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

This patch introduces support for sampling YMM registers via the
sample_simd_vec_reg_* fields.

Each YMM register consists of 4 u64 words, assembled from two halves:
XMM (the lower 2 u64 words) and YMMH (the upper 2 u64 words). Although
both XMM and YMMH data can be retrieved with a single xsaves instruction,
they are stored in separate locations. The perf_simd_reg_value() function
is responsible for assembling these halves into a complete YMM register
for output to userspace.

Additionally, sample_simd_vec_reg_qwords should be set to 4 to indicate
YMM sampling.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Co-developed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/core.c                |  8 ++++++++
 arch/x86/events/perf_event.h          |  9 +++++++++
 arch/x86/include/asm/perf_event.h     |  4 ++++
 arch/x86/include/uapi/asm/perf_regs.h |  6 ++++--
 arch/x86/kernel/perf_regs.c           | 10 +++++++++-
 5 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index bd47127fb84d..e80a392e30b0 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -720,6 +720,9 @@ int x86_pmu_hw_config(struct perf_event *event)
 			if (event_needs_xmm(event) &&
 			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_SSE))
 				return -EINVAL;
+			if (event_needs_ymm(event) &&
+			    !(x86_pmu.ext_regs_mask & XFEATURE_MASK_YMM))
+				return -EINVAL;
 		}
 	}
 
@@ -1844,6 +1847,7 @@ inline void x86_pmu_clear_perf_regs(struct pt_regs *regs)
 	struct x86_perf_regs *perf_regs = container_of(regs, struct x86_perf_regs, regs);
 
 	perf_regs->xmm_regs = NULL;
+	perf_regs->ymmh_regs = NULL;
 }
 
 static inline void __x86_pmu_sample_ext_regs(u64 mask)
@@ -1869,6 +1873,8 @@ static inline void x86_pmu_update_ext_regs(struct x86_perf_regs *perf_regs,
 
 	if (mask & XFEATURE_MASK_SSE)
 		perf_regs->xmm_space = xsave->i387.xmm_space;
+	if (mask & XFEATURE_MASK_YMM)
+		perf_regs->ymmh = get_xsave_addr(xsave, XFEATURE_YMM);
 }
 
 /*
@@ -1928,6 +1934,8 @@ static void x86_pmu_sample_extended_regs(struct perf_event *event,
 
 	if (event_needs_xmm(event))
 		mask |= XFEATURE_MASK_SSE;
+	if (event_needs_ymm(event))
+		mask |= XFEATURE_MASK_YMM;
 
 	mask &= x86_pmu.ext_regs_mask;
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 02eea137e261..4f18ba6ef0c4 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -149,6 +149,15 @@ static inline bool event_needs_xmm(struct perf_event *event)
 	return false;
 }
 
+static inline bool event_needs_ymm(struct perf_event *event)
+{
+	if (event->attr.sample_simd_regs_enabled &&
+	    event->attr.sample_simd_vec_reg_qwords >= PERF_X86_YMM_QWORDS)
+		return true;
+
+	return false;
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 1f172740916c..bffe47851676 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -714,6 +714,10 @@ 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 342b08448138..eac11a29fce6 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -57,14 +57,16 @@ enum perf_event_x86_regs {
 
 enum {
 	PERF_X86_SIMD_XMM_REGS      = 16,
-	PERF_X86_SIMD_VEC_REGS_MAX  = PERF_X86_SIMD_XMM_REGS,
+	PERF_X86_SIMD_YMM_REGS      = 16,
+	PERF_X86_SIMD_VEC_REGS_MAX  = PERF_X86_SIMD_YMM_REGS,
 };
 
 #define PERF_X86_SIMD_VEC_MASK	GENMASK_ULL(PERF_X86_SIMD_VEC_REGS_MAX - 1, 0)
 
 enum {
 	PERF_X86_XMM_QWORDS      = 2,
-	PERF_X86_SIMD_QWORDS_MAX = PERF_X86_XMM_QWORDS,
+	PERF_X86_YMM_QWORDS      = 4,
+	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 9947a6b5c260..4062a679cc5b 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -77,6 +77,8 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
+#define PERF_X86_YMMH_QWORDS	(PERF_X86_YMM_QWORDS / 2)
+
 u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 			u16 qwords_idx, bool pred)
 {
@@ -95,6 +97,11 @@ u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
 			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;
@@ -111,7 +118,8 @@ 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;
-- 
2.34.1