[PATCH v6 0/3] x86/kvm: Support AVX512_4VNNIW and AVX512_4FMAPS for KVM guest

[PATCH v6 0/3] x86/kvm: Support AVX512_4VNNIW and AVX512_4FMAPS for KVM guest

[He Chen]

This patch series is going to add two new AVX512 features to KVM guest.
Since these two features are defined as scattered features in kernel,
some extra modification in kernel is included.

BTW. sorry for sending patch so frequently, and really appreciate your
kindly review.

---
Changes in v6:
* refine commit messages.

Changes in v5:
* divide the whole patchset into 3 parts.
* refine commit messages.

Changes in v4:
* divide patch into 2 parts, including modification in scattered.c and
  support new AVX512 instructions for KVM.
* coding style.
* refine commit message.

Changes in v3:
* add a helper in scattered.c to get scattered leaf.

Changes in v2:
* add new macros for new AVX512 scattered features.
* add a cpuid_count_edx function to processor.h

He Chen (3):
  x86/cpuid: Cleanup cpuid_regs definitions
  x86/cpuid: Add a helper in scattered.c to return cpuid
  x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS subfeatures support

 arch/x86/events/intel/pt.c       | 45 ++++++++++++++-----------------
 arch/x86/include/asm/processor.h | 14 ++++++++++
 arch/x86/kernel/cpu/scattered.c  | 57 ++++++++++++++++++++++++++--------------
 arch/x86/kernel/cpuid.c          |  4 ---
 arch/x86/kvm/cpuid.c             | 14 +++++++++-
 5 files changed, 84 insertions(+), 50 deletions(-)

-- 
2.7.4

[PATCH v6 1/3] x86/cpuid: Cleanup cpuid_regs definitions

[He Chen]

make cpuid_regs more clear and avoid potential name clash.

Signed-off-by: He Chen <he.chen@linux.intel.com>
---
 arch/x86/events/intel/pt.c       | 45 +++++++++++++++++-----------------------
 arch/x86/include/asm/processor.h | 11 ++++++++++
 arch/x86/kernel/cpu/scattered.c  | 28 ++++++++++---------------
 arch/x86/kernel/cpuid.c          |  4 ----
 4 files changed, 41 insertions(+), 47 deletions(-)

diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index c5047b8..1c1b9fe 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx);
 
 static struct pt_pmu pt_pmu;
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
 /*
  * Capabilities of Intel PT hardware, such as number of address bits or
  * supported output schemes, are cached and exported to userspace as "caps"
@@ -64,21 +57,21 @@ static struct pt_cap_desc {
 	u8		reg;
 	u32		mask;
 } pt_caps[] = {
-	PT_CAP(max_subleaf,		0, CR_EAX, 0xffffffff),
-	PT_CAP(cr3_filtering,		0, CR_EBX, BIT(0)),
-	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
-	PT_CAP(ip_filtering,		0, CR_EBX, BIT(2)),
-	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
-	PT_CAP(ptwrite,			0, CR_EBX, BIT(4)),
-	PT_CAP(power_event_trace,	0, CR_EBX, BIT(5)),
-	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
-	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
-	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
-	PT_CAP(payloads_lip,		0, CR_ECX, BIT(31)),
-	PT_CAP(num_address_ranges,	1, CR_EAX, 0x3),
-	PT_CAP(mtc_periods,		1, CR_EAX, 0xffff0000),
-	PT_CAP(cycle_thresholds,	1, CR_EBX, 0xffff),
-	PT_CAP(psb_periods,		1, CR_EBX, 0xffff0000),
+	PT_CAP(max_subleaf,		0, CPUID_EAX, 0xffffffff),
+	PT_CAP(cr3_filtering,		0, CPUID_EBX, BIT(0)),
+	PT_CAP(psb_cyc,			0, CPUID_EBX, BIT(1)),
+	PT_CAP(ip_filtering,		0, CPUID_EBX, BIT(2)),
+	PT_CAP(mtc,			0, CPUID_EBX, BIT(3)),
+	PT_CAP(ptwrite,			0, CPUID_EBX, BIT(4)),
+	PT_CAP(power_event_trace,	0, CPUID_EBX, BIT(5)),
+	PT_CAP(topa_output,		0, CPUID_ECX, BIT(0)),
+	PT_CAP(topa_multiple_entries,	0, CPUID_ECX, BIT(1)),
+	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
+	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
+	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
+	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
+	PT_CAP(cycle_thresholds,	1, CPUID_EBX, 0xffff),
+	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
 };
 
 static u32 pt_cap_get(enum pt_capabilities cap)
@@ -213,10 +206,10 @@ static int __init pt_pmu_hw_init(void)
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
-			    &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]);
+			    &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM]);
 	}
 
 	ret = -ENOMEM;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf..8f6ac5b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -137,6 +137,17 @@ struct cpuinfo_x86 {
 	u32			microcode;
 };
 
+struct cpuid_regs {
+	u32 eax, ebx, ecx, edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
 #define X86_VENDOR_INTEL	0
 #define X86_VENDOR_CYRIX	1
 #define X86_VENDOR_AMD		2
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 1db8dc4..dbb470e 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -17,13 +17,6 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
 void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 {
 	u32 max_level;
@@ -31,14 +24,14 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	const struct cpuid_bit *cb;
 
 	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_INTEL_PT,		CR_EBX,25, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4VNNIW,	CR_EDX, 2, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4FMAPS,	CR_EDX, 3, 0x00000007, 0 },
-		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
-		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
-		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
-		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
-		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
+		{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
+		{ X86_FEATURE_AVX512_4VNNIW,	CPUID_EDX,  2, 0x00000007, 0 },
+		{ X86_FEATURE_AVX512_4FMAPS,	CPUID_EDX,  3, 0x00000007, 0 },
+		{ X86_FEATURE_APERFMPERF,	CPUID_ECX,  0, 0x00000006, 0 },
+		{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+		{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
+		{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
+		{ X86_FEATURE_PROC_FEEDBACK,	CPUID_EDX, 11, 0x80000007, 0 },
 		{ 0, 0, 0, 0, 0 }
 	};
 
@@ -50,8 +43,9 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		    max_level > (cb->level | 0xffff))
 			continue;
 
-		cpuid_count(cb->level, cb->sub_leaf, &regs[CR_EAX],
-			    &regs[CR_EBX], &regs[CR_ECX], &regs[CR_EDX]);
+		cpuid_count(cb->level, cb->sub_leaf, &regs[CPUID_EAX],
+			    &regs[CPUID_EBX], &regs[CPUID_ECX],
+			    &regs[CPUID_EDX]);
 
 		if (regs[cb->reg] & (1 << cb->bit))
 			set_cpu_cap(c, cb->feature);
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 2836de3..9095c80 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -46,10 +46,6 @@
 
 static struct class *cpuid_class;
 
-struct cpuid_regs {
-	u32 eax, ebx, ecx, edx;
-};
-
 static void cpuid_smp_cpuid(void *cmd_block)
 {
 	struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block;
-- 
2.7.4

[PATCH v6 2/3] x86/cpuid: Add a helper in scattered.c to return cpuid

[He Chen]

Some sparse CPUID leafs are gathered in a fake leaf to save size of
x86_capability array in current code, but sometimes, kernel or other
modules (e.g. KVM CPUID enumeration) may need actual hardware leaf
information.

This patch adds a helper get_scattered_cpuid_leaf() to rebuild actual
CPUID leaf, and it can be called outside by modules.

Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: He Chen <he.chen@linux.intel.com>
---
 arch/x86/include/asm/processor.h |  3 +++
 arch/x86/kernel/cpu/scattered.c  | 49 ++++++++++++++++++++++++++++++----------
 2 files changed, 40 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 8f6ac5b..e7f8c62 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -189,6 +189,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index dbb470e..d1316f9 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -17,24 +17,25 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
+/* Please keep the leaf sorted by cpuid_bit.level for faster search. */
+static const struct cpuid_bit cpuid_bits[] = {
+	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
+	{ X86_FEATURE_EPB,              CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_INTEL_PT,         CPUID_EBX, 25, 0x00000007, 0 },
+	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
+	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
+	{ X86_FEATURE_HW_PSTATE,        CPUID_EDX,  7, 0x80000007, 0 },
+	{ X86_FEATURE_CPB,              CPUID_EDX,  9, 0x80000007, 0 },
+	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
+	{ 0, 0, 0, 0, 0 }
+};
+
 void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 {
 	u32 max_level;
 	u32 regs[4];
 	const struct cpuid_bit *cb;
 
-	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4VNNIW,	CPUID_EDX,  2, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4FMAPS,	CPUID_EDX,  3, 0x00000007, 0 },
-		{ X86_FEATURE_APERFMPERF,	CPUID_ECX,  0, 0x00000006, 0 },
-		{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
-		{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
-		{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
-		{ X86_FEATURE_PROC_FEEDBACK,	CPUID_EDX, 11, 0x80000007, 0 },
-		{ 0, 0, 0, 0, 0 }
-	};
-
 	for (cb = cpuid_bits; cb->feature; cb++) {
 
 		/* Verify that the level is valid */
@@ -51,3 +52,27 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, cb->feature);
 	}
 }
+
+u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
+			     enum cpuid_regs_idx reg)
+{
+	const struct cpuid_bit *cb;
+	u32 cpuid_val = 0;
+
+	for (cb = cpuid_bits; cb->feature; cb++) {
+
+		if (level > cb->level)
+			continue;
+
+		if (level < cb->level)
+			break;
+
+		if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
+			if (cpu_has(&boot_cpu_data, cb->feature))
+				cpuid_val |= BIT(cb->bit);
+		}
+	}
+
+	return cpuid_val;
+}
+EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);
-- 
2.7.4

[PATCH v6 3/3] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[He Chen]

Add two new AVX512 subfeatures support for KVM guest.

AVX512_4VNNIW:
Vector instructions for deep learning enhanced word variable precision.

AVX512_4FMAPS:
Vector instructions for deep learning floating-point single precision.

Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: He Chen <he.chen@linux.intel.com>
---
 arch/x86/kvm/cpuid.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index afa7bbb..ddcdf7c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/processor.h>
 #include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
@@ -65,6 +66,11 @@ u64 kvm_supported_xcr0(void)
 
 #define F(x) bit(X86_FEATURE_##x)
 
+/* These are scattered features in cpufeatures.h. */
+#define KVM_CPUID_BIT_AVX512_4VNNIW     2
+#define KVM_CPUID_BIT_AVX512_4FMAPS     3
+#define KF(x) bit(KVM_CPUID_BIT_##x)
+
 int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -376,6 +382,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/;
 
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -458,12 +468,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			/* PKU is not yet implemented for shadow paging. */
 			if (!tdp_enabled)
 				entry->ecx &= ~F(PKU);
+			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+			entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
 		} else {
 			entry->ebx = 0;
 			entry->ecx = 0;
+			entry->edx = 0;
 		}
 		entry->eax = 0;
-		entry->edx = 0;
 		break;
 	}
 	case 9:
-- 
2.7.4

Re: [PATCH v6 3/3] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[Borislav Petkov]

On Fri, Nov 11, 2016 at 05:25:36PM +0800, He Chen wrote:
> Add two new AVX512 subfeatures support for KVM guest.
> 
> AVX512_4VNNIW:
> Vector instructions for deep learning enhanced word variable precision.
> 
> AVX512_4FMAPS:
> Vector instructions for deep learning floating-point single precision.
> 
> Reviewed-by: Borislav Petkov <bp@suse.de>
> Signed-off-by: Luwei Kang <luwei.kang@intel.com>
> Signed-off-by: He Chen <he.chen@linux.intel.com>
> ---

Whoops, I said it looked ok but missed that SOB chain above.

What does it mean? Did Luwei wrote the patch and you're sending it or
...?

-- 
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.

Re: [PATCH v6 3/3] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[He Chen]

On Sat, Nov 12, 2016 at 01:53:29PM +0100, Borislav Petkov wrote:
> On Fri, Nov 11, 2016 at 05:25:36PM +0800, He Chen wrote:
> > Add two new AVX512 subfeatures support for KVM guest.
> > 
> > AVX512_4VNNIW:
> > Vector instructions for deep learning enhanced word variable precision.
> > 
> > AVX512_4FMAPS:
> > Vector instructions for deep learning floating-point single precision.
> > 
> > Reviewed-by: Borislav Petkov <bp@suse.de>
> > Signed-off-by: Luwei Kang <luwei.kang@intel.com>
> > Signed-off-by: He Chen <he.chen@linux.intel.com>
> > ---
> 
> Whoops, I said it looked ok but missed that SOB chain above.
> 
> What does it mean? Did Luwei wrote the patch and you're sending it or
> ...?
> 
Yep, Luwei wrote it and I send it on behalf of him.

Thanks,
-He

Re: [PATCH v6 3/3] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[Borislav Petkov]

On Mon, Nov 14, 2016 at 09:41:04AM +0800, He Chen wrote:
> Yep, Luwei wrote it and I send it on behalf of him.

Then it needs to have the following format so that tools can pick up the
proper author:

"From: Luwei ...

<commit message text>

Signed-off-by: He Chen...
Signed-off-by: Luwei...
...
"

git format-patch gives that formatting.

If you want to change the ownership, do the following on the local
commit:

$ git commit --amend --author="Luwei Kang <luwei.kang@intel.com>"

in case it lists you locally as author.

HTH.

-- 
Regards/Gruss,
    Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.

[Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[He Chen]

>From 2daa60b3c6ab5aa6414ebb33119a34403dad2048 Mon Sep 17 00:00:00 2001
From: Luwei Kang <luwei.kang@intel.com>
Date: Mon, 7 Nov 2016 14:03:20 +0800
Subject: [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

Add two new AVX512 subfeatures support for KVM guest.

AVX512_4VNNIW:
Vector instructions for deep learning enhanced word variable precision.

AVX512_4FMAPS:
Vector instructions for deep learning floating-point single precision.

Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: He Chen <he.chen@linux.intel.com>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
---
 arch/x86/kvm/cpuid.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index afa7bbb..ddcdf7c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/processor.h>
 #include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
 #include <asm/fpu/xstate.h>
@@ -65,6 +66,11 @@ u64 kvm_supported_xcr0(void)
 
 #define F(x) bit(X86_FEATURE_##x)
 
+/* These are scattered features in cpufeatures.h. */
+#define KVM_CPUID_BIT_AVX512_4VNNIW     2
+#define KVM_CPUID_BIT_AVX512_4FMAPS     3
+#define KF(x) bit(KVM_CPUID_BIT_##x)
+
 int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -376,6 +382,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/;
 
+	/* cpuid 7.0.edx*/
+	const u32 kvm_cpuid_7_0_edx_x86_features =
+		KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS);
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -458,12 +468,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			/* PKU is not yet implemented for shadow paging. */
 			if (!tdp_enabled)
 				entry->ecx &= ~F(PKU);
+			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+			entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
 		} else {
 			entry->ebx = 0;
 			entry->ecx = 0;
+			entry->edx = 0;
 		}
 		entry->eax = 0;
-		entry->edx = 0;
 		break;
 	}
 	case 9:
-- 
2.7.4

Re: [PATCH v6 3/3] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[He Chen]

On Mon, Nov 14, 2016 at 06:58:22AM +0100, Borislav Petkov wrote:
> On Mon, Nov 14, 2016 at 09:41:04AM +0800, He Chen wrote:
> > Yep, Luwei wrote it and I send it on behalf of him.
> 
> Then it needs to have the following format so that tools can pick up the
> proper author:
> 
> "From: Luwei ...
> 
> <commit message text>
> 
> Signed-off-by: He Chen...
> Signed-off-by: Luwei...
> ...
> "
> 
> git format-patch gives that formatting.
> 
> If you want to change the ownership, do the following on the local
> commit:
> 
> $ git commit --amend --author="Luwei Kang <luwei.kang@intel.com>"
> 
> in case it lists you locally as author.
> 
> HTH.
> 
I am not sure if it is ok to reply this amended patch in this thread.
or should I send another [Patch v6.1] patchset?

Thanks,
-He

Re: [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 1961 bytes --]

Hi He,

[auto build test ERROR on kvm/linux-next]
[also build test ERROR on v4.9-rc5]
[cannot apply to next-20161114]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/He-Chen/x86-kvm-Add-AVX512_4VNNIW-and-AVX512_4FMAPS-support/20161114-170941
base:   https://git.kernel.org/pub/scm/virt/kvm/kvm.git linux-next
config: x86_64-kexec (attached as .config)
compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
reproduce:
        # save the attached .config to linux build tree
        make ARCH=x86_64 

All errors (new ones prefixed by >>):

   arch/x86/kvm/cpuid.c: In function '__do_cpuid_ent':
>> arch/x86/kvm/cpuid.c:472:18: error: implicit declaration of function 'get_scattered_cpuid_leaf' [-Werror=implicit-function-declaration]
       entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
                     ^~~~~~~~~~~~~~~~~~~~~~~~
>> arch/x86/kvm/cpuid.c:472:49: error: 'CPUID_EDX' undeclared (first use in this function)
       entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
                                                    ^~~~~~~~~
   arch/x86/kvm/cpuid.c:472:49: note: each undeclared identifier is reported only once for each function it appears in
   cc1: some warnings being treated as errors

vim +/get_scattered_cpuid_leaf +472 arch/x86/kvm/cpuid.c

   466				entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
   467				cpuid_mask(&entry->ecx, CPUID_7_ECX);
   468				/* PKU is not yet implemented for shadow paging. */
   469				if (!tdp_enabled)
   470					entry->ecx &= ~F(PKU);
   471				entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 > 472				entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
   473			} else {
   474				entry->ebx = 0;
   475				entry->ecx = 0;

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 24231 bytes --]

Re: [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[He Chen]

On Tue, Nov 15, 2016 at 04:24:39AM +0800, kbuild test robot wrote:
> Hi He,
> 
> [auto build test ERROR on kvm/linux-next]
> [also build test ERROR on v4.9-rc5]
> [cannot apply to next-20161114]
> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
> 
> url:    https://github.com/0day-ci/linux/commits/He-Chen/x86-kvm-Add-AVX512_4VNNIW-and-AVX512_4FMAPS-support/20161114-170941
> base:   https://git.kernel.org/pub/scm/virt/kvm/kvm.git linux-next
> config: x86_64-kexec (attached as .config)
> compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
> reproduce:
>         # save the attached .config to linux build tree
>         make ARCH=x86_64 
> 
> All errors (new ones prefixed by >>):
> 
>    arch/x86/kvm/cpuid.c: In function '__do_cpuid_ent':
> >> arch/x86/kvm/cpuid.c:472:18: error: implicit declaration of function 'get_scattered_cpuid_leaf' [-Werror=implicit-function-declaration]
>        entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
>                      ^~~~~~~~~~~~~~~~~~~~~~~~
> >> arch/x86/kvm/cpuid.c:472:49: error: 'CPUID_EDX' undeclared (first use in this function)
>        entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
>                                                     ^~~~~~~~~
>    arch/x86/kvm/cpuid.c:472:49: note: each undeclared identifier is reported only once for each function it appears in
>    cc1: some warnings being treated as errors
>
I have downloaded .config.gz in attachment and use the .config in it
to build kernel in my local branch again, and I don't see any warn or
error message.

I wonder whether the previous 0001 and 0002 patches have applied to run
this test? Or is there something wrong with my compiler or patches?

Thanks,
-He

Re: [kbuild-all] [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[Fengguang Wu]

Hi He Chen,

On Tue, Nov 15, 2016 at 02:02:23PM +0800, He Chen wrote:
>On Tue, Nov 15, 2016 at 04:24:39AM +0800, kbuild test robot wrote:
>> Hi He,
>>
>> [auto build test ERROR on kvm/linux-next]
>> [also build test ERROR on v4.9-rc5]
>> [cannot apply to next-20161114]
>> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
>>
>> url:    https://github.com/0day-ci/linux/commits/He-Chen/x86-kvm-Add-AVX512_4VNNIW-and-AVX512_4FMAPS-support/20161114-170941
>> base:   https://git.kernel.org/pub/scm/virt/kvm/kvm.git linux-next

>I have downloaded .config.gz in attachment and use the .config in it
>to build kernel in my local branch again, and I don't see any warn or
>error message.
>
>I wonder whether the previous 0001 and 0002 patches have applied to run
>this test? Or is there something wrong with my compiler or patches?

Sorry the robot is not smart enough to see the 0001/0002 patches.
As you may see from the above url, only this patch is applied on top
of the KVM linux-next branch.

Thanks,
Fengguang

Re: [PATCH v6 0/3] x86/kvm: Support AVX512_4VNNIW and AVX512_4FMAPS for KVM guest

[Thomas Gleixner]

On Fri, 11 Nov 2016, He Chen wrote:

> This patch series is going to add two new AVX512 features to KVM guest.
> Since these two features are defined as scattered features in kernel,
> some extra modification in kernel is included.

I merged the first two patches into 

 git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/cpufeatures

Paolo, feel free to pull that branch up to commit 47bdf3378d62 into kvm so
you can apply the KVM patch on top.

Thanks,

	tglx

[tip:x86/cpufeature] x86/cpuid: Cleanup cpuid_regs definitions

[tip-bot for He Chen]

Commit-ID:  47f10a36003eaf493125a5e6687dd1ff775bfd8c
Gitweb:     http://git.kernel.org/tip/47f10a36003eaf493125a5e6687dd1ff775bfd8c
Author:     He Chen <he.chen@linux.intel.com>
AuthorDate: Fri, 11 Nov 2016 17:25:34 +0800
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Wed, 16 Nov 2016 11:13:09 +0100

x86/cpuid: Cleanup cpuid_regs definitions

cpuid_regs is defined multiple times as structure and enum. Rename the enum
and move all of it to processor.h so we don't end up with more instances.

Rename the misnomed register enumeration from CR_* to the obvious CPUID_*.

[ tglx: Rewrote changelog ]

Signed-off-by: He Chen <he.chen@linux.intel.com>
Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Luwei Kang <luwei.kang@intel.com>
Cc: kvm@vger.kernel.org
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Piotr Luc <Piotr.Luc@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lkml.kernel.org/r/1478856336-9388-2-git-send-email-he.chen@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/x86/events/intel/pt.c       | 45 +++++++++++++++++-----------------------
 arch/x86/include/asm/processor.h | 11 ++++++++++
 arch/x86/kernel/cpu/scattered.c  | 28 ++++++++++---------------
 arch/x86/kernel/cpuid.c          |  4 ----
 4 files changed, 41 insertions(+), 47 deletions(-)

diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index c5047b8..1c1b9fe 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx);
 
 static struct pt_pmu pt_pmu;
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
 /*
  * Capabilities of Intel PT hardware, such as number of address bits or
  * supported output schemes, are cached and exported to userspace as "caps"
@@ -64,21 +57,21 @@ static struct pt_cap_desc {
 	u8		reg;
 	u32		mask;
 } pt_caps[] = {
-	PT_CAP(max_subleaf,		0, CR_EAX, 0xffffffff),
-	PT_CAP(cr3_filtering,		0, CR_EBX, BIT(0)),
-	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
-	PT_CAP(ip_filtering,		0, CR_EBX, BIT(2)),
-	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
-	PT_CAP(ptwrite,			0, CR_EBX, BIT(4)),
-	PT_CAP(power_event_trace,	0, CR_EBX, BIT(5)),
-	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
-	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
-	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
-	PT_CAP(payloads_lip,		0, CR_ECX, BIT(31)),
-	PT_CAP(num_address_ranges,	1, CR_EAX, 0x3),
-	PT_CAP(mtc_periods,		1, CR_EAX, 0xffff0000),
-	PT_CAP(cycle_thresholds,	1, CR_EBX, 0xffff),
-	PT_CAP(psb_periods,		1, CR_EBX, 0xffff0000),
+	PT_CAP(max_subleaf,		0, CPUID_EAX, 0xffffffff),
+	PT_CAP(cr3_filtering,		0, CPUID_EBX, BIT(0)),
+	PT_CAP(psb_cyc,			0, CPUID_EBX, BIT(1)),
+	PT_CAP(ip_filtering,		0, CPUID_EBX, BIT(2)),
+	PT_CAP(mtc,			0, CPUID_EBX, BIT(3)),
+	PT_CAP(ptwrite,			0, CPUID_EBX, BIT(4)),
+	PT_CAP(power_event_trace,	0, CPUID_EBX, BIT(5)),
+	PT_CAP(topa_output,		0, CPUID_ECX, BIT(0)),
+	PT_CAP(topa_multiple_entries,	0, CPUID_ECX, BIT(1)),
+	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
+	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
+	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
+	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
+	PT_CAP(cycle_thresholds,	1, CPUID_EBX, 0xffff),
+	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
 };
 
 static u32 pt_cap_get(enum pt_capabilities cap)
@@ -213,10 +206,10 @@ static int __init pt_pmu_hw_init(void)
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
-			    &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]);
+			    &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM]);
 	}
 
 	ret = -ENOMEM;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf..8f6ac5b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -137,6 +137,17 @@ struct cpuinfo_x86 {
 	u32			microcode;
 };
 
+struct cpuid_regs {
+	u32 eax, ebx, ecx, edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
 #define X86_VENDOR_INTEL	0
 #define X86_VENDOR_CYRIX	1
 #define X86_VENDOR_AMD		2
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 1db8dc4..dbb470e 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -17,13 +17,6 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
 void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 {
 	u32 max_level;
@@ -31,14 +24,14 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	const struct cpuid_bit *cb;
 
 	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_INTEL_PT,		CR_EBX,25, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4VNNIW,	CR_EDX, 2, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4FMAPS,	CR_EDX, 3, 0x00000007, 0 },
-		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
-		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
-		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
-		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
-		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
+		{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
+		{ X86_FEATURE_AVX512_4VNNIW,	CPUID_EDX,  2, 0x00000007, 0 },
+		{ X86_FEATURE_AVX512_4FMAPS,	CPUID_EDX,  3, 0x00000007, 0 },
+		{ X86_FEATURE_APERFMPERF,	CPUID_ECX,  0, 0x00000006, 0 },
+		{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+		{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
+		{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
+		{ X86_FEATURE_PROC_FEEDBACK,	CPUID_EDX, 11, 0x80000007, 0 },
 		{ 0, 0, 0, 0, 0 }
 	};
 
@@ -50,8 +43,9 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		    max_level > (cb->level | 0xffff))
 			continue;
 
-		cpuid_count(cb->level, cb->sub_leaf, &regs[CR_EAX],
-			    &regs[CR_EBX], &regs[CR_ECX], &regs[CR_EDX]);
+		cpuid_count(cb->level, cb->sub_leaf, &regs[CPUID_EAX],
+			    &regs[CPUID_EBX], &regs[CPUID_ECX],
+			    &regs[CPUID_EDX]);
 
 		if (regs[cb->reg] & (1 << cb->bit))
 			set_cpu_cap(c, cb->feature);
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 2836de3..9095c80 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -46,10 +46,6 @@
 
 static struct class *cpuid_class;
 
-struct cpuid_regs {
-	u32 eax, ebx, ecx, edx;
-};
-
 static void cpuid_smp_cpuid(void *cmd_block)
 {
 	struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block;

[tip:x86/cpufeature] x86/cpuid: Provide get_scattered_cpuid_leaf()

[tip-bot for He Chen]

Commit-ID:  47bdf3378d62a627cfb8a54e1180c08d67078b61
Gitweb:     http://git.kernel.org/tip/47bdf3378d62a627cfb8a54e1180c08d67078b61
Author:     He Chen <he.chen@linux.intel.com>
AuthorDate: Fri, 11 Nov 2016 17:25:35 +0800
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Wed, 16 Nov 2016 11:13:09 +0100

x86/cpuid: Provide get_scattered_cpuid_leaf()

Sparse populated CPUID leafs are collected in a software provided leaf to
avoid bloat of the x86_capability array, but there is no way to rebuild the
real leafs (e.g. for KVM CPUID enumeration) other than rereading the CPUID
leaf from the CPU. While this is possible it is problematic as it does not
take software disabled features into account. If a feature is disabled on
the host it should not be exposed to a guest either.

Add get_scattered_cpuid_leaf() which rebuilds the leaf from the scattered
cpuid table information and the active CPU features.

[ tglx: Rewrote changelog ]

Signed-off-by: He Chen <he.chen@linux.intel.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Luwei Kang <luwei.kang@intel.com>
Cc: kvm@vger.kernel.org
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Piotr Luc <Piotr.Luc@intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lkml.kernel.org/r/1478856336-9388-3-git-send-email-he.chen@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/x86/include/asm/processor.h |  3 +++
 arch/x86/kernel/cpu/scattered.c  | 49 ++++++++++++++++++++++++++++++----------
 2 files changed, 40 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 8f6ac5b..e7f8c62 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -189,6 +189,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index dbb470e..d1316f9 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -17,24 +17,25 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
+/* Please keep the leaf sorted by cpuid_bit.level for faster search. */
+static const struct cpuid_bit cpuid_bits[] = {
+	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
+	{ X86_FEATURE_EPB,              CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_INTEL_PT,         CPUID_EBX, 25, 0x00000007, 0 },
+	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
+	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
+	{ X86_FEATURE_HW_PSTATE,        CPUID_EDX,  7, 0x80000007, 0 },
+	{ X86_FEATURE_CPB,              CPUID_EDX,  9, 0x80000007, 0 },
+	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
+	{ 0, 0, 0, 0, 0 }
+};
+
 void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 {
 	u32 max_level;
 	u32 regs[4];
 	const struct cpuid_bit *cb;
 
-	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4VNNIW,	CPUID_EDX,  2, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4FMAPS,	CPUID_EDX,  3, 0x00000007, 0 },
-		{ X86_FEATURE_APERFMPERF,	CPUID_ECX,  0, 0x00000006, 0 },
-		{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
-		{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
-		{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
-		{ X86_FEATURE_PROC_FEEDBACK,	CPUID_EDX, 11, 0x80000007, 0 },
-		{ 0, 0, 0, 0, 0 }
-	};
-
 	for (cb = cpuid_bits; cb->feature; cb++) {
 
 		/* Verify that the level is valid */
@@ -51,3 +52,27 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, cb->feature);
 	}
 }
+
+u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
+			     enum cpuid_regs_idx reg)
+{
+	const struct cpuid_bit *cb;
+	u32 cpuid_val = 0;
+
+	for (cb = cpuid_bits; cb->feature; cb++) {
+
+		if (level > cb->level)
+			continue;
+
+		if (level < cb->level)
+			break;
+
+		if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
+			if (cpu_has(&boot_cpu_data, cb->feature))
+				cpuid_val |= BIT(cb->bit);
+		}
+	}
+
+	return cpuid_val;
+}
+EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);

Re: [PATCH v6 0/3] x86/kvm: Support AVX512_4VNNIW and AVX512_4FMAPS for KVM guest

[Radim Krčmář]

2016-11-16 11:16+0100, Thomas Gleixner:
> On Fri, 11 Nov 2016, He Chen wrote:
> 
>> This patch series is going to add two new AVX512 features to KVM guest.
>> Since these two features are defined as scattered features in kernel,
>> some extra modification in kernel is included.
> 
> I merged the first two patches into 
> 
>  git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/cpufeatures
> 
> Paolo, feel free to pull that branch up to commit 47bdf3378d62 into kvm so
> you can apply the KVM patch on top.

Pulled into kvm/next, thanks.

Re: [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[Radim Krčmář]

2016-11-14 16:45+0800, He Chen:
> From 2daa60b3c6ab5aa6414ebb33119a34403dad2048 Mon Sep 17 00:00:00 2001
> From: Luwei Kang <luwei.kang@intel.com>
> Date: Mon, 7 Nov 2016 14:03:20 +0800
> Subject: [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support
> 
> Add two new AVX512 subfeatures support for KVM guest.
> 
> AVX512_4VNNIW:
> Vector instructions for deep learning enhanced word variable precision.
> 
> AVX512_4FMAPS:
> Vector instructions for deep learning floating-point single precision.
> 
> Reviewed-by: Borislav Petkov <bp@suse.de>
> Signed-off-by: He Chen <he.chen@linux.intel.com>
> Signed-off-by: Luwei Kang <luwei.kang@intel.com>
> ---

I changed the subject tags to 'kvm: x86:' and applied to kvm/queue,
thanks.

Re: [kbuild-all] [Patch v6.1] x86/kvm: Add AVX512_4VNNIW and AVX512_4FMAPS support

[Ye Xiaolong]

On 11/15, He Chen wrote:
>On Tue, Nov 15, 2016 at 04:24:39AM +0800, kbuild test robot wrote:
>> Hi He,
>> 
>> [auto build test ERROR on kvm/linux-next]
>> [also build test ERROR on v4.9-rc5]
>> [cannot apply to next-20161114]
>> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
>> 
>> url:    https://github.com/0day-ci/linux/commits/He-Chen/x86-kvm-Add-AVX512_4VNNIW-and-AVX512_4FMAPS-support/20161114-170941
>> base:   https://git.kernel.org/pub/scm/virt/kvm/kvm.git linux-next
>> config: x86_64-kexec (attached as .config)
>> compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
>> reproduce:
>>         # save the attached .config to linux build tree
>>         make ARCH=x86_64 
>> 
>> All errors (new ones prefixed by >>):
>> 
>>    arch/x86/kvm/cpuid.c: In function '__do_cpuid_ent':
>> >> arch/x86/kvm/cpuid.c:472:18: error: implicit declaration of function 'get_scattered_cpuid_leaf' [-Werror=implicit-function-declaration]
>>        entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
>>                      ^~~~~~~~~~~~~~~~~~~~~~~~
>> >> arch/x86/kvm/cpuid.c:472:49: error: 'CPUID_EDX' undeclared (first use in this function)
>>        entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
>>                                                     ^~~~~~~~~
>>    arch/x86/kvm/cpuid.c:472:49: note: each undeclared identifier is reported only once for each function it appears in
>>    cc1: some warnings being treated as errors
>>
>I have downloaded .config.gz in attachment and use the .config in it
>to build kernel in my local branch again, and I don't see any warn or
>error message.
>
>I wonder whether the previous 0001 and 0002 patches have applied to run
>this test? Or is there something wrong with my compiler or patches?

Hi, He

0day robot has't applied previous 0001 and 0002 patches in this case
for it considered this patch as an individual one. Please ignore this
warning. 

Btw: You could try use git(>=2.9.0) format-patch --base=<commit> (or
--base=auto for convenience) to record what (public, well-known) commit
your patch series was built on.

Thanks,
Xiaolong
>
>Thanks,
>-He
>_______________________________________________
>kbuild-all mailing list
>kbuild-all@lists.01.org
>https://lists.01.org/mailman/listinfo/kbuild-all