[v3] Support vector and more extended registers in perf

[PATCH V3 08/17] perf/x86: Add YMM into sample_simd_vec_regs

Posted by kan.liang@linux.intel.com 1 month, 3 weeks ago

From: Kan Liang <kan.liang@linux.intel.com>

The YMM0-15 is composed of XMM and YMMH. It requires 2 XSAVE commands to
get the complete value. Internally, the XMM and YMMH are stored in
different structures, which follow the XSAVE format. But the output
dumps the YMM as a whole.

The qwords 4 imply YMM.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/core.c                | 13 +++++++++++++
 arch/x86/include/asm/perf_event.h     |  4 ++++
 arch/x86/include/uapi/asm/perf_regs.h |  4 +++-
 arch/x86/kernel/perf_regs.c           | 10 +++++++++-
 4 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 1789b91c95c6..aebd4e56dff1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -423,6 +423,9 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
 
 	if (valid_mask & XFEATURE_MASK_SSE)
 		perf_regs->xmm_space = xsave->i387.xmm_space;
+
+	if (valid_mask & XFEATURE_MASK_YMM)
+		perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
 }
 
 static void release_ext_regs_buffers(void)
@@ -725,6 +728,9 @@ int x86_pmu_hw_config(struct perf_event *event)
 			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_XMM_QWORDS &&
 			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_SSE))
 				return -EINVAL;
+			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS &&
+			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_YMM))
+				return -EINVAL;
 		}
 	}
 	return x86_setup_perfctr(event);
@@ -1837,6 +1843,13 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
 		mask |= XFEATURE_MASK_SSE;
 	}
 
+	if (attr->sample_simd_regs_enabled) {
+		if (attr->sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS) {
+			perf_regs->ymmh_regs = NULL;
+			mask |= XFEATURE_MASK_YMM;
+		}
+	}
+
 	mask &= ~ignore_mask;
 	if (mask)
 		x86_pmu_get_ext_regs(perf_regs, mask);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 538219c59979..81e3143fd91a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -597,6 +597,10 @@ struct x86_perf_regs {
 		u64	*xmm_regs;
 		u32	*xmm_space;	/* for xsaves */
 	};
+	union {
+		u64	*ymmh_regs;
+		struct ymmh_struct *ymmh;
+	};
 };
 
 extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index bd8af802f757..feb3e8f80761 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -59,6 +59,8 @@ enum perf_event_x86_regs {
 #define PERF_X86_SIMD_VEC_MASK		GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
 
 #define PERF_X86_XMM_QWORDS		2
-#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_XMM_QWORDS
+#define PERF_X86_YMM_QWORDS		4
+#define PERF_X86_YMMH_QWORDS		(PERF_X86_YMM_QWORDS / 2)
+#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_YMM_QWORDS
 
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 397357c5896b..d94bc687e4bf 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -66,6 +66,9 @@ void perf_simd_reg_check(struct pt_regs *regs,
 	if (*vec_qwords >= PERF_X86_XMM_QWORDS && !perf_regs->xmm_regs)
 		*nr_vectors = 0;
 
+	if (*vec_qwords >= PERF_X86_YMM_QWORDS && !perf_regs->xmm_regs)
+		*vec_qwords = PERF_X86_XMM_QWORDS;
+
 	*nr_pred = 0;
 }
 
@@ -105,6 +108,10 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 		if (!perf_regs->xmm_regs)
 			return 0;
 		return perf_regs->xmm_regs[idx * PERF_X86_XMM_QWORDS + qwords_idx];
+	} else if (qwords_idx < PERF_X86_YMM_QWORDS) {
+		if (!perf_regs->ymmh_regs)
+			return 0;
+		return perf_regs->ymmh_regs[idx * PERF_X86_YMMH_QWORDS + qwords_idx - PERF_X86_XMM_QWORDS];
 	}
 
 	return 0;
@@ -121,7 +128,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
 		if (vec_mask)
 			return -EINVAL;
 	} else {
-		if (vec_qwords != PERF_X86_XMM_QWORDS)
+		if (vec_qwords != PERF_X86_XMM_QWORDS &&
+		    vec_qwords != PERF_X86_YMM_QWORDS)
 			return -EINVAL;
 		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
 			return -EINVAL;
-- 
2.38.1

Re: [PATCH V3 08/17] perf/x86: Add YMM into sample_simd_vec_regs

Posted by Mi, Dapeng 1 month, 2 weeks ago

On 8/16/2025 5:34 AM, kan.liang@linux.intel.com wrote:
> From: Kan Liang <kan.liang@linux.intel.com>
>
> The YMM0-15 is composed of XMM and YMMH. It requires 2 XSAVE commands to
> get the complete value. Internally, the XMM and YMMH are stored in
> different structures, which follow the XSAVE format. But the output
> dumps the YMM as a whole.
>
> The qwords 4 imply YMM.
>
> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
> ---
>  arch/x86/events/core.c                | 13 +++++++++++++
>  arch/x86/include/asm/perf_event.h     |  4 ++++
>  arch/x86/include/uapi/asm/perf_regs.h |  4 +++-
>  arch/x86/kernel/perf_regs.c           | 10 +++++++++-
>  4 files changed, 29 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
> index 1789b91c95c6..aebd4e56dff1 100644
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -423,6 +423,9 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
>  
>  	if (valid_mask & XFEATURE_MASK_SSE)
>  		perf_regs->xmm_space = xsave->i387.xmm_space;
> +
> +	if (valid_mask & XFEATURE_MASK_YMM)
> +		perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
>  }
>  
>  static void release_ext_regs_buffers(void)
> @@ -725,6 +728,9 @@ int x86_pmu_hw_config(struct perf_event *event)
>  			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_XMM_QWORDS &&
>  			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_SSE))
>  				return -EINVAL;
> +			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS &&
> +			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_YMM))
> +				return -EINVAL;
>  		}
>  	}
>  	return x86_setup_perfctr(event);
> @@ -1837,6 +1843,13 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
>  		mask |= XFEATURE_MASK_SSE;
>  	}
>  
> +	if (attr->sample_simd_regs_enabled) {
> +		if (attr->sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS) {
> +			perf_regs->ymmh_regs = NULL;
> +			mask |= XFEATURE_MASK_YMM;
> +		}
> +	}
> +
>  	mask &= ~ignore_mask;
>  	if (mask)
>  		x86_pmu_get_ext_regs(perf_regs, mask);
> diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
> index 538219c59979..81e3143fd91a 100644
> --- a/arch/x86/include/asm/perf_event.h
> +++ b/arch/x86/include/asm/perf_event.h
> @@ -597,6 +597,10 @@ struct x86_perf_regs {
>  		u64	*xmm_regs;
>  		u32	*xmm_space;	/* for xsaves */
>  	};
> +	union {
> +		u64	*ymmh_regs;
> +		struct ymmh_struct *ymmh;
> +	};
>  };
>  
>  extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
> diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
> index bd8af802f757..feb3e8f80761 100644
> --- a/arch/x86/include/uapi/asm/perf_regs.h
> +++ b/arch/x86/include/uapi/asm/perf_regs.h
> @@ -59,6 +59,8 @@ enum perf_event_x86_regs {
>  #define PERF_X86_SIMD_VEC_MASK		GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
>  
>  #define PERF_X86_XMM_QWORDS		2
> -#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_XMM_QWORDS
> +#define PERF_X86_YMM_QWORDS		4
> +#define PERF_X86_YMMH_QWORDS		(PERF_X86_YMM_QWORDS / 2)
> +#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_YMM_QWORDS
>  
>  #endif /* _ASM_X86_PERF_REGS_H */
> diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
> index 397357c5896b..d94bc687e4bf 100644
> --- a/arch/x86/kernel/perf_regs.c
> +++ b/arch/x86/kernel/perf_regs.c
> @@ -66,6 +66,9 @@ void perf_simd_reg_check(struct pt_regs *regs,
>  	if (*vec_qwords >= PERF_X86_XMM_QWORDS && !perf_regs->xmm_regs)
>  		*nr_vectors = 0;
>  
> +	if (*vec_qwords >= PERF_X86_YMM_QWORDS && !perf_regs->xmm_regs)

should be "!perf_regs->ymmh_regs"?


> +		*vec_qwords = PERF_X86_XMM_QWORDS;
> +
>  	*nr_pred = 0;
>  }
>  
> @@ -105,6 +108,10 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
>  		if (!perf_regs->xmm_regs)
>  			return 0;
>  		return perf_regs->xmm_regs[idx * PERF_X86_XMM_QWORDS + qwords_idx];
> +	} else if (qwords_idx < PERF_X86_YMM_QWORDS) {
> +		if (!perf_regs->ymmh_regs)
> +			return 0;
> +		return perf_regs->ymmh_regs[idx * PERF_X86_YMMH_QWORDS + qwords_idx - PERF_X86_XMM_QWORDS];
>  	}
>  
>  	return 0;
> @@ -121,7 +128,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
>  		if (vec_mask)
>  			return -EINVAL;
>  	} else {
> -		if (vec_qwords != PERF_X86_XMM_QWORDS)
> +		if (vec_qwords != PERF_X86_XMM_QWORDS &&
> +		    vec_qwords != PERF_X86_YMM_QWORDS)
>  			return -EINVAL;
>  		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
>  			return -EINVAL;

Re: [PATCH V3 08/17] perf/x86: Add YMM into sample_simd_vec_regs

Posted by Liang, Kan 1 month, 2 weeks ago


On 2025-08-20 2:59 a.m., Mi, Dapeng wrote:
> 
> On 8/16/2025 5:34 AM, kan.liang@linux.intel.com wrote:
>> From: Kan Liang <kan.liang@linux.intel.com>
>>
>> The YMM0-15 is composed of XMM and YMMH. It requires 2 XSAVE commands to
>> get the complete value. Internally, the XMM and YMMH are stored in
>> different structures, which follow the XSAVE format. But the output
>> dumps the YMM as a whole.
>>
>> The qwords 4 imply YMM.
>>
>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
>> ---
>>  arch/x86/events/core.c                | 13 +++++++++++++
>>  arch/x86/include/asm/perf_event.h     |  4 ++++
>>  arch/x86/include/uapi/asm/perf_regs.h |  4 +++-
>>  arch/x86/kernel/perf_regs.c           | 10 +++++++++-
>>  4 files changed, 29 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
>> index 1789b91c95c6..aebd4e56dff1 100644
>> --- a/arch/x86/events/core.c
>> +++ b/arch/x86/events/core.c
>> @@ -423,6 +423,9 @@ static void x86_pmu_get_ext_regs(struct x86_perf_regs *perf_regs, u64 mask)
>>  
>>  	if (valid_mask & XFEATURE_MASK_SSE)
>>  		perf_regs->xmm_space = xsave->i387.xmm_space;
>> +
>> +	if (valid_mask & XFEATURE_MASK_YMM)
>> +		perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
>>  }
>>  
>>  static void release_ext_regs_buffers(void)
>> @@ -725,6 +728,9 @@ int x86_pmu_hw_config(struct perf_event *event)
>>  			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_XMM_QWORDS &&
>>  			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_SSE))
>>  				return -EINVAL;
>> +			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS &&
>> +			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_YMM))
>> +				return -EINVAL;
>>  		}
>>  	}
>>  	return x86_setup_perfctr(event);
>> @@ -1837,6 +1843,13 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
>>  		mask |= XFEATURE_MASK_SSE;
>>  	}
>>  
>> +	if (attr->sample_simd_regs_enabled) {
>> +		if (attr->sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS) {
>> +			perf_regs->ymmh_regs = NULL;
>> +			mask |= XFEATURE_MASK_YMM;
>> +		}
>> +	}
>> +
>>  	mask &= ~ignore_mask;
>>  	if (mask)
>>  		x86_pmu_get_ext_regs(perf_regs, mask);
>> diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
>> index 538219c59979..81e3143fd91a 100644
>> --- a/arch/x86/include/asm/perf_event.h
>> +++ b/arch/x86/include/asm/perf_event.h
>> @@ -597,6 +597,10 @@ struct x86_perf_regs {
>>  		u64	*xmm_regs;
>>  		u32	*xmm_space;	/* for xsaves */
>>  	};
>> +	union {
>> +		u64	*ymmh_regs;
>> +		struct ymmh_struct *ymmh;
>> +	};
>>  };
>>  
>>  extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
>> diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
>> index bd8af802f757..feb3e8f80761 100644
>> --- a/arch/x86/include/uapi/asm/perf_regs.h
>> +++ b/arch/x86/include/uapi/asm/perf_regs.h
>> @@ -59,6 +59,8 @@ enum perf_event_x86_regs {
>>  #define PERF_X86_SIMD_VEC_MASK		GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
>>  
>>  #define PERF_X86_XMM_QWORDS		2
>> -#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_XMM_QWORDS
>> +#define PERF_X86_YMM_QWORDS		4
>> +#define PERF_X86_YMMH_QWORDS		(PERF_X86_YMM_QWORDS / 2)
>> +#define PERF_X86_SIMD_QWORDS_MAX	PERF_X86_YMM_QWORDS
>>  
>>  #endif /* _ASM_X86_PERF_REGS_H */
>> diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
>> index 397357c5896b..d94bc687e4bf 100644
>> --- a/arch/x86/kernel/perf_regs.c
>> +++ b/arch/x86/kernel/perf_regs.c
>> @@ -66,6 +66,9 @@ void perf_simd_reg_check(struct pt_regs *regs,
>>  	if (*vec_qwords >= PERF_X86_XMM_QWORDS && !perf_regs->xmm_regs)
>>  		*nr_vectors = 0;
>>  
>> +	if (*vec_qwords >= PERF_X86_YMM_QWORDS && !perf_regs->xmm_regs)
> 
> should be "!perf_regs->ymmh_regs"?

Oops, good catch.

Thansk,
Kan

> 
> 
>> +		*vec_qwords = PERF_X86_XMM_QWORDS;
>> +
>>  	*nr_pred = 0;
>>  }
>>  
>> @@ -105,6 +108,10 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
>>  		if (!perf_regs->xmm_regs)
>>  			return 0;
>>  		return perf_regs->xmm_regs[idx * PERF_X86_XMM_QWORDS + qwords_idx];
>> +	} else if (qwords_idx < PERF_X86_YMM_QWORDS) {
>> +		if (!perf_regs->ymmh_regs)
>> +			return 0;
>> +		return perf_regs->ymmh_regs[idx * PERF_X86_YMMH_QWORDS + qwords_idx - PERF_X86_XMM_QWORDS];
>>  	}
>>  
>>  	return 0;
>> @@ -121,7 +128,8 @@ int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
>>  		if (vec_mask)
>>  			return -EINVAL;
>>  	} else {
>> -		if (vec_qwords != PERF_X86_XMM_QWORDS)
>> +		if (vec_qwords != PERF_X86_XMM_QWORDS &&
>> +		    vec_qwords != PERF_X86_YMM_QWORDS)
>>  			return -EINVAL;
>>  		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
>>  			return -EINVAL;