kvmarm.lists.cs.columbia.edu archive mirror
 help / color / mirror / Atom feed
* [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters
@ 2019-05-22 15:30 Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 1/6] KVM: arm/arm64: rename kvm_pmu_{enable/disable}_counter functions Andrew Murray
                   ` (5 more replies)
  0 siblings, 6 replies; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

ARMv8 provides support for chained PMU counters, where an event type
of 0x001E is set for odd-numbered counters, the event counter will
increment by one for each overflow of the preceding even-numbered
counter. Let's emulate this in KVM by creating a 64 bit perf counter
when a user chains two emulated counters together.

Testing has been performed by hard-coding hwc->sample_period in
__hw_perf_event_init (arm_pmu.c) to a small value, this results in
regular overflows (for non sampling events). The following command
was then used to measure chained and non-chained instruction cycles:

perf stat -e armv8_pmuv3/long=1,inst_retired/u \
          -e armv8_pmuv3/long=0,inst_retired/u dd if=/dev/zero bs=1M \
          count=10 | gzip > /dev/null

The reported values were identical (and for non-chained was in the
same ballpark when running on a kernel without this patchset). Debug
was added to verify that the guest received overflow interrupts for
the chain counter.

The test was also repeated using the cycle counter (cycle:u).

For chained events we only support generating an overflow interrupt
on the high counter. We use the attributes of the low counter to
determine the attributes of the perf event.

Changes since v7:

 - Remove pmc->bitmask

 - Remove a couple of instances of using kvm_pmu_get_canonical_pmc
   when not needed

 - Remove unused perf_event variable

Changes since v6:

 - Drop kvm_pmu_{get,set}_perf_event

 - Avoid duplicate work by using kvm_pmu_get_pair_counter_value inside
   kvm_pmu_stop_counter

 - Use GENMASK for 64bit mask

Changes since v5:

 - Use kvm_pmu_pmc_is_high_counter instead of open coding

 - Rename kvm_pmu_event_is_chained to kvm_pmu_idx_has_chain_evtype

 - Use kvm_pmu_get_canonical_pmc only where needed and reintroduce
   the kvm_pmu_{set, get}_perf_event functions

 - Drop masking of counter in kvm_pmu_get_pair_counter_value

 - Only initialise pmc once in kvm_pmu_create_perf_event and other
   minor changes.

Changes since v4:

 - Track pairs of chained counters with a bitmap instead of using
   a struct kvm_pmc_pair.

 - Rebase onto kvmarm/queue

Changes since v3:

 - Simplify approach by not creating events lazily and by introducing
   a struct kvm_pmc_pair to represent the relationship between
   adjacent counters.

 - Rebase onto v5.1-rc2

Changes since v2:

 - Rebased onto v5.0-rc7

 - Add check for cycle counter in correct patch

 - Minor style, naming and comment changes

 - Extract armv8pmu_evtype_is_chain from arch/arm64/kernel/perf_event.c
   into a common header that KVM can use

Changes since v1:

 - Rename kvm_pmu_{enable,disable}_counter to reflect that they can
   operate on multiple counters at once and use these functions where
   possible

 - Fix bugs with overflow handing, kvm_pmu_get_counter_value did not
   take into consideration the perf counter value overflowing the low
   counter

 - Ensure PMCCFILTR_EL0 is used when operating on the cycle counter

 - Rename kvm_pmu_reenable_enabled_{pair, single} and similar

 - Always create perf event disabled to simplify logic elsewhere

 - Move PMCNTENSET_EL0 test to kvm_pmu_enable_counter_mask


Andrew Murray (6):
  KVM: arm/arm64: rename kvm_pmu_{enable/disable}_counter functions
  KVM: arm/arm64: extract duplicated code to own function
  KVM: arm/arm64: re-create event when setting counter value
  arm64: perf: extract chain helper into header
  KVM: arm/arm64: remove pmc->bitmask
  KVM: arm/arm64: support chained PMU counters

 arch/arm64/include/asm/perf_event.h |   5 +
 arch/arm64/kernel/perf_event.c      |   2 +-
 arch/arm64/kvm/sys_regs.c           |   4 +-
 include/kvm/arm_pmu.h               |  11 +-
 virt/kvm/arm/pmu.c                  | 335 ++++++++++++++++++++++------
 5 files changed, 282 insertions(+), 75 deletions(-)

-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH v8 1/6] KVM: arm/arm64: rename kvm_pmu_{enable/disable}_counter functions
  2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
@ 2019-05-22 15:30 ` Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 2/6] KVM: arm/arm64: extract duplicated code to own function Andrew Murray
                   ` (4 subsequent siblings)
  5 siblings, 0 replies; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

The kvm_pmu_{enable/disable}_counter functions can enabled/disable
multiple counters at once as they operate on a bitmask. Let's
make this clearer by renaming the function.

Suggested-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
 arch/arm64/kvm/sys_regs.c |  4 ++--
 include/kvm/arm_pmu.h     |  8 ++++----
 virt/kvm/arm/pmu.c        | 12 ++++++------
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 9d02643bc601..8e98fb173ed3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -876,12 +876,12 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		if (r->Op2 & 0x1) {
 			/* accessing PMCNTENSET_EL0 */
 			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
-			kvm_pmu_enable_counter(vcpu, val);
+			kvm_pmu_enable_counter_mask(vcpu, val);
 			kvm_vcpu_pmu_restore_guest(vcpu);
 		} else {
 			/* accessing PMCNTENCLR_EL0 */
 			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
-			kvm_pmu_disable_counter(vcpu, val);
+			kvm_pmu_disable_counter_mask(vcpu, val);
 		}
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index f87fe20fcb05..b73f31baca52 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -46,8 +46,8 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
-void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
-void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
 bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu);
@@ -83,8 +83,8 @@ static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 }
 static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
-static inline void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val) {}
-static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
 static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 1c5b76c46e26..c5a722ad283f 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -135,13 +135,13 @@ u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 }
 
 /**
- * kvm_pmu_enable_counter - enable selected PMU counter
+ * kvm_pmu_enable_counter_mask - enable selected PMU counters
  * @vcpu: The vcpu pointer
  * @val: the value guest writes to PMCNTENSET register
  *
  * Call perf_event_enable to start counting the perf event
  */
-void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
+void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -164,13 +164,13 @@ void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
 }
 
 /**
- * kvm_pmu_disable_counter - disable selected PMU counter
+ * kvm_pmu_disable_counter_mask - disable selected PMU counters
  * @vcpu: The vcpu pointer
  * @val: the value guest writes to PMCNTENCLR register
  *
  * Call perf_event_disable to stop counting the perf event
  */
-void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val)
+void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
@@ -347,10 +347,10 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 
 	mask = kvm_pmu_valid_counter_mask(vcpu);
 	if (val & ARMV8_PMU_PMCR_E) {
-		kvm_pmu_enable_counter(vcpu,
+		kvm_pmu_enable_counter_mask(vcpu,
 		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
 	} else {
-		kvm_pmu_disable_counter(vcpu, mask);
+		kvm_pmu_disable_counter_mask(vcpu, mask);
 	}
 
 	if (val & ARMV8_PMU_PMCR_C)
-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply related	[flat|nested] 14+ messages in thread

* [PATCH v8 2/6] KVM: arm/arm64: extract duplicated code to own function
  2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 1/6] KVM: arm/arm64: rename kvm_pmu_{enable/disable}_counter functions Andrew Murray
@ 2019-05-22 15:30 ` Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 3/6] KVM: arm/arm64: re-create event when setting counter value Andrew Murray
                   ` (3 subsequent siblings)
  5 siblings, 0 replies; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

Let's reduce code duplication by extracting common code to its own
function.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
 virt/kvm/arm/pmu.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index c5a722ad283f..6e7c179103a6 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -64,6 +64,19 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 	__vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
 }
 
+/**
+ * kvm_pmu_release_perf_event - remove the perf event
+ * @pmc: The PMU counter pointer
+ */
+static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		perf_event_disable(pmc->perf_event);
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+	}
+}
+
 /**
  * kvm_pmu_stop_counter - stop PMU counter
  * @pmc: The PMU counter pointer
@@ -79,9 +92,7 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
 		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
 		__vcpu_sys_reg(vcpu, reg) = counter;
-		perf_event_disable(pmc->perf_event);
-		perf_event_release_kernel(pmc->perf_event);
-		pmc->perf_event = NULL;
+		kvm_pmu_release_perf_event(pmc);
 	}
 }
 
@@ -112,15 +123,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
-		struct kvm_pmc *pmc = &pmu->pmc[i];
-
-		if (pmc->perf_event) {
-			perf_event_disable(pmc->perf_event);
-			perf_event_release_kernel(pmc->perf_event);
-			pmc->perf_event = NULL;
-		}
-	}
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+		kvm_pmu_release_perf_event(&pmu->pmc[i]);
 }
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply related	[flat|nested] 14+ messages in thread

* [PATCH v8 3/6] KVM: arm/arm64: re-create event when setting counter value
  2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 1/6] KVM: arm/arm64: rename kvm_pmu_{enable/disable}_counter functions Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 2/6] KVM: arm/arm64: extract duplicated code to own function Andrew Murray
@ 2019-05-22 15:30 ` Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 4/6] arm64: perf: extract chain helper into header Andrew Murray
                   ` (2 subsequent siblings)
  5 siblings, 0 replies; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

The perf event sample_period is currently set based upon the current
counter value, when PMXEVTYPER is written to and the perf event is created.
However the user may choose to write the type before the counter value in
which case sample_period will be set incorrectly. Let's instead decouple
event creation from PMXEVTYPER and (re)create the event in either
suitation.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
 virt/kvm/arm/pmu.c | 42 +++++++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 9 deletions(-)

diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 6e7c179103a6..ae1e886d4a1a 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -24,6 +24,7 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
 
+static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
 /**
  * kvm_pmu_get_counter_value - get PMU counter value
  * @vcpu: The vcpu pointer
@@ -62,6 +63,9 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
 	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
 	__vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
+
+	/* Recreate the perf event to reflect the updated sample_period */
+	kvm_pmu_create_perf_event(vcpu, select_idx);
 }
 
 /**
@@ -378,23 +382,21 @@ static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
 }
 
 /**
- * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
+ * kvm_pmu_create_perf_event - create a perf event for a counter
  * @vcpu: The vcpu pointer
- * @data: The data guest writes to PMXEVTYPER_EL0
  * @select_idx: The number of selected counter
- *
- * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an
- * event with given hardware event number. Here we call perf_event API to
- * emulate this action and create a kernel perf event for it.
  */
-void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
-				    u64 select_idx)
+static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
 	struct perf_event *event;
 	struct perf_event_attr attr;
-	u64 eventsel, counter;
+	u64 eventsel, counter, reg, data;
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
+	data = __vcpu_sys_reg(vcpu, reg);
 
 	kvm_pmu_stop_counter(vcpu, pmc);
 	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
@@ -431,6 +433,28 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	pmc->perf_event = event;
 }
 
+/**
+ * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
+ * @vcpu: The vcpu pointer
+ * @data: The data guest writes to PMXEVTYPER_EL0
+ * @select_idx: The number of selected counter
+ *
+ * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an
+ * event with given hardware event number. Here we call perf_event API to
+ * emulate this action and create a kernel perf event for it.
+ */
+void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
+				    u64 select_idx)
+{
+	u64 reg, event_type = data & ARMV8_PMU_EVTYPE_MASK;
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
+
+	__vcpu_sys_reg(vcpu, reg) = event_type;
+	kvm_pmu_create_perf_event(vcpu, select_idx);
+}
+
 bool kvm_arm_support_pmu_v3(void)
 {
 	/*
-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply related	[flat|nested] 14+ messages in thread

* [PATCH v8 4/6] arm64: perf: extract chain helper into header
  2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
                   ` (2 preceding siblings ...)
  2019-05-22 15:30 ` [PATCH v8 3/6] KVM: arm/arm64: re-create event when setting counter value Andrew Murray
@ 2019-05-22 15:30 ` Andrew Murray
  2019-06-10 11:39   ` Will Deacon
  2019-05-22 15:30 ` [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask Andrew Murray
  2019-05-22 15:30 ` [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters Andrew Murray
  5 siblings, 1 reply; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

The ARMv8 Performance Monitors Extension includes an architectural
event type named CHAIN which allows for chaining counters together.

Let's extract the test for this event into a header file such that
other users, such as KVM (for PMU emulation) can make use of.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
---
 arch/arm64/include/asm/perf_event.h | 5 +++++
 arch/arm64/kernel/perf_event.c      | 2 +-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index c593761ba61c..cd13f3fd1055 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -219,6 +219,11 @@
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
 
+static inline bool armv8pmu_evtype_is_chain(u64 evtype)
+{
+	return (evtype == ARMV8_PMUV3_PERFCTR_CHAIN);
+}
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 314b1adedf06..265bd835a724 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -879,7 +879,7 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 static int armv8pmu_filter_match(struct perf_event *event)
 {
 	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
-	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
+	return !armv8pmu_evtype_is_chain(evtype);
 }
 
 static void armv8pmu_reset(void *info)
-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply related	[flat|nested] 14+ messages in thread

* [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask
  2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
                   ` (3 preceding siblings ...)
  2019-05-22 15:30 ` [PATCH v8 4/6] arm64: perf: extract chain helper into header Andrew Murray
@ 2019-05-22 15:30 ` Andrew Murray
  2019-05-22 16:07   ` Marc Zyngier
  2019-05-22 15:30 ` [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters Andrew Murray
  5 siblings, 1 reply; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

We currently use pmc->bitmask to determine the width of the pmc - however
it's superfluous as the pmc index already describes if the pmc is a cycle
counter or event counter. The architecture clearly describes the widths of
these counters.

Let's remove the bitmask to simplify the code.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
---
 include/kvm/arm_pmu.h |  1 -
 virt/kvm/arm/pmu.c    | 15 +++++----------
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index b73f31baca52..2f0e28dc5a9e 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -28,7 +28,6 @@
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
 	struct perf_event *perf_event;
-	u64 bitmask;
 };
 
 struct kvm_pmu {
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index ae1e886d4a1a..c4e2bc213617 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -47,7 +47,10 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 		counter += perf_event_read_value(pmc->perf_event, &enabled,
 						 &running);
 
-	return counter & pmc->bitmask;
+	if (select_idx != ARMV8_PMU_CYCLE_IDX)
+		counter = lower_32_bits(counter);
+
+	return counter;
 }
 
 /**
@@ -113,7 +116,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
 		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
 		pmu->pmc[i].idx = i;
-		pmu->pmc[i].bitmask = 0xffffffffUL;
 	}
 }
 
@@ -348,8 +350,6 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
  */
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
 	u64 mask;
 	int i;
 
@@ -368,11 +368,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
 			kvm_pmu_set_counter_value(vcpu, i, 0);
 	}
-
-	if (val & ARMV8_PMU_PMCR_LC) {
-		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
-		pmc->bitmask = 0xffffffffffffffffUL;
-	}
 }
 
 static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
@@ -420,7 +415,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 
 	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
 	/* The initial sample period (overflow count) of an event. */
-	attr.sample_period = (-counter) & pmc->bitmask;
+	attr.sample_period = (-counter) & GENMASK(31, 0);
 
 	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_pmu_perf_overflow, pmc);
-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply related	[flat|nested] 14+ messages in thread

* [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters
  2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
                   ` (4 preceding siblings ...)
  2019-05-22 15:30 ` [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask Andrew Murray
@ 2019-05-22 15:30 ` Andrew Murray
  2019-06-10 10:21   ` Julien Thierry
  2019-06-10 16:05   ` Suzuki K Poulose
  5 siblings, 2 replies; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 15:30 UTC (permalink / raw)
  To: Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

ARMv8 provides support for chained PMU counters, where an event type
of 0x001E is set for odd-numbered counters, the event counter will
increment by one for each overflow of the preceding even-numbered
counter. Let's emulate this in KVM by creating a 64 bit perf counter
when a user chains two emulated counters together.

For chained events we only support generating an overflow interrupt
on the high counter. We use the attributes of the low counter to
determine the attributes of the perf event.

Suggested-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Andrew Murray <andrew.murray@arm.com>
---
 include/kvm/arm_pmu.h |   2 +
 virt/kvm/arm/pmu.c    | 248 ++++++++++++++++++++++++++++++++++++------
 2 files changed, 215 insertions(+), 35 deletions(-)

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 2f0e28dc5a9e..589f49ed8cf8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -22,6 +22,7 @@
 #include <asm/perf_event.h>
 
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
+#define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
 
 #ifdef CONFIG_KVM_ARM_PMU
 
@@ -33,6 +34,7 @@ struct kvm_pmc {
 struct kvm_pmu {
 	int irq_num;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
+	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 	bool ready;
 	bool created;
 	bool irq_level;
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index c4e2bc213617..796bcf76911f 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -25,29 +25,129 @@
 #include <kvm/arm_vgic.h>
 
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
+
+#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
+
+static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu;
+	struct kvm_vcpu_arch *vcpu_arch;
+
+	pmc -= pmc->idx;
+	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
+	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
+	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+}
+
 /**
- * kvm_pmu_get_counter_value - get PMU counter value
+ * kvm_pmu_pmc_is_chained - determine if the pmc is chained
+ * @pmc: The PMU counter pointer
+ */
+static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc)
+{
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+
+	return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+}
+
+/**
+ * kvm_pmu_pmc_is_high_counter - determine if select_idx is a high/low counter
+ * @select_idx: The counter index
+ */
+static bool kvm_pmu_pmc_is_high_counter(u64 select_idx)
+{
+	return select_idx & 0x1;
+}
+
+/**
+ * kvm_pmu_get_canonical_pmc - obtain the canonical pmc
+ * @pmc: The PMU counter pointer
+ *
+ * When a pair of PMCs are chained together we use the low counter (canonical)
+ * to hold the underlying perf event.
+ */
+static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
+{
+	if (kvm_pmu_pmc_is_chained(pmc) &&
+	    kvm_pmu_pmc_is_high_counter(pmc->idx))
+		return pmc - 1;
+
+	return pmc;
+}
+
+/**
+ * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
  * @vcpu: The vcpu pointer
  * @select_idx: The counter index
  */
-u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	u64 counter, reg, enabled, running;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	u64 eventsel, reg;
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
-	counter = __vcpu_sys_reg(vcpu, reg);
+	select_idx |= 0x1;
+
+	if (select_idx == ARMV8_PMU_CYCLE_IDX)
+		return false;
 
-	/* The real counter value is equal to the value of counter register plus
+	reg = PMEVTYPER0_EL0 + select_idx;
+	eventsel = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_EVENT;
+
+	return armv8pmu_evtype_is_chain(eventsel);
+}
+
+/**
+ * kvm_pmu_get_pair_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @pmc: The PMU counter pointer
+ */
+static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
+					  struct kvm_pmc *pmc)
+{
+	u64 counter, counter_high, reg, enabled, running;
+
+	if (kvm_pmu_pmc_is_chained(pmc)) {
+		pmc = kvm_pmu_get_canonical_pmc(pmc);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+
+		counter = __vcpu_sys_reg(vcpu, reg);
+		counter_high = __vcpu_sys_reg(vcpu, reg + 1);
+
+		counter = lower_32_bits(counter) | (counter_high << 32);
+	} else {
+		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
+		counter = __vcpu_sys_reg(vcpu, reg);
+	}
+
+	/*
+	 * The real counter value is equal to the value of counter register plus
 	 * the value perf event counts.
 	 */
 	if (pmc->perf_event)
 		counter += perf_event_read_value(pmc->perf_event, &enabled,
 						 &running);
 
-	if (select_idx != ARMV8_PMU_CYCLE_IDX)
+	return counter;
+}
+
+/**
+ * kvm_pmu_get_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	u64 counter;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_pmc_is_chained(pmc) &&
+	    kvm_pmu_pmc_is_high_counter(select_idx))
+		counter = upper_32_bits(counter);
+
+	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -77,6 +177,7 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
  */
 static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
 {
+	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (pmc->perf_event) {
 		perf_event_disable(pmc->perf_event);
 		perf_event_release_kernel(pmc->perf_event);
@@ -94,13 +195,23 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
 	u64 counter, reg;
 
-	if (pmc->perf_event) {
-		counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
+	pmc = kvm_pmu_get_canonical_pmc(pmc);
+	if (!pmc->perf_event)
+		return;
+
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_pmc_is_chained(pmc)) {
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	} else {
 		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
 		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = counter;
-		kvm_pmu_release_perf_event(pmc);
+		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
 	}
+
+	kvm_pmu_release_perf_event(pmc);
 }
 
 /**
@@ -117,6 +228,8 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
 		pmu->pmc[i].idx = i;
 	}
+
+	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 }
 
 /**
@@ -165,6 +278,18 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 
 		pmc = &pmu->pmc[i];
+
+		/*
+		 * For high counters of chained events we must recreate the
+		 * perf event with the long (64bit) attribute set.
+		 */
+		if (kvm_pmu_pmc_is_chained(pmc) &&
+		    kvm_pmu_pmc_is_high_counter(i)) {
+			kvm_pmu_create_perf_event(vcpu, i);
+			continue;
+		}
+
+		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event) {
 			perf_event_enable(pmc->perf_event);
 			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
@@ -194,6 +319,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 
 		pmc = &pmu->pmc[i];
+
+		/*
+		 * For high counters of chained events we must recreate the
+		 * perf event with the long (64bit) attribute unset.
+		 */
+		if (kvm_pmu_pmc_is_chained(pmc) &&
+		    kvm_pmu_pmc_is_high_counter(i)) {
+			kvm_pmu_create_perf_event(vcpu, i);
+			continue;
+		}
+
+		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event)
 			perf_event_disable(pmc->perf_event);
 	}
@@ -283,17 +420,6 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
 	kvm_pmu_update_state(vcpu);
 }
 
-static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
-{
-	struct kvm_pmu *pmu;
-	struct kvm_vcpu_arch *vcpu_arch;
-
-	pmc -= pmc->idx;
-	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
-	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
-	return container_of(vcpu_arch, struct kvm_vcpu, arch);
-}
-
 /**
  * When the perf event overflows, set the overflow status and inform the vcpu.
  */
@@ -384,13 +510,20 @@ static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct kvm_pmc *pmc;
 	struct perf_event *event;
 	struct perf_event_attr attr;
 	u64 eventsel, counter, reg, data;
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
+	/*
+	 * For chained counters the event type and filtering attributes are
+	 * obtained from the low/even counter. We also use this counter to
+	 * determine if the event is enabled/disabled.
+	 */
+	pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]);
+
+	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx;
 	data = __vcpu_sys_reg(vcpu, reg);
 
 	kvm_pmu_stop_counter(vcpu, pmc);
@@ -398,27 +531,43 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 
 	/* Software increment event does't need to be backed by a perf event */
 	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
-	    select_idx != ARMV8_PMU_CYCLE_IDX)
+	    pmc->idx != ARMV8_PMU_CYCLE_IDX)
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.type = PERF_TYPE_RAW;
 	attr.size = sizeof(attr);
 	attr.pinned = 1;
-	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
+	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx);
 	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
-	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
+	attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ?
 		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
 
-	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
-	/* The initial sample period (overflow count) of an event. */
-	attr.sample_period = (-counter) & GENMASK(31, 0);
+	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+
+	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+		/**
+		 * The initial sample period (overflow count) of an event. For
+		 * chained counters we only support overflow interrupts on the
+		 * high counter.
+		 */
+		attr.sample_period = (-counter) & GENMASK(63, 0);
+		event = perf_event_create_kernel_counter(&attr, -1, current,
+							 kvm_pmu_perf_overflow,
+							 pmc + 1);
 
-	event = perf_event_create_kernel_counter(&attr, -1, current,
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+	} else {
+		/* The initial sample period (overflow count) of an event. */
+		attr.sample_period = (-counter) & GENMASK(31, 0);
+		event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_pmu_perf_overflow, pmc);
+	}
+
 	if (IS_ERR(event)) {
 		pr_err_once("kvm: pmu event creation failed %ld\n",
 			    PTR_ERR(event));
@@ -428,6 +577,33 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	pmc->perf_event = event;
 }
 
+/**
+ * kvm_pmu_update_pmc_chained - update chained bitmap
+ * @vcpu: The vcpu pointer
+ * @select_idx: The number of selected counter
+ *
+ * Update the chained bitmap based on the event type written in the
+ * typer register.
+ */
+static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+		/*
+		 * During promotion from !chained to chained we must ensure
+		 * the adjacent counter is stopped and its event destroyed
+		 */
+		if (!kvm_pmu_pmc_is_chained(pmc))
+			kvm_pmu_stop_counter(vcpu, pmc);
+
+		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	} else {
+		clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	}
+}
+
 /**
  * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
  * @vcpu: The vcpu pointer
@@ -447,6 +623,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
 
 	__vcpu_sys_reg(vcpu, reg) = event_type;
+
+	kvm_pmu_update_pmc_chained(vcpu, select_idx);
 	kvm_pmu_create_perf_event(vcpu, select_idx);
 }
 
-- 
2.21.0

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply related	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask
  2019-05-22 15:30 ` [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask Andrew Murray
@ 2019-05-22 16:07   ` Marc Zyngier
  2019-05-22 16:26     ` Andrew Murray
  0 siblings, 1 reply; 14+ messages in thread
From: Marc Zyngier @ 2019-05-22 16:07 UTC (permalink / raw)
  To: Andrew Murray, Christoffer Dall; +Cc: kvmarm, linux-arm-kernel

On 22/05/2019 16:30, Andrew Murray wrote:
> We currently use pmc->bitmask to determine the width of the pmc - however
> it's superfluous as the pmc index already describes if the pmc is a cycle
> counter or event counter. The architecture clearly describes the widths of
> these counters.
> 
> Let's remove the bitmask to simplify the code.
> 
> Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> ---
>  include/kvm/arm_pmu.h |  1 -
>  virt/kvm/arm/pmu.c    | 15 +++++----------
>  2 files changed, 5 insertions(+), 11 deletions(-)
> 
> diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
> index b73f31baca52..2f0e28dc5a9e 100644
> --- a/include/kvm/arm_pmu.h
> +++ b/include/kvm/arm_pmu.h
> @@ -28,7 +28,6 @@
>  struct kvm_pmc {
>  	u8 idx;	/* index into the pmu->pmc array */
>  	struct perf_event *perf_event;
> -	u64 bitmask;
>  };
>  
>  struct kvm_pmu {
> diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
> index ae1e886d4a1a..c4e2bc213617 100644
> --- a/virt/kvm/arm/pmu.c
> +++ b/virt/kvm/arm/pmu.c
> @@ -47,7 +47,10 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
>  		counter += perf_event_read_value(pmc->perf_event, &enabled,
>  						 &running);
>  
> -	return counter & pmc->bitmask;
> +	if (select_idx != ARMV8_PMU_CYCLE_IDX)
> +		counter = lower_32_bits(counter);
> +
> +	return counter;
>  }
>  
>  /**
> @@ -113,7 +116,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
>  	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
>  		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
>  		pmu->pmc[i].idx = i;
> -		pmu->pmc[i].bitmask = 0xffffffffUL;
>  	}
>  }
>  
> @@ -348,8 +350,6 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
>   */
>  void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
>  {
> -	struct kvm_pmu *pmu = &vcpu->arch.pmu;
> -	struct kvm_pmc *pmc;
>  	u64 mask;
>  	int i;
>  
> @@ -368,11 +368,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
>  		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
>  			kvm_pmu_set_counter_value(vcpu, i, 0);
>  	}
> -
> -	if (val & ARMV8_PMU_PMCR_LC) {
> -		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
> -		pmc->bitmask = 0xffffffffffffffffUL;
> -	}
>  }
>  
>  static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
> @@ -420,7 +415,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
>  
>  	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
>  	/* The initial sample period (overflow count) of an event. */
> -	attr.sample_period = (-counter) & pmc->bitmask;
> +	attr.sample_period = (-counter) & GENMASK(31, 0);

Isn't this the one case where the bitmask actually matters? If we're
dealing with the cycle counter, it shouldn't be truncated, right?

>  
>  	event = perf_event_create_kernel_counter(&attr, -1, current,
>  						 kvm_pmu_perf_overflow, pmc);
> 

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny...
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask
  2019-05-22 16:07   ` Marc Zyngier
@ 2019-05-22 16:26     ` Andrew Murray
  2019-06-10 12:54       ` Suzuki K Poulose
  0 siblings, 1 reply; 14+ messages in thread
From: Andrew Murray @ 2019-05-22 16:26 UTC (permalink / raw)
  To: Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

On Wed, May 22, 2019 at 05:07:31PM +0100, Marc Zyngier wrote:
> On 22/05/2019 16:30, Andrew Murray wrote:
> > We currently use pmc->bitmask to determine the width of the pmc - however
> > it's superfluous as the pmc index already describes if the pmc is a cycle
> > counter or event counter. The architecture clearly describes the widths of
> > these counters.
> > 
> > Let's remove the bitmask to simplify the code.
> > 
> > Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> > ---
> >  include/kvm/arm_pmu.h |  1 -
> >  virt/kvm/arm/pmu.c    | 15 +++++----------
> >  2 files changed, 5 insertions(+), 11 deletions(-)
> > 
> > diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
> > index b73f31baca52..2f0e28dc5a9e 100644
> > --- a/include/kvm/arm_pmu.h
> > +++ b/include/kvm/arm_pmu.h
> > @@ -28,7 +28,6 @@
> >  struct kvm_pmc {
> >  	u8 idx;	/* index into the pmu->pmc array */
> >  	struct perf_event *perf_event;
> > -	u64 bitmask;
> >  };
> >  
> >  struct kvm_pmu {
> > diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
> > index ae1e886d4a1a..c4e2bc213617 100644
> > --- a/virt/kvm/arm/pmu.c
> > +++ b/virt/kvm/arm/pmu.c
> > @@ -47,7 +47,10 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
> >  		counter += perf_event_read_value(pmc->perf_event, &enabled,
> >  						 &running);
> >  
> > -	return counter & pmc->bitmask;
> > +	if (select_idx != ARMV8_PMU_CYCLE_IDX)
> > +		counter = lower_32_bits(counter);
> > +
> > +	return counter;
> >  }
> >  
> >  /**
> > @@ -113,7 +116,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
> >  	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
> >  		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
> >  		pmu->pmc[i].idx = i;
> > -		pmu->pmc[i].bitmask = 0xffffffffUL;
> >  	}
> >  }
> >  
> > @@ -348,8 +350,6 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
> >   */
> >  void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
> >  {
> > -	struct kvm_pmu *pmu = &vcpu->arch.pmu;
> > -	struct kvm_pmc *pmc;
> >  	u64 mask;
> >  	int i;
> >  
> > @@ -368,11 +368,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
> >  		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
> >  			kvm_pmu_set_counter_value(vcpu, i, 0);
> >  	}
> > -
> > -	if (val & ARMV8_PMU_PMCR_LC) {
> > -		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
> > -		pmc->bitmask = 0xffffffffffffffffUL;
> > -	}
> >  }
> >  
> >  static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
> > @@ -420,7 +415,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
> >  
> >  	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
> >  	/* The initial sample period (overflow count) of an event. */
> > -	attr.sample_period = (-counter) & pmc->bitmask;
> > +	attr.sample_period = (-counter) & GENMASK(31, 0);
> 
> Isn't this the one case where the bitmask actually matters? If we're
> dealing with the cycle counter, it shouldn't be truncated, right?

Ah yes, that should be conditional on idx as well. 

Thanks,

Andrew Murray

> 
> >  
> >  	event = perf_event_create_kernel_counter(&attr, -1, current,
> >  						 kvm_pmu_perf_overflow, pmc);
> > 
> 
> Thanks,
> 
> 	M.
> -- 
> Jazz is not dead. It just smells funny...
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters
  2019-05-22 15:30 ` [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters Andrew Murray
@ 2019-06-10 10:21   ` Julien Thierry
  2019-06-10 16:05   ` Suzuki K Poulose
  1 sibling, 0 replies; 14+ messages in thread
From: Julien Thierry @ 2019-06-10 10:21 UTC (permalink / raw)
  To: Andrew Murray, Christoffer Dall, Marc Zyngier; +Cc: kvmarm, linux-arm-kernel

Hi Andrew,

On 22/05/2019 16:30, Andrew Murray wrote:
> ARMv8 provides support for chained PMU counters, where an event type
> of 0x001E is set for odd-numbered counters, the event counter will
> increment by one for each overflow of the preceding even-numbered
> counter. Let's emulate this in KVM by creating a 64 bit perf counter
> when a user chains two emulated counters together.
> 
> For chained events we only support generating an overflow interrupt
> on the high counter. We use the attributes of the low counter to
> determine the attributes of the perf event.
> 

I think this looks good now. Once the previous patch is fixed you can add:

Reviewed-by: Julien Thierry <julien.thierry@arm.com>

Cheers,

Julien

> Suggested-by: Marc Zyngier <marc.zyngier@arm.com>
> Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> ---
>  include/kvm/arm_pmu.h |   2 +
>  virt/kvm/arm/pmu.c    | 248 ++++++++++++++++++++++++++++++++++++------
>  2 files changed, 215 insertions(+), 35 deletions(-)
> 
> diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
> index 2f0e28dc5a9e..589f49ed8cf8 100644
> --- a/include/kvm/arm_pmu.h
> +++ b/include/kvm/arm_pmu.h
> @@ -22,6 +22,7 @@
>  #include <asm/perf_event.h>
>  
>  #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
> +#define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
>  
>  #ifdef CONFIG_KVM_ARM_PMU
>  
> @@ -33,6 +34,7 @@ struct kvm_pmc {
>  struct kvm_pmu {
>  	int irq_num;
>  	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
> +	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
>  	bool ready;
>  	bool created;
>  	bool irq_level;
> diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
> index c4e2bc213617..796bcf76911f 100644
> --- a/virt/kvm/arm/pmu.c
> +++ b/virt/kvm/arm/pmu.c
> @@ -25,29 +25,129 @@
>  #include <kvm/arm_vgic.h>
>  
>  static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
> +
> +#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
> +
> +static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
> +{
> +	struct kvm_pmu *pmu;
> +	struct kvm_vcpu_arch *vcpu_arch;
> +
> +	pmc -= pmc->idx;
> +	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
> +	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
> +	return container_of(vcpu_arch, struct kvm_vcpu, arch);
> +}
> +
>  /**
> - * kvm_pmu_get_counter_value - get PMU counter value
> + * kvm_pmu_pmc_is_chained - determine if the pmc is chained
> + * @pmc: The PMU counter pointer
> + */
> +static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc)
> +{
> +	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
> +
> +	return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
> +}
> +
> +/**
> + * kvm_pmu_pmc_is_high_counter - determine if select_idx is a high/low counter
> + * @select_idx: The counter index
> + */
> +static bool kvm_pmu_pmc_is_high_counter(u64 select_idx)
> +{
> +	return select_idx & 0x1;
> +}
> +
> +/**
> + * kvm_pmu_get_canonical_pmc - obtain the canonical pmc
> + * @pmc: The PMU counter pointer
> + *
> + * When a pair of PMCs are chained together we use the low counter (canonical)
> + * to hold the underlying perf event.
> + */
> +static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
> +{
> +	if (kvm_pmu_pmc_is_chained(pmc) &&
> +	    kvm_pmu_pmc_is_high_counter(pmc->idx))
> +		return pmc - 1;
> +
> +	return pmc;
> +}
> +
> +/**
> + * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
>   * @vcpu: The vcpu pointer
>   * @select_idx: The counter index
>   */
> -u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
> +static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx)
>  {
> -	u64 counter, reg, enabled, running;
> -	struct kvm_pmu *pmu = &vcpu->arch.pmu;
> -	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
> +	u64 eventsel, reg;
>  
> -	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
> -	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
> -	counter = __vcpu_sys_reg(vcpu, reg);
> +	select_idx |= 0x1;
> +
> +	if (select_idx == ARMV8_PMU_CYCLE_IDX)
> +		return false;
>  
> -	/* The real counter value is equal to the value of counter register plus
> +	reg = PMEVTYPER0_EL0 + select_idx;
> +	eventsel = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_EVENT;
> +
> +	return armv8pmu_evtype_is_chain(eventsel);
> +}
> +
> +/**
> + * kvm_pmu_get_pair_counter_value - get PMU counter value
> + * @vcpu: The vcpu pointer
> + * @pmc: The PMU counter pointer
> + */
> +static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
> +					  struct kvm_pmc *pmc)
> +{
> +	u64 counter, counter_high, reg, enabled, running;
> +
> +	if (kvm_pmu_pmc_is_chained(pmc)) {
> +		pmc = kvm_pmu_get_canonical_pmc(pmc);
> +		reg = PMEVCNTR0_EL0 + pmc->idx;
> +
> +		counter = __vcpu_sys_reg(vcpu, reg);
> +		counter_high = __vcpu_sys_reg(vcpu, reg + 1);
> +
> +		counter = lower_32_bits(counter) | (counter_high << 32);
> +	} else {
> +		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
> +		      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
> +		counter = __vcpu_sys_reg(vcpu, reg);
> +	}
> +
> +	/*
> +	 * The real counter value is equal to the value of counter register plus
>  	 * the value perf event counts.
>  	 */
>  	if (pmc->perf_event)
>  		counter += perf_event_read_value(pmc->perf_event, &enabled,
>  						 &running);
>  
> -	if (select_idx != ARMV8_PMU_CYCLE_IDX)
> +	return counter;
> +}
> +
> +/**
> + * kvm_pmu_get_counter_value - get PMU counter value
> + * @vcpu: The vcpu pointer
> + * @select_idx: The counter index
> + */
> +u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
> +{
> +	u64 counter;
> +	struct kvm_pmu *pmu = &vcpu->arch.pmu;
> +	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
> +
> +	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
> +
> +	if (kvm_pmu_pmc_is_chained(pmc) &&
> +	    kvm_pmu_pmc_is_high_counter(select_idx))
> +		counter = upper_32_bits(counter);
> +
> +	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
>  		counter = lower_32_bits(counter);
>  
>  	return counter;
> @@ -77,6 +177,7 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
>   */
>  static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
>  {
> +	pmc = kvm_pmu_get_canonical_pmc(pmc);
>  	if (pmc->perf_event) {
>  		perf_event_disable(pmc->perf_event);
>  		perf_event_release_kernel(pmc->perf_event);
> @@ -94,13 +195,23 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
>  {
>  	u64 counter, reg;
>  
> -	if (pmc->perf_event) {
> -		counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
> +	pmc = kvm_pmu_get_canonical_pmc(pmc);
> +	if (!pmc->perf_event)
> +		return;
> +
> +	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
> +
> +	if (kvm_pmu_pmc_is_chained(pmc)) {
> +		reg = PMEVCNTR0_EL0 + pmc->idx;
> +		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
> +		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
> +	} else {
>  		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
>  		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
> -		__vcpu_sys_reg(vcpu, reg) = counter;
> -		kvm_pmu_release_perf_event(pmc);
> +		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
>  	}
> +
> +	kvm_pmu_release_perf_event(pmc);
>  }
>  
>  /**
> @@ -117,6 +228,8 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
>  		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
>  		pmu->pmc[i].idx = i;
>  	}
> +
> +	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
>  }
>  
>  /**
> @@ -165,6 +278,18 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
>  			continue;
>  
>  		pmc = &pmu->pmc[i];
> +
> +		/*
> +		 * For high counters of chained events we must recreate the
> +		 * perf event with the long (64bit) attribute set.
> +		 */
> +		if (kvm_pmu_pmc_is_chained(pmc) &&
> +		    kvm_pmu_pmc_is_high_counter(i)) {
> +			kvm_pmu_create_perf_event(vcpu, i);
> +			continue;
> +		}
> +
> +		/* At this point, pmc must be the canonical */
>  		if (pmc->perf_event) {
>  			perf_event_enable(pmc->perf_event);
>  			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
> @@ -194,6 +319,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
>  			continue;
>  
>  		pmc = &pmu->pmc[i];
> +
> +		/*
> +		 * For high counters of chained events we must recreate the
> +		 * perf event with the long (64bit) attribute unset.
> +		 */
> +		if (kvm_pmu_pmc_is_chained(pmc) &&
> +		    kvm_pmu_pmc_is_high_counter(i)) {
> +			kvm_pmu_create_perf_event(vcpu, i);
> +			continue;
> +		}
> +
> +		/* At this point, pmc must be the canonical */
>  		if (pmc->perf_event)
>  			perf_event_disable(pmc->perf_event);
>  	}
> @@ -283,17 +420,6 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
>  	kvm_pmu_update_state(vcpu);
>  }
>  
> -static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
> -{
> -	struct kvm_pmu *pmu;
> -	struct kvm_vcpu_arch *vcpu_arch;
> -
> -	pmc -= pmc->idx;
> -	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
> -	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
> -	return container_of(vcpu_arch, struct kvm_vcpu, arch);
> -}
> -
>  /**
>   * When the perf event overflows, set the overflow status and inform the vcpu.
>   */
> @@ -384,13 +510,20 @@ static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
>  static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
>  {
>  	struct kvm_pmu *pmu = &vcpu->arch.pmu;
> -	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
> +	struct kvm_pmc *pmc;
>  	struct perf_event *event;
>  	struct perf_event_attr attr;
>  	u64 eventsel, counter, reg, data;
>  
> -	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
> -	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
> +	/*
> +	 * For chained counters the event type and filtering attributes are
> +	 * obtained from the low/even counter. We also use this counter to
> +	 * determine if the event is enabled/disabled.
> +	 */
> +	pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]);
> +
> +	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
> +	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx;
>  	data = __vcpu_sys_reg(vcpu, reg);
>  
>  	kvm_pmu_stop_counter(vcpu, pmc);
> @@ -398,27 +531,43 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
>  
>  	/* Software increment event does't need to be backed by a perf event */
>  	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
> -	    select_idx != ARMV8_PMU_CYCLE_IDX)
> +	    pmc->idx != ARMV8_PMU_CYCLE_IDX)
>  		return;
>  
>  	memset(&attr, 0, sizeof(struct perf_event_attr));
>  	attr.type = PERF_TYPE_RAW;
>  	attr.size = sizeof(attr);
>  	attr.pinned = 1;
> -	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
> +	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx);
>  	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
>  	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
>  	attr.exclude_hv = 1; /* Don't count EL2 events */
>  	attr.exclude_host = 1; /* Don't count host events */
> -	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
> +	attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ?
>  		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
>  
> -	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
> -	/* The initial sample period (overflow count) of an event. */
> -	attr.sample_period = (-counter) & GENMASK(31, 0);
> +	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
> +
> +	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
> +		/**
> +		 * The initial sample period (overflow count) of an event. For
> +		 * chained counters we only support overflow interrupts on the
> +		 * high counter.
> +		 */
> +		attr.sample_period = (-counter) & GENMASK(63, 0);
> +		event = perf_event_create_kernel_counter(&attr, -1, current,
> +							 kvm_pmu_perf_overflow,
> +							 pmc + 1);
>  
> -	event = perf_event_create_kernel_counter(&attr, -1, current,
> +		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
> +			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
> +	} else {
> +		/* The initial sample period (overflow count) of an event. */
> +		attr.sample_period = (-counter) & GENMASK(31, 0);
> +		event = perf_event_create_kernel_counter(&attr, -1, current,
>  						 kvm_pmu_perf_overflow, pmc);
> +	}
> +
>  	if (IS_ERR(event)) {
>  		pr_err_once("kvm: pmu event creation failed %ld\n",
>  			    PTR_ERR(event));
> @@ -428,6 +577,33 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
>  	pmc->perf_event = event;
>  }
>  
> +/**
> + * kvm_pmu_update_pmc_chained - update chained bitmap
> + * @vcpu: The vcpu pointer
> + * @select_idx: The number of selected counter
> + *
> + * Update the chained bitmap based on the event type written in the
> + * typer register.
> + */
> +static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
> +{
> +	struct kvm_pmu *pmu = &vcpu->arch.pmu;
> +	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
> +
> +	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
> +		/*
> +		 * During promotion from !chained to chained we must ensure
> +		 * the adjacent counter is stopped and its event destroyed
> +		 */
> +		if (!kvm_pmu_pmc_is_chained(pmc))
> +			kvm_pmu_stop_counter(vcpu, pmc);
> +
> +		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
> +	} else {
> +		clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
> +	}
> +}
> +
>  /**
>   * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
>   * @vcpu: The vcpu pointer
> @@ -447,6 +623,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
>  	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
>  
>  	__vcpu_sys_reg(vcpu, reg) = event_type;
> +
> +	kvm_pmu_update_pmc_chained(vcpu, select_idx);
>  	kvm_pmu_create_perf_event(vcpu, select_idx);
>  }
>  
> 

-- 
Julien Thierry
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 4/6] arm64: perf: extract chain helper into header
  2019-05-22 15:30 ` [PATCH v8 4/6] arm64: perf: extract chain helper into header Andrew Murray
@ 2019-06-10 11:39   ` Will Deacon
  0 siblings, 0 replies; 14+ messages in thread
From: Will Deacon @ 2019-06-10 11:39 UTC (permalink / raw)
  To: Andrew Murray; +Cc: Marc Zyngier, kvmarm, linux-arm-kernel

On Wed, May 22, 2019 at 04:30:17PM +0100, Andrew Murray wrote:
> The ARMv8 Performance Monitors Extension includes an architectural
> event type named CHAIN which allows for chaining counters together.
> 
> Let's extract the test for this event into a header file such that
> other users, such as KVM (for PMU emulation) can make use of.
> 
> Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
> ---
>  arch/arm64/include/asm/perf_event.h | 5 +++++
>  arch/arm64/kernel/perf_event.c      | 2 +-
>  2 files changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
> index c593761ba61c..cd13f3fd1055 100644
> --- a/arch/arm64/include/asm/perf_event.h
> +++ b/arch/arm64/include/asm/perf_event.h
> @@ -219,6 +219,11 @@
>  #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
>  #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
>  
> +static inline bool armv8pmu_evtype_is_chain(u64 evtype)
> +{
> +	return (evtype == ARMV8_PMUV3_PERFCTR_CHAIN);
> +}
> +
>  #ifdef CONFIG_PERF_EVENTS
>  struct pt_regs;
>  extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
> index 314b1adedf06..265bd835a724 100644
> --- a/arch/arm64/kernel/perf_event.c
> +++ b/arch/arm64/kernel/perf_event.c
> @@ -879,7 +879,7 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
>  static int armv8pmu_filter_match(struct perf_event *event)
>  {
>  	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
> -	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
> +	return !armv8pmu_evtype_is_chain(evtype);

Acked-by: Will Deacon <will.deacon@arm.com>

Although if the definition of armv8pmu_evtype_is_chain() isn't going to
get any more complicated than a single evtype comparison, I'm not sure it's
worth this abstraction, to be honest.

Will
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask
  2019-05-22 16:26     ` Andrew Murray
@ 2019-06-10 12:54       ` Suzuki K Poulose
  2019-06-12 14:30         ` Andrew Murray
  0 siblings, 1 reply; 14+ messages in thread
From: Suzuki K Poulose @ 2019-06-10 12:54 UTC (permalink / raw)
  To: andrew.murray, marc.zyngier; +Cc: linux-arm-kernel, kvmarm



On 22/05/2019 17:26, Andrew Murray wrote:
> On Wed, May 22, 2019 at 05:07:31PM +0100, Marc Zyngier wrote:
>> On 22/05/2019 16:30, Andrew Murray wrote:
>>> We currently use pmc->bitmask to determine the width of the pmc - however
>>> it's superfluous as the pmc index already describes if the pmc is a cycle
>>> counter or event counter. The architecture clearly describes the widths of
>>> these counters.
>>>
>>> Let's remove the bitmask to simplify the code.
>>>
>>> Signed-off-by: Andrew Murray <andrew.murray@arm.com>
>>> ---
>>>   include/kvm/arm_pmu.h |  1 -
>>>   virt/kvm/arm/pmu.c    | 15 +++++----------
>>>   2 files changed, 5 insertions(+), 11 deletions(-)
>>>
>>> diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
>>> index b73f31baca52..2f0e28dc5a9e 100644
>>> --- a/include/kvm/arm_pmu.h
>>> +++ b/include/kvm/arm_pmu.h
>>> @@ -28,7 +28,6 @@
>>>   struct kvm_pmc {
>>>   	u8 idx;	/* index into the pmu->pmc array */
>>>   	struct perf_event *perf_event;
>>> -	u64 bitmask;
>>>   };
>>>   


>>> -
>>> -	if (val & ARMV8_PMU_PMCR_LC) {
>>> -		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
>>> -		pmc->bitmask = 0xffffffffffffffffUL;
>>> -	}
>>>   }

...

>>>   
>>>   static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
>>> @@ -420,7 +415,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
>>>   
>>>   	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
>>>   	/* The initial sample period (overflow count) of an event. */
>>> -	attr.sample_period = (-counter) & pmc->bitmask;
>>> +	attr.sample_period = (-counter) & GENMASK(31, 0);
>>
>> Isn't this the one case where the bitmask actually matters? If we're
>> dealing with the cycle counter, it shouldn't be truncated, right?
> 
> Ah yes, that should be conditional on idx as well.

The mask for Cycle counter also depends on the PMCR.LC field set by the
guest, isn't it ? So unless we correlate that with the idx, we could be
passing in wrong results ?

Suzuki
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters
  2019-05-22 15:30 ` [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters Andrew Murray
  2019-06-10 10:21   ` Julien Thierry
@ 2019-06-10 16:05   ` Suzuki K Poulose
  1 sibling, 0 replies; 14+ messages in thread
From: Suzuki K Poulose @ 2019-06-10 16:05 UTC (permalink / raw)
  To: andrew.murray, christoffer.dall, marc.zyngier; +Cc: kvmarm, linux-arm-kernel

Hi Andrew,

> @@ -398,27 +531,43 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
>   
>   	/* Software increment event does't need to be backed by a perf event */
>   	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
> -	    select_idx != ARMV8_PMU_CYCLE_IDX)
> +	    pmc->idx != ARMV8_PMU_CYCLE_IDX)
>   		return;
>   
>   	memset(&attr, 0, sizeof(struct perf_event_attr));
>   	attr.type = PERF_TYPE_RAW;
>   	attr.size = sizeof(attr);
>   	attr.pinned = 1;
> -	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
> +	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx);
>   	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
>   	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
>   	attr.exclude_hv = 1; /* Don't count EL2 events */
>   	attr.exclude_host = 1; /* Don't count host events */
> -	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
> +	attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ?
>   		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
>   
> -	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
> -	/* The initial sample period (overflow count) of an event. */
> -	attr.sample_period = (-counter) & GENMASK(31, 0);
> +	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
> +
> +	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
> +		/**
> +		 * The initial sample period (overflow count) of an event. For
> +		 * chained counters we only support overflow interrupts on the
> +		 * high counter.
> +		 */
> +		attr.sample_period = (-counter) & GENMASK(63, 0);
> +		event = perf_event_create_kernel_counter(&attr, -1, current,
> +							 kvm_pmu_perf_overflow,
> +							 pmc + 1);
>   
> -	event = perf_event_create_kernel_counter(&attr, -1, current,
> +		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
> +			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
> +	} else {
> +		/* The initial sample period (overflow count) of an event. */
> +		attr.sample_period = (-counter) & GENMASK(31, 0);
> +		event = perf_event_create_kernel_counter(&attr, -1, current,
>   						 kvm_pmu_perf_overflow, pmc);
> +	}
> +

If this was the Cycle counter and t he PMCR_LC was set, shouldn't we be using
64bit mask here ? We fall back to using the Cycle counter in 64bit mode for
"normal" (read guest) kernel. So shouldn't we reflect that here ?

Rest looks fine to me.

Suzuki
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask
  2019-06-10 12:54       ` Suzuki K Poulose
@ 2019-06-12 14:30         ` Andrew Murray
  0 siblings, 0 replies; 14+ messages in thread
From: Andrew Murray @ 2019-06-12 14:30 UTC (permalink / raw)
  To: Suzuki K Poulose; +Cc: marc.zyngier, kvmarm, linux-arm-kernel

On Mon, Jun 10, 2019 at 01:54:35PM +0100, Suzuki K Poulose wrote:
> 
> 
> On 22/05/2019 17:26, Andrew Murray wrote:
> > On Wed, May 22, 2019 at 05:07:31PM +0100, Marc Zyngier wrote:
> > > On 22/05/2019 16:30, Andrew Murray wrote:
> > > > We currently use pmc->bitmask to determine the width of the pmc - however
> > > > it's superfluous as the pmc index already describes if the pmc is a cycle
> > > > counter or event counter. The architecture clearly describes the widths of
> > > > these counters.
> > > > 
> > > > Let's remove the bitmask to simplify the code.
> > > > 
> > > > Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> > > > ---
> > > >   include/kvm/arm_pmu.h |  1 -
> > > >   virt/kvm/arm/pmu.c    | 15 +++++----------
> > > >   2 files changed, 5 insertions(+), 11 deletions(-)
> > > > 
> > > > diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
> > > > index b73f31baca52..2f0e28dc5a9e 100644
> > > > --- a/include/kvm/arm_pmu.h
> > > > +++ b/include/kvm/arm_pmu.h
> > > > @@ -28,7 +28,6 @@
> > > >   struct kvm_pmc {
> > > >   	u8 idx;	/* index into the pmu->pmc array */
> > > >   	struct perf_event *perf_event;
> > > > -	u64 bitmask;
> > > >   };
> 
> 
> > > > -
> > > > -	if (val & ARMV8_PMU_PMCR_LC) {
> > > > -		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
> > > > -		pmc->bitmask = 0xffffffffffffffffUL;
> > > > -	}
> > > >   }
> 
> ...
> 
> > > >   static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
> > > > @@ -420,7 +415,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
> > > >   	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
> > > >   	/* The initial sample period (overflow count) of an event. */
> > > > -	attr.sample_period = (-counter) & pmc->bitmask;
> > > > +	attr.sample_period = (-counter) & GENMASK(31, 0);
> > > 
> > > Isn't this the one case where the bitmask actually matters? If we're
> > > dealing with the cycle counter, it shouldn't be truncated, right?
> > 
> > Ah yes, that should be conditional on idx as well.
> 
> The mask for Cycle counter also depends on the PMCR.LC field set by the
> guest, isn't it ? So unless we correlate that with the idx, we could be
> passing in wrong results ?

Yes that's right, I misread the description of LC - it's RES1 for AArch64
but of course this doesn't stop a 32 bit host kernel. I'll update this.

Thanks,

Andrew Murray

> 
> Suzuki
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

^ permalink raw reply	[flat|nested] 14+ messages in thread

end of thread, other threads:[~2019-06-12 14:30 UTC | newest]

Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-05-22 15:30 [PATCH v8 0/6] KVM: arm/arm64: add support for chained counters Andrew Murray
2019-05-22 15:30 ` [PATCH v8 1/6] KVM: arm/arm64: rename kvm_pmu_{enable/disable}_counter functions Andrew Murray
2019-05-22 15:30 ` [PATCH v8 2/6] KVM: arm/arm64: extract duplicated code to own function Andrew Murray
2019-05-22 15:30 ` [PATCH v8 3/6] KVM: arm/arm64: re-create event when setting counter value Andrew Murray
2019-05-22 15:30 ` [PATCH v8 4/6] arm64: perf: extract chain helper into header Andrew Murray
2019-06-10 11:39   ` Will Deacon
2019-05-22 15:30 ` [PATCH v8 5/6] KVM: arm/arm64: remove pmc->bitmask Andrew Murray
2019-05-22 16:07   ` Marc Zyngier
2019-05-22 16:26     ` Andrew Murray
2019-06-10 12:54       ` Suzuki K Poulose
2019-06-12 14:30         ` Andrew Murray
2019-05-22 15:30 ` [PATCH v8 6/6] KVM: arm/arm64: support chained PMU counters Andrew Murray
2019-06-10 10:21   ` Julien Thierry
2019-06-10 16:05   ` Suzuki K Poulose

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).