of the file requires the sorting) and added my SOB. Dropping my SOB or adding a text "[Qiuxu: Get the macros in the Ice Lake group sorted by model number.]" at the end of the commit message - which one is better/clear for you?

Thanks!
-Qiuxu

maintainer
#10 lore raw
Quoted 6 lines · Qiuxu

During internal co-work, based on Kan's original patch, I got the "#define" in the Ice Lake group sorted by model number(the header of the file requires the sorting) and added my SOB. Dropping my SOB or adding a text "[Qiuxu: Get the macros in the Ice Lake group sorted by model number.]" at the end of the commit message - which one is better/clear for you?

I'll add that note when applying.

Thx.

Signature · 4 lines
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.
#11 lore raw
Quoted 8 lines

From: Borislav Petkov [mailto:[email protected]]

Quoted 3 lines

...
Dropping my SOB or adding a text "[Qiuxu: Get the macros in the Ice Lake group sorted by model number.]" at the end of the commit message - which one is better/clear for you?

I'll add that note when applying.

Thx.

Thanks Boris!
-Qiuxu

#12 lore raw

[tip:x86/urgent] x86/CPU: Add more Icelake model numbers

In reply to [email protected]
x86/CPU: Add more Icelake model numbers
Commit-ID:  e35faeb64146f2015f2aec14b358ae508e4066db
Gitweb:     https://git.kernel.org/tip/e35faeb64146f2015f2aec14b358ae508e4066db
Author:     Kan Liang <[email protected]>
AuthorDate: Mon, 3 Jun 2019 06:41:20 -0700
Committer:  Borislav Petkov <[email protected]>
CommitDate: Thu, 6 Jun 2019 09:42:36 +0200

x86/CPU: Add more Icelake model numbers

Add the CPUID model numbers of Icelake (ICL) desktop and server processors to the Intel family list.

[ Qiuxu: Sort the macros by model number. ]

Cc "H. Peter Anvin" <[email protected]>
Cc Andy Shevchenko <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Qiuxu Zhuo <[email protected]>
Cc Rajneesh Bhardwaj <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Tony Luck <[email protected]>
Cc x86-ml <[email protected]>
---
 arch/x86/include/asm/intel-family.h | 3 +++
 1 file changed, 3 insertions(+)
arch/x86/include/asm/intel-family.h +3 -0
index 9f15384c504a..310118805f57 100644
@@ -52,6 +52,9 @@
 
 #define INTEL_FAM6_CANNONLAKE_MOBILE	0x66
 
+#define INTEL_FAM6_ICELAKE_X		0x6A
+#define INTEL_FAM6_ICELAKE_XEON_D	0x6C
+#define INTEL_FAM6_ICELAKE_DESKTOP	0x7D
 #define INTEL_FAM6_ICELAKE_MOBILE	0x7E
 
 /* "Small Core" Processors (Atom) */