linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Colton Lewis <coltonlewis@google.com>
To: kvm@vger.kernel.org
Cc: Russell King <linux@armlinux.org.uk>,
	Catalin Marinas <catalin.marinas@arm.com>,
	 Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
	Oliver Upton <oliver.upton@linux.dev>,
	 Joey Gouly <joey.gouly@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	 Zenghui Yu <yuzenghui@huawei.com>,
	Mark Rutland <mark.rutland@arm.com>,
	 Paolo Bonzini <pbonzini@redhat.com>,
	Shuah Khan <shuah@kernel.org>,
	 linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,  kvmarm@lists.linux.dev,
	linux-perf-users@vger.kernel.org,
	 linux-kselftest@vger.kernel.org,
	Colton Lewis <coltonlewis@google.com>
Subject: [RFC PATCH v2 3/4] perf: arm_pmuv3: Keep out of guest counter partition
Date: Sat,  8 Feb 2025 02:01:10 +0000	[thread overview]
Message-ID: <20250208020111.2068239-4-coltonlewis@google.com> (raw)
In-Reply-To: <20250208020111.2068239-1-coltonlewis@google.com>

If the PMU is partitioned, keep the driver out of the guest counter
partition and only use the host counter partition. Partitioning is
defined by the MDCR_EL2.HPMN register field and saved in
cpu_pmu->hpmn. The range 0..HPMN-1 is accessible by EL1 and EL0 while
HPMN..PMCR.N is reserved for EL2.

Define some macros that take HPMN as an argument and construct
mutually exclusive bitmaps for testing which partition a particular
counter is in. Note that despite their different position in the
bitmap, the cycle and instruction counters are always in the guest
partition.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 drivers/perf/arm_pmuv3.c       | 73 +++++++++++++++++++++++++++++-----
 include/linux/perf/arm_pmuv3.h |  8 ++++
 2 files changed, 71 insertions(+), 10 deletions(-)

diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 39109260b161..01468ec9fead 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -754,15 +754,19 @@ static void armv8pmu_disable_event_irq(struct perf_event *event)
 	armv8pmu_disable_intens(BIT(event->hw.idx));
 }
 
-static u64 armv8pmu_getreset_flags(void)
+static u64 armv8pmu_getreset_flags(struct arm_pmu *cpu_pmu)
 {
 	u64 value;
 
 	/* Read */
 	value = read_pmovsclr();
 
+	if (cpu_pmu->partitioned)
+		value &= ARMV8_PMU_HOST_CNT_PART(cpu_pmu->hpmn);
+	else
+		value &= ARMV8_PMU_OVERFLOWED_MASK;
+
 	/* Write to clear flags */
-	value &= ARMV8_PMU_OVERFLOWED_MASK;
 	write_pmovsclr(value);
 
 	return value;
@@ -789,6 +793,18 @@ static void armv8pmu_disable_user_access(void)
 	update_pmuserenr(0);
 }
 
+static bool armv8pmu_is_guest_part(struct arm_pmu *cpu_pmu, u8 idx)
+{
+	return cpu_pmu->partitioned &&
+		(BIT(idx) & ARMV8_PMU_GUEST_CNT_PART(cpu_pmu->hpmn));
+}
+
+static bool armv8pmu_is_host_part(struct arm_pmu *cpu_pmu, u8 idx)
+{
+	return !cpu_pmu->partitioned ||
+		(BIT(idx) & ARMV8_PMU_HOST_CNT_PART(cpu_pmu->hpmn));
+}
+
 static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
 {
 	int i;
@@ -797,6 +813,8 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
 	if (is_pmuv3p9(cpu_pmu->pmuver)) {
 		u64 mask = 0;
 		for_each_set_bit(i, cpuc->used_mask, ARMPMU_MAX_HWEVENTS) {
+			if (armv8pmu_is_guest_part(cpu_pmu, i))
+				continue;
 			if (armv8pmu_event_has_user_read(cpuc->events[i]))
 				mask |= BIT(i);
 		}
@@ -805,6 +823,8 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
 		/* Clear any unused counters to avoid leaking their contents */
 		for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask,
 				    ARMPMU_MAX_HWEVENTS) {
+			if (armv8pmu_is_guest_part(cpu_pmu, i))
+				continue;
 			if (i == ARMV8_PMU_CYCLE_IDX)
 				write_pmccntr(0);
 			else if (i == ARMV8_PMU_INSTR_IDX)
@@ -850,7 +870,10 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 		armv8pmu_disable_user_access();
 
 	/* Enable all counters */
-	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
+	if (cpu_pmu->partitioned)
+		armv8pmu_mdcr_write(armv8pmu_mdcr_read() | ARMV8_PMU_MDCR_HPME);
+	else
+		armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
 
 	kvm_vcpu_pmu_resync_el0();
 }
@@ -858,7 +881,10 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
 {
 	/* Disable all counters */
-	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
+	if (cpu_pmu->partitioned)
+		armv8pmu_mdcr_write(armv8pmu_mdcr_read() & ~ARMV8_PMU_MDCR_HPME);
+	else
+		armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
 }
 
 static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
@@ -872,7 +898,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	/*
 	 * Get and reset the IRQ flags
 	 */
-	pmovsr = armv8pmu_getreset_flags();
+	pmovsr = armv8pmu_getreset_flags(cpu_pmu);
 
 	/*
 	 * Did an overflow occur?
@@ -930,6 +956,8 @@ static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
 	int idx;
 
 	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+		if (armv8pmu_is_guest_part(cpu_pmu, idx))
+			continue;
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
@@ -946,6 +974,8 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
 	 * the lower idx must be even.
 	 */
 	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+		if (armv8pmu_is_guest_part(cpu_pmu, idx))
+			continue;
 		if (!(idx & 0x1))
 			continue;
 		if (!test_and_set_bit(idx, cpuc->used_mask)) {
@@ -968,6 +998,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 
 	/* Always prefer to place a cycle counter into the cycle counter. */
 	if ((evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) &&
+	    !cpu_pmu->partitioned &&
 	    !armv8pmu_event_get_threshold(&event->attr)) {
 		if (!test_and_set_bit(ARMV8_PMU_CYCLE_IDX, cpuc->used_mask))
 			return ARMV8_PMU_CYCLE_IDX;
@@ -983,6 +1014,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	 * may not know how to handle it.
 	 */
 	if ((evtype == ARMV8_PMUV3_PERFCTR_INST_RETIRED) &&
+	    !cpu_pmu->partitioned &&
 	    !armv8pmu_event_get_threshold(&event->attr) &&
 	    test_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask) &&
 	    !armv8pmu_event_want_user_access(event)) {
@@ -994,7 +1026,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	 * Otherwise use events counters
 	 */
 	if (armv8pmu_event_is_chained(event))
-		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
+		return armv8pmu_get_chain_idx(cpuc, cpu_pmu);
 	else
 		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
 }
@@ -1086,6 +1118,16 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	return 0;
 }
 
+static void armv8pmu_reset_host_counters(struct arm_pmu *cpu_pmu)
+{
+	int idx;
+
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+		if (armv8pmu_is_host_part(cpu_pmu, idx))
+			armv8pmu_write_evcntr(idx, 0);
+	}
+}
+
 static void armv8pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
@@ -1093,8 +1135,10 @@ static void armv8pmu_reset(void *info)
 
 	bitmap_to_arr64(&mask, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS);
 
-	if (cpu_pmu->partitioned)
+	if (cpu_pmu->partitioned) {
 		armv8pmu_partition(cpu_pmu->hpmn);
+		mask &= ARMV8_PMU_HOST_CNT_PART(cpu_pmu->hpmn);
+	}
 
 	/* The counter and interrupt enable registers are unknown at reset. */
 	armv8pmu_disable_counter(mask);
@@ -1103,11 +1147,20 @@ static void armv8pmu_reset(void *info)
 	/* Clear the counters we flip at guest entry/exit */
 	kvm_clr_pmu_events(mask);
 
+
+	pmcr = ARMV8_PMU_PMCR_LC;
+
 	/*
-	 * Initialize & Reset PMNC. Request overflow interrupt for
-	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
+	 * Initialize & Reset PMNC. Request overflow interrupt for 64
+	 * bit cycle counter but cheat in armv8pmu_write_counter().
+	 *
+	 * When partitioned, there is no single bit to reset only the
+	 * host counters. so reset them individually.
 	 */
-	pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC;
+	if (cpu_pmu->partitioned)
+		armv8pmu_reset_host_counters(cpu_pmu);
+	else
+		pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C;
 
 	/* Enable long event counter support where available */
 	if (armv8pmu_has_long_event(cpu_pmu))
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 115ee39f693a..5f8b143794ce 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -247,6 +247,14 @@
 #define ARMV8_PMU_OVSR_F		ARMV8_PMU_CNT_MASK_F
 /* Mask for writable bits is both P and C fields */
 #define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_CNT_MASK_ALL
+
+/* Masks for guest and host counter partitions */
+#define ARMV8_PMU_HPMN_CNT_MASK(N)	GENMASK((N) - 1, 0)
+#define ARMV8_PMU_GUEST_CNT_PART(N)	(ARMV8_PMU_HPMN_CNT_MASK(N) | \
+					 ARMV8_PMU_CNT_MASK_C | \
+					 ARMV8_PMU_CNT_MASK_F)
+#define ARMV8_PMU_HOST_CNT_PART(N)	(ARMV8_PMU_CNT_MASK_ALL & \
+					 ~ARMV8_PMU_GUEST_CNT_PART(N))
 /*
  * PMXEVTYPER: Event selection reg
  */
-- 
2.48.1.502.g6dc24dfdaf-goog


  parent reply	other threads:[~2025-02-08  2:01 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-08  2:01 [RFC PATCH v2 0/4] PMU partitioning driver support Colton Lewis
2025-02-08  2:01 ` [RFC PATCH v2 1/4] perf: arm_pmuv3: Generalize counter bitmasks Colton Lewis
2025-02-08  2:01 ` [RFC PATCH v2 2/4] perf: arm_pmuv3: Introduce module param to partition the PMU Colton Lewis
2025-02-10  7:25   ` Oliver Upton
2025-02-10 23:07     ` Colton Lewis
2025-02-08  2:01 ` Colton Lewis [this message]
2025-02-08  2:01 ` [RFC PATCH v2 4/4] KVM: arm64: Make guests see only counters they can access Colton Lewis
2025-02-10  7:37   ` Oliver Upton
2025-02-10 23:08     ` Colton Lewis

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250208020111.2068239-4-coltonlewis@google.com \
    --to=coltonlewis@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=joey.gouly@arm.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=oliver.upton@linux.dev \
    --cc=pbonzini@redhat.com \
    --cc=shuah@kernel.org \
    --cc=suzuki.poulose@arm.com \
    --cc=will@kernel.org \
    --cc=yuzenghui@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).