[PATCH v2 0/4] KVM: x86/pmu: Refactoring code by reusing pmc->eventsel for fixed_counters

[PATCH v2 0/4] KVM: x86/pmu: Refactoring code by reusing pmc->eventsel for fixed_counters

[Like Xu]

Hi,

This patch set is essentially triggered by Jim's patch set[1]
(especially patch 01 and 04).

The new idea to set up and maintain pmc->eventsel for fixed counters.
This would unify all fixed/gp code logic based on the same semantics
"pmc->eventsel". (I demonstrated this in patch 01-03, more can be done)

v1 -> v2 Changelog:
- Rename find_perf_hw_id() to pmc_perf_hw_id(); [Paolo]
- Add WARN_ON for amd_pmc_perf_hw_id(); [Paolo]
- Add pmc->intr to drop dummy need_overflow_intr(pmc); [Paolo]

Previous:
https://lore.kernel.org/kvm/20211116122030.4698-1-likexu@tencent.com/T/#t

[1] https://lore.kernel.org/kvm/96170437-1e00-7841-260e-39d181e7886d@gmail.com/T/#t

Please check each commit message for more details
and let me know if there is any room for improvement,

Thanks.

Like Xu (4):
  KVM: x86/pmu: Setup pmc->eventsel for fixed PMCs
  KVM: x86/pmu: Refactoring find_arch_event() to pmc_perf_hw_id()
  KVM: x86/pmu: Reuse pmc_perf_hw_id() and drop find_fixed_event()
  KVM: x86/pmu: Add pmc->intr to refactor kvm_perf_overflow{_intr}()

 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/pmu.c              | 58 +++++++++++++--------------------
 arch/x86/kvm/pmu.h              |  4 +--
 arch/x86/kvm/svm/pmu.c          | 19 +++++------
 arch/x86/kvm/vmx/pmu_intel.c    | 54 ++++++++++++++++++++----------
 5 files changed, 69 insertions(+), 67 deletions(-)

-- 
2.33.1

[PATCH v2 1/4] KVM: x86/pmu: Setup pmc->eventsel for fixed PMCs

[Like Xu]

From: Like Xu <likexu@tencent.com>

The current pmc->eventsel for fixed counter is underutilised. The
pmc->eventsel can be setup for all known available fixed counters
since we have mapping between fixed pmc index and
the intel_arch_events array.

Either gp or fixed counter, it will simplify the later checks for
consistency between eventsel and perf_hw_id.

Signed-off-by: Like Xu <likexu@tencent.com>
---
 arch/x86/kvm/vmx/pmu_intel.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 1b7456b2177b..b7ab5fd03681 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -459,6 +459,21 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 1;
 }
 
+static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu)
+{
+	size_t size = ARRAY_SIZE(fixed_pmc_events);
+	struct kvm_pmc *pmc;
+	u32 event;
+	int i;
+
+	for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
+		pmc = &pmu->fixed_counters[i];
+		event = fixed_pmc_events[array_index_nospec(i, size)];
+		pmc->eventsel = (intel_arch_events[event].unit_mask << 8) |
+			intel_arch_events[event].eventsel;
+	}
+}
+
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -506,6 +521,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			edx.split.bit_width_fixed, x86_pmu.bit_width_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
+		setup_fixed_pmc_eventsel(pmu);
 	}
 
 	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
-- 
2.33.1

[PATCH v2 2/4] KVM: x86/pmu: Refactoring find_arch_event() to pmc_perf_hw_id()

[Like Xu]

From: Like Xu <likexu@tencent.com>

The find_arch_event() returns a "unsigned int" value,
which is used by the pmc_reprogram_counter() to
program a PERF_TYPE_HARDWARE type perf_event.

The returned value is actually the kernel defined gernic
perf_hw_id, let's rename it to pmc_perf_hw_id() with simpler
incoming parameters for better self-explanation.

Signed-off-by: Like Xu <likexu@tencent.com>
---
 arch/x86/kvm/pmu.c           | 8 +-------
 arch/x86/kvm/pmu.h           | 3 +--
 arch/x86/kvm/svm/pmu.c       | 8 ++++----
 arch/x86/kvm/vmx/pmu_intel.c | 9 +++++----
 4 files changed, 11 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 09873f6488f7..3b3ccf5b1106 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -174,7 +174,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 {
 	unsigned config, type = PERF_TYPE_RAW;
-	u8 event_select, unit_mask;
 	struct kvm *kvm = pmc->vcpu->kvm;
 	struct kvm_pmu_event_filter *filter;
 	int i;
@@ -206,17 +205,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (!allow_event)
 		return;
 
-	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
-	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
-
 	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
 			  ARCH_PERFMON_EVENTSEL_INV |
 			  ARCH_PERFMON_EVENTSEL_CMASK |
 			  HSW_IN_TX |
 			  HSW_IN_TX_CHECKPOINTED))) {
-		config = kvm_x86_ops.pmu_ops->find_arch_event(pmc_to_pmu(pmc),
-						      event_select,
-						      unit_mask);
+		config = kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc);
 		if (config != PERF_COUNT_HW_MAX)
 			type = PERF_TYPE_HARDWARE;
 	}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 59d6b76203d5..dd7dbb1c5048 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -24,8 +24,7 @@ struct kvm_event_hw_type_mapping {
 };
 
 struct kvm_pmu_ops {
-	unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select,
-				    u8 unit_mask);
+	unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc);
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 871c426ec389..3c00a34457d7 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -134,10 +134,10 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	return &pmu->gp_counters[msr_to_index(msr)];
 }
 
-static unsigned amd_find_arch_event(struct kvm_pmu *pmu,
-				    u8 event_select,
-				    u8 unit_mask)
+static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc)
 {
+	u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
+	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++)
@@ -319,7 +319,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu)
 }
 
 struct kvm_pmu_ops amd_pmu_ops = {
-	.find_arch_event = amd_find_arch_event,
+	.pmc_perf_hw_id = amd_pmc_perf_hw_id,
 	.find_fixed_event = amd_find_fixed_event,
 	.pmc_is_enabled = amd_pmc_is_enabled,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index b7ab5fd03681..67a0188ecdc5 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -68,10 +68,11 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
 		reprogram_counter(pmu, bit);
 }
 
-static unsigned intel_find_arch_event(struct kvm_pmu *pmu,
-				      u8 event_select,
-				      u8 unit_mask)
+static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
 {
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+	u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
+	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++)
@@ -719,7 +720,7 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
 }
 
 struct kvm_pmu_ops intel_pmu_ops = {
-	.find_arch_event = intel_find_arch_event,
+	.pmc_perf_hw_id = intel_pmc_perf_hw_id,
 	.find_fixed_event = intel_find_fixed_event,
 	.pmc_is_enabled = intel_pmc_is_enabled,
 	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
-- 
2.33.1

[PATCH v2 3/4] KVM: x86/pmu: Reuse pmc_perf_hw_id() and drop find_fixed_event()

[Like Xu]

From: Like Xu <likexu@tencent.com>

Since we set the same semantic event value for the fixed counter in
pmc->eventsel, returning the perf_hw_id for the fixed counter via
find_fixed_event() can be painlessly replaced by pmc_perf_hw_id()
with the help of pmc_is_fixed() check.

Signed-off-by: Like Xu <likexu@tencent.com>
---
 arch/x86/kvm/pmu.c           |  2 +-
 arch/x86/kvm/pmu.h           |  1 -
 arch/x86/kvm/svm/pmu.c       | 11 ++++-------
 arch/x86/kvm/vmx/pmu_intel.c | 29 ++++++++++++++++-------------
 4 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 3b3ccf5b1106..b7a1ae28ab87 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -262,7 +262,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 
 	pmc->current_config = (u64)ctrl;
 	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
-			      kvm_x86_ops.pmu_ops->find_fixed_event(idx),
+			      kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc),
 			      !(en_field & 0x2), /* exclude user */
 			      !(en_field & 0x1), /* exclude kernel */
 			      pmi, false, false);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index dd7dbb1c5048..c91d9725aafd 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -25,7 +25,6 @@ struct kvm_event_hw_type_mapping {
 
 struct kvm_pmu_ops {
 	unsigned int (*pmc_perf_hw_id)(struct kvm_pmc *pmc);
-	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
 	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 3c00a34457d7..da8aa1e5bff0 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -140,6 +140,10 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc)
 	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 	int i;
 
+	/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */
+	if (WARN_ON(pmc_is_fixed(pmc)))
+		return PERF_COUNT_HW_MAX;
+
 	for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++)
 		if (amd_event_mapping[i].eventsel == event_select
 		    && amd_event_mapping[i].unit_mask == unit_mask)
@@ -151,12 +155,6 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc)
 	return amd_event_mapping[i].event_type;
 }
 
-/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */
-static unsigned amd_find_fixed_event(int idx)
-{
-	return PERF_COUNT_HW_MAX;
-}
-
 /* check if a PMC is enabled by comparing it against global_ctrl bits. Because
  * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE).
  */
@@ -320,7 +318,6 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu)
 
 struct kvm_pmu_ops amd_pmu_ops = {
 	.pmc_perf_hw_id = amd_pmc_perf_hw_id,
-	.find_fixed_event = amd_find_fixed_event,
 	.pmc_is_enabled = amd_pmc_is_enabled,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
 	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 67a0188ecdc5..72db4ffb7eb2 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -68,6 +68,19 @@ static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
 		reprogram_counter(pmu, bit);
 }
 
+static inline unsigned int intel_find_fixed_event(int idx)
+{
+	u32 event;
+	size_t size = ARRAY_SIZE(fixed_pmc_events);
+
+	if (idx >= size)
+		return PERF_COUNT_HW_MAX;
+
+	event = fixed_pmc_events[array_index_nospec(idx, size)];
+	return intel_arch_events[event].event_type;
+}
+
+
 static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -75,6 +88,9 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
 	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 	int i;
 
+	if (pmc_is_fixed(pmc))
+		return intel_find_fixed_event(pmc->idx - INTEL_PMC_IDX_FIXED);
+
 	for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++)
 		if (intel_arch_events[i].eventsel == event_select
 		    && intel_arch_events[i].unit_mask == unit_mask
@@ -87,18 +103,6 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
 	return intel_arch_events[i].event_type;
 }
 
-static unsigned intel_find_fixed_event(int idx)
-{
-	u32 event;
-	size_t size = ARRAY_SIZE(fixed_pmc_events);
-
-	if (idx >= size)
-		return PERF_COUNT_HW_MAX;
-
-	event = fixed_pmc_events[array_index_nospec(idx, size)];
-	return intel_arch_events[event].event_type;
-}
-
 /* check if a PMC is enabled by comparing it with globl_ctrl bits. */
 static bool intel_pmc_is_enabled(struct kvm_pmc *pmc)
 {
@@ -721,7 +725,6 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
 
 struct kvm_pmu_ops intel_pmu_ops = {
 	.pmc_perf_hw_id = intel_pmc_perf_hw_id,
-	.find_fixed_event = intel_find_fixed_event,
 	.pmc_is_enabled = intel_pmc_is_enabled,
 	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
 	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
-- 
2.33.1

[PATCH v2 4/4] KVM: x86/pmu: Add pmc->intr to refactor kvm_perf_overflow{_intr}()

[Like Xu]

From: Like Xu <likexu@tencent.com>

Depending on whether intr should be triggered or not, KVM registers
two different event overflow callbacks in the perf_event context.

The code skeleton of these two functions is very similar, so
the pmc->intr can be stored into pmc from pmc_reprogram_counter()
which provides smaller instructions footprint against the
u-architecture branch predictor.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Like Xu <likexu@tencent.com>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/pmu.c              | 48 ++++++++++++++-------------------
 2 files changed, 21 insertions(+), 28 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1fcb345bc107..9fa63499e77e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -496,6 +496,7 @@ struct kvm_pmc {
 	 */
 	u64 current_config;
 	bool is_paused;
+	bool intr;
 };
 
 struct kvm_pmu {
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index b7a1ae28ab87..9b52f18f56e0 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -62,36 +62,28 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
-		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
-		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
-	}
-}
+	/* Ignore counters that have been reprogrammed already. */
+	if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi))
+		return;
 
-static void kvm_perf_overflow_intr(struct perf_event *perf_event,
-				   struct perf_sample_data *data,
-				   struct pt_regs *regs)
-{
-	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
-	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+	__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
+	kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 
-	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
-		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
-		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+	if (!pmc->intr)
+		return;
 
-		/*
-		 * Inject PMI. If vcpu was in a guest mode during NMI PMI
-		 * can be ejected on a guest mode re-entry. Otherwise we can't
-		 * be sure that vcpu wasn't executing hlt instruction at the
-		 * time of vmexit and is not going to re-enter guest mode until
-		 * woken up. So we should wake it, but this is impossible from
-		 * NMI context. Do it from irq work instead.
-		 */
-		if (!kvm_is_in_guest())
-			irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
-		else
-			kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
-	}
+	/*
+	 * Inject PMI. If vcpu was in a guest mode during NMI PMI
+	 * can be ejected on a guest mode re-entry. Otherwise we can't
+	 * be sure that vcpu wasn't executing hlt instruction at the
+	 * time of vmexit and is not going to re-enter guest mode until
+	 * woken up. So we should wake it, but this is impossible from
+	 * NMI context. Do it from irq work instead.
+	 */
+	if (!kvm_is_in_guest())
+		irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
+	else
+		kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
 }
 
 static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
@@ -126,7 +118,6 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	}
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
-						 intr ? kvm_perf_overflow_intr :
 						 kvm_perf_overflow, pmc);
 	if (IS_ERR(event)) {
 		pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
@@ -138,6 +129,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	pmc_to_pmu(pmc)->event_count++;
 	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
 	pmc->is_paused = false;
+	pmc->intr = intr;
 }
 
 static void pmc_pause_counter(struct kvm_pmc *pmc)
-- 
2.33.1