[RFC PATCH V2 07/13] perf/x86: Move XMM to sample_simd_vec_regs

[kan.liang@linux.intel.com]

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

The XMM0-15 are SIMD registers. Move them from sample_regs to
sample_simd_vec_regs. Reject access to the extended space of the sample_regs
if the new sample_simd_vec_regs is used.

The perf_reg_value requires the abi to understand the layout of the
sample_regs. Add the abi information in the struct x86_perf_regs.

Implement the X86-specific perf_simd_reg_validate to validate the SIMD
registers configuration from the user tool. Only the XMM0-15 is
supported now. More registers will be added in the following patches.
Implement the X86-specific perf_simd_reg_value to retrieve the XMM
value.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/core.c                | 38 ++++++++++++++++++++-
 arch/x86/events/intel/ds.c            |  2 +-
 arch/x86/events/perf_event.h          | 12 +++++++
 arch/x86/include/asm/perf_event.h     |  1 +
 arch/x86/include/uapi/asm/perf_regs.h |  6 ++++
 arch/x86/kernel/perf_regs.c           | 49 ++++++++++++++++++++++++++-
 6 files changed, 105 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 899bd5680f6b..2515179ac664 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -710,6 +710,22 @@ int x86_pmu_hw_config(struct perf_event *event)
 				return -EINVAL;
 			if (!(x86_pmu.ext_regs_mask & X86_EXT_REGS_XMM))
 				return -EINVAL;
+			if (event->attr.sample_simd_regs_enabled)
+				return -EINVAL;
+		}
+
+		if (event_has_simd_regs(event)) {
+			if (!(event->pmu->capabilities & PERF_PMU_CAP_SIMD_REGS))
+				return -EINVAL;
+			/* Not require any vector registers but set width */
+			if (event->attr.sample_simd_vec_reg_qwords &&
+			    !event->attr.sample_simd_vec_reg_intr &&
+			    !event->attr.sample_simd_vec_reg_user)
+				return -EINVAL;
+			/* The vector registers set is not supported */
+			if (event->attr.sample_simd_vec_reg_qwords >= PERF_X86_XMM_QWORDS &&
+			    !(x86_pmu.ext_regs_mask & X86_EXT_REGS_XMM))
+				return -EINVAL;
 		}
 	}
 	return x86_setup_perfctr(event);
@@ -1785,6 +1801,16 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
 		data->dyn_size += sizeof(u64);
 		if (data->regs_user.regs)
 			data->dyn_size += hweight64(attr->sample_regs_user) * sizeof(u64);
+		if (attr->sample_simd_regs_enabled && data->regs_user.abi) {
+			/* num and qwords of vector and pred registers */
+			data->dyn_size += sizeof(u64);
+			/* data[] */
+			data->dyn_size += hweight64(attr->sample_simd_vec_reg_user) *
+					  sizeof(u64) *
+					  attr->sample_simd_vec_reg_qwords;
+			data->regs_user.abi |= PERF_SAMPLE_REGS_ABI_SIMD;
+		}
+		perf_regs->abi = data->regs_user.abi;
 		data->sample_flags |= PERF_SAMPLE_REGS_USER;
 	}
 
@@ -1794,10 +1820,20 @@ void x86_pmu_setup_regs_data(struct perf_event *event,
 		data->dyn_size += sizeof(u64);
 		if (data->regs_intr.regs)
 			data->dyn_size += hweight64(attr->sample_regs_intr) * sizeof(u64);
+		if (attr->sample_simd_regs_enabled && data->regs_intr.abi) {
+			/* num and qwords of vector and pred registers */
+			data->dyn_size += sizeof(u64);
+			/* data[] */
+			data->dyn_size += hweight64(attr->sample_simd_vec_reg_intr) *
+					  sizeof(u64) *
+					  attr->sample_simd_vec_reg_qwords;
+			data->regs_intr.abi |= PERF_SAMPLE_REGS_ABI_SIMD;
+		}
+		perf_regs->abi = data->regs_intr.abi;
 		data->sample_flags |= PERF_SAMPLE_REGS_INTR;
 	}
 
-	if (event_has_extended_regs(event)) {
+	if (event_needs_xmm(event)) {
 		perf_regs->xmm_regs = NULL;
 		mask |= XFEATURE_MASK_SSE;
 	}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8437730abfb7..849136bef336 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1415,7 +1415,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 	if (gprs || (attr->precise_ip < 2) || tsx_weight)
 		pebs_data_cfg |= PEBS_DATACFG_GP;
 
-	if (event_has_extended_regs(event))
+	if (event_needs_xmm(event))
 		pebs_data_cfg |= PEBS_DATACFG_XMMS;
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 37ed46cafa53..69964433a245 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -133,6 +133,18 @@ static inline bool is_acr_event_group(struct perf_event *event)
 	return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR);
 }
 
+static inline bool event_needs_xmm(struct perf_event *event)
+{
+	if (event->attr.sample_simd_regs_enabled &&
+	    event->attr.sample_simd_vec_reg_qwords >= PERF_X86_XMM_QWORDS)
+		return true;
+
+	if (!event->attr.sample_simd_regs_enabled &&
+	    event_has_extended_regs(event))
+		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 f36f04bc95f1..538219c59979 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -592,6 +592,7 @@ extern void perf_events_lapic_init(void);
 struct pt_regs;
 struct x86_perf_regs {
 	struct pt_regs	regs;
+	u64		abi;
 	union {
 		u64	*xmm_regs;
 		u32	*xmm_space;	/* for xsaves */
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index 7c9d2bb3833b..bd8af802f757 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -55,4 +55,10 @@ enum perf_event_x86_regs {
 
 #define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
 
+#define PERF_X86_SIMD_VEC_REGS_MAX	16
+#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
+
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 624703af80a1..638b9e186c50 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -63,6 +63,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 
 	if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
 		perf_regs = container_of(regs, struct x86_perf_regs, regs);
+		/* SIMD registers are moved to dedicated sample_simd_vec_reg */
+		if (perf_regs->abi & PERF_SAMPLE_REGS_ABI_SIMD)
+			return 0;
 		if (!perf_regs->xmm_regs)
 			return 0;
 		return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
@@ -74,6 +77,49 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
+u64 perf_simd_reg_value(struct pt_regs *regs, int idx,
+			u16 qwords_idx, bool pred)
+{
+	struct x86_perf_regs *perf_regs = container_of(regs, struct x86_perf_regs, regs);
+
+	if (pred)
+		return 0;
+
+	if (WARN_ON_ONCE(idx >= PERF_X86_SIMD_VEC_REGS_MAX ||
+			 qwords_idx >= PERF_X86_SIMD_QWORDS_MAX))
+		return 0;
+
+	if (qwords_idx < PERF_X86_XMM_QWORDS) {
+		if (!perf_regs->xmm_regs)
+			return 0;
+		return perf_regs->xmm_regs[idx * PERF_X86_XMM_QWORDS + qwords_idx];
+	}
+
+	return 0;
+}
+
+int perf_simd_reg_validate(u16 vec_qwords, u64 vec_mask,
+			   u16 pred_qwords, u32 pred_mask)
+{
+	/* pred_qwords implies sample_simd_{pred,vec}_reg_* are supported */
+	if (!pred_qwords)
+		return 0;
+
+	if (!vec_qwords) {
+		if (vec_mask)
+			return -EINVAL;
+	} else {
+		if (vec_qwords != PERF_X86_XMM_QWORDS)
+			return -EINVAL;
+		if (vec_mask & ~PERF_X86_SIMD_VEC_MASK)
+			return -EINVAL;
+	}
+	if (pred_mask)
+		return -EINVAL;
+
+	return 0;
+}
+
 #define PERF_REG_X86_RESERVED	(((1ULL << PERF_REG_X86_XMM0) - 1) & \
 				 ~((1ULL << PERF_REG_X86_MAX) - 1))
 
@@ -114,7 +160,8 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
+	/* The mask could be 0 if only the SIMD registers are interested */
+	if (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED))
 		return -EINVAL;
 
 	return 0;
-- 
2.38.1