All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoffer Dall <cdall@linaro.org>
To: kvmarm@lists.cs.columbia.edu, linux-arm-kernel@lists.infradead.org
Cc: kvm@vger.kernel.org, Marc Zyngier <marc.zyngier@arm.com>,
	Christoffer Dall <cdall@linaro.org>
Subject: [RFC PATCH v2 01/19] arm64: Use physical counter for in-kernel reads
Date: Mon, 17 Jul 2017 16:27:00 +0200	[thread overview]
Message-ID: <20170717142718.13853-2-cdall@linaro.org> (raw)
In-Reply-To: <20170717142718.13853-1-cdall@linaro.org>

Using the physical counter allows KVM to retain the offset between the
virtual and physical counter as long as it is actively running a VCPU.

As soon as a VCPU is released, another thread is scheduled or we start
running userspace applications, we reset the offset to 0, so that
userspace accessing the virtual timer can still read the cirtual counter
and get the same view of time as the kernel.

This opens up potential improvements for KVM performance.

VHE kernels or kernels continuing to use the virtual timer should be
unaffected.

Signed-off-by: Christoffer Dall <cdall@linaro.org>
---
 arch/arm64/include/asm/arch_timer.h  | 6 ++++--
 drivers/clocksource/arm_arch_timer.c | 3 +--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 74d08e4..ee5619b 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -148,11 +148,13 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 
 static inline u64 arch_counter_get_cntpct(void)
 {
+	u64 cval;
 	/*
 	 * AArch64 kernel and user space mandate the use of CNTVCT.
 	 */
-	BUG();
-	return 0;
+	isb();
+	asm volatile("mrs %0, cntpct_el0" : "=r" (cval));
+	return cval;
 }
 
 static inline u64 arch_counter_get_cntvct(void)
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index aae87c4..c24327c 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -886,8 +886,7 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_TIMER_TYPE_CP15) {
-		if (IS_ENABLED(CONFIG_ARM64) ||
-		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
+		if (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
-- 
2.9.0

WARNING: multiple messages have this Message-ID (diff)
From: cdall@linaro.org (Christoffer Dall)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCH v2 01/19] arm64: Use physical counter for in-kernel reads
Date: Mon, 17 Jul 2017 16:27:00 +0200	[thread overview]
Message-ID: <20170717142718.13853-2-cdall@linaro.org> (raw)
In-Reply-To: <20170717142718.13853-1-cdall@linaro.org>

Using the physical counter allows KVM to retain the offset between the
virtual and physical counter as long as it is actively running a VCPU.

As soon as a VCPU is released, another thread is scheduled or we start
running userspace applications, we reset the offset to 0, so that
userspace accessing the virtual timer can still read the cirtual counter
and get the same view of time as the kernel.

This opens up potential improvements for KVM performance.

VHE kernels or kernels continuing to use the virtual timer should be
unaffected.

Signed-off-by: Christoffer Dall <cdall@linaro.org>
---
 arch/arm64/include/asm/arch_timer.h  | 6 ++++--
 drivers/clocksource/arm_arch_timer.c | 3 +--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 74d08e4..ee5619b 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -148,11 +148,13 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 
 static inline u64 arch_counter_get_cntpct(void)
 {
+	u64 cval;
 	/*
 	 * AArch64 kernel and user space mandate the use of CNTVCT.
 	 */
-	BUG();
-	return 0;
+	isb();
+	asm volatile("mrs %0, cntpct_el0" : "=r" (cval));
+	return cval;
 }
 
 static inline u64 arch_counter_get_cntvct(void)
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index aae87c4..c24327c 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -886,8 +886,7 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_TIMER_TYPE_CP15) {
-		if (IS_ENABLED(CONFIG_ARM64) ||
-		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
+		if (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
-- 
2.9.0

  reply	other threads:[~2017-07-17 14:27 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-17 14:26 [RFC PATCH v2 00/19] KVM: arm/arm64: Optimize arch timer register handling Christoffer Dall
2017-07-17 14:26 ` Christoffer Dall
2017-07-17 14:27 ` Christoffer Dall [this message]
2017-07-17 14:27   ` [RFC PATCH v2 01/19] arm64: Use physical counter for in-kernel reads Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 02/19] arm64: Use the physical counter when available for read_cycles Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-25  9:43   ` Will Deacon
2017-07-25  9:43     ` Will Deacon
2017-07-25 14:36     ` Christoffer Dall
2017-07-25 14:36       ` Christoffer Dall
2017-07-26 17:17       ` Will Deacon
2017-07-26 17:17         ` Will Deacon
2017-07-27  7:14         ` Christoffer Dall
2017-07-27  7:14           ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 03/19] KVM: arm/arm64: Guard kvm_vgic_map_is_active against !vgic_initialized Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 04/19] KVM: arm/arm64: Support calling vgic_update_irq_pending from irq context Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 05/19] KVM: arm/arm64: Check that system supports split eoi/deactivate Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-08-01 11:35   ` Marc Zyngier
2017-08-01 11:35     ` Marc Zyngier
2017-08-01 12:26     ` Christoffer Dall
2017-08-01 12:26       ` Christoffer Dall
2017-08-01 12:37       ` Marc Zyngier
2017-08-01 12:37         ` Marc Zyngier
2017-08-01 12:54         ` Christoffer Dall
2017-08-01 12:54           ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 06/19] KVM: arm/arm64: Make timer_arm and timer_disarm helpers more generic Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-08-01 14:10   ` Marc Zyngier
2017-08-01 14:10     ` Marc Zyngier
2017-08-01 14:57     ` Christoffer Dall
2017-08-01 14:57       ` Christoffer Dall
2017-08-01 15:41       ` Marc Zyngier
2017-08-01 15:41         ` Marc Zyngier
2017-07-17 14:27 ` [RFC PATCH v2 07/19] KVM: arm/arm64: Rename soft timer to bg_timer Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 08/19] KVM: arm/arm64: Use separate timer for phys timer emulation Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 09/19] KVM: arm/arm64: Move timer/vgic flush/sync under disabled irq Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 10/19] KVM: arm/arm64: Move timer save/restore out of the hyp code Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 11/19] genirq: Document vcpu_info usage for per-CPU interrupts Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-08-01 16:15   ` Marc Zyngier
2017-08-01 16:15     ` Marc Zyngier
2017-08-01 16:57     ` Christoffer Dall
2017-08-01 16:57       ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 12/19] KVM: arm/arm64: Set VCPU affinity for virt timer irq Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 13/19] KVM: arm/arm64: Avoid timer save/restore in vcpu entry/exit Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 14/19] KVM: arm/arm64: Support EL1 phys timer register access in set/get reg Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 15/19] KVM: arm/arm64: Use kvm_arm_timer_set/get_reg for guest register traps Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 16/19] KVM: arm/arm64: Move phys_timer_emulate function Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 17/19] KVM: arm/arm64: Avoid phys timer emulation in vcpu entry/exit Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 18/19] KVM: arm/arm64: Get rid of kvm_timer_flush_hwstate Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall
2017-07-17 14:27 ` [RFC PATCH v2 19/19] KVM: arm/arm64: Rework kvm_timer_should_fire Christoffer Dall
2017-07-17 14:27   ` Christoffer Dall

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=20170717142718.13853-2-cdall@linaro.org \
    --to=cdall@linaro.org \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=marc.zyngier@arm.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.