From: Marc Zyngier <maz@kernel.org>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
"Radim Krčmář" <rkrcmar@redhat.com>
Cc: Alexander Graf <graf@amazon.com>,
Andrew Jones <drjones@redhat.com>,
Christian Borntraeger <borntraeger@de.ibm.com>,
Christoffer Dall <christoffer.dall@arm.com>,
Eric Auger <eric.auger@redhat.com>,
Heinrich Schuchardt <xypron.glpk@gmx.de>,
Julien Grall <julien.grall@arm.com>,
Mark Rutland <mark.rutland@arm.com>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Steven Price <steven.price@arm.com>,
Thomas Gleixner <tglx@linutronix.de>,
Will Deacon <will@kernel.org>, Zenghui Yu <yuzenghui@huawei.com>,
James Morse <james.morse@arm.com>,
Julien Thierry <julien.thierry.kdev@gmail.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
linux-arm-kernel@lists.infradead.org, kvm@vger.kernel.org,
kvmarm@lists.cs.columbia.edu
Subject: [PATCH 12/22] arm64: Retrieve stolen time as paravirtualized guest
Date: Wed, 20 Nov 2019 16:42:26 +0000 [thread overview]
Message-ID: <20191120164236.29359-13-maz@kernel.org> (raw)
In-Reply-To: <20191120164236.29359-1-maz@kernel.org>
From: Steven Price <steven.price@arm.com>
Enable paravirtualization features when running under a hypervisor
supporting the PV_TIME_ST hypercall.
For each (v)CPU, we ask the hypervisor for the location of a shared
page which the hypervisor will use to report stolen time to us. We set
pv_time_ops to the stolen time function which simply reads the stolen
value from the shared page for a VCPU. We guarantee single-copy
atomicity using READ_ONCE which means we can also read the stolen
time for another VCPU than the currently running one while it is
potentially being updated by the hypervisor.
Signed-off-by: Steven Price <steven.price@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
.../admin-guide/kernel-parameters.txt | 6 +-
arch/arm64/include/asm/paravirt.h | 9 +-
arch/arm64/kernel/paravirt.c | 140 ++++++++++++++++++
arch/arm64/kernel/time.c | 3 +
include/linux/cpuhotplug.h | 1 +
5 files changed, 155 insertions(+), 4 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a84a83f8881e..19f465530e86 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3083,9 +3083,9 @@
[X86,PV_OPS] Disable paravirtualized VMware scheduler
clock and use the default one.
- no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting.
- steal time is computed, but won't influence scheduler
- behaviour
+ no-steal-acc [X86,KVM,ARM64] Disable paravirtualized steal time
+ accounting. steal time is computed, but won't
+ influence scheduler behaviour
nolapic [X86-32,APIC] Do not enable or use the local APIC.
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index 799d9dd6f7cc..cf3a0fd7c1a7 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu)
{
return pv_ops.time.steal_clock(cpu);
}
-#endif
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif // CONFIG_PARAVIRT
#endif
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 4cfed91fe256..1ef702b0be2d 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -6,13 +6,153 @@
* Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
*/
+#define pr_fmt(fmt) "arm-pv: " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/cpuhotplug.h>
#include <linux/export.h>
+#include <linux/io.h>
#include <linux/jump_label.h>
+#include <linux/printk.h>
+#include <linux/psci.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
#include <linux/types.h>
+
#include <asm/paravirt.h>
+#include <asm/pvclock-abi.h>
+#include <asm/smp_plat.h>
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
struct paravirt_patch_template pv_ops;
EXPORT_SYMBOL_GPL(pv_ops);
+
+struct pv_time_stolen_time_region {
+ struct pvclock_vcpu_stolen_time *kaddr;
+};
+
+static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+ steal_acc = false;
+ return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+/* return stolen time in ns by asking the hypervisor */
+static u64 pv_steal_clock(int cpu)
+{
+ struct pv_time_stolen_time_region *reg;
+
+ reg = per_cpu_ptr(&stolen_time_region, cpu);
+ if (!reg->kaddr) {
+ pr_warn_once("stolen time enabled but not configured for cpu %d\n",
+ cpu);
+ return 0;
+ }
+
+ return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
+}
+
+static int stolen_time_dying_cpu(unsigned int cpu)
+{
+ struct pv_time_stolen_time_region *reg;
+
+ reg = this_cpu_ptr(&stolen_time_region);
+ if (!reg->kaddr)
+ return 0;
+
+ memunmap(reg->kaddr);
+ memset(reg, 0, sizeof(*reg));
+
+ return 0;
+}
+
+static int init_stolen_time_cpu(unsigned int cpu)
+{
+ struct pv_time_stolen_time_region *reg;
+ struct arm_smccc_res res;
+
+ reg = this_cpu_ptr(&stolen_time_region);
+
+ arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+ if (res.a0 == SMCCC_RET_NOT_SUPPORTED)
+ return -EINVAL;
+
+ reg->kaddr = memremap(res.a0,
+ sizeof(struct pvclock_vcpu_stolen_time),
+ MEMREMAP_WB);
+
+ if (!reg->kaddr) {
+ pr_warn("Failed to map stolen time data structure\n");
+ return -ENOMEM;
+ }
+
+ if (le32_to_cpu(reg->kaddr->revision) != 0 ||
+ le32_to_cpu(reg->kaddr->attributes) != 0) {
+ pr_warn_once("Unexpected revision or attributes in stolen time data\n");
+ return -ENXIO;
+ }
+
+ return 0;
+}
+
+static int pv_time_init_stolen_time(void)
+{
+ int ret;
+
+ ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
+ "hypervisor/arm/pvtime:starting",
+ init_stolen_time_cpu, stolen_time_dying_cpu);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+static bool has_pv_steal_clock(void)
+{
+ struct arm_smccc_res res;
+
+ /* To detect the presence of PV time support we require SMCCC 1.1+ */
+ if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+ return false;
+
+ arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+ ARM_SMCCC_HV_PV_TIME_FEATURES, &res);
+
+ if (res.a0 != SMCCC_RET_SUCCESS)
+ return false;
+
+ arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES,
+ ARM_SMCCC_HV_PV_TIME_ST, &res);
+
+ return (res.a0 == SMCCC_RET_SUCCESS);
+}
+
+int __init pv_time_init(void)
+{
+ int ret;
+
+ if (!has_pv_steal_clock())
+ return 0;
+
+ ret = pv_time_init_stolen_time();
+ if (ret)
+ return ret;
+
+ pv_ops.time.steal_clock = pv_steal_clock;
+
+ static_key_slow_inc(¶virt_steal_enabled);
+ if (steal_acc)
+ static_key_slow_inc(¶virt_steal_rq_enabled);
+
+ pr_info("using stolen time PV\n");
+
+ return 0;
+}
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 0b2946414dc9..73f06d4b3aae 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -30,6 +30,7 @@
#include <asm/thread_info.h>
#include <asm/stacktrace.h>
+#include <asm/paravirt.h>
unsigned long profile_pc(struct pt_regs *regs)
{
@@ -65,4 +66,6 @@ void __init time_init(void)
/* Calibrate the delay loop directly */
lpj_fine = arch_timer_rate / HZ;
+
+ pv_time_init();
}
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 068793a619ca..89d75edb5750 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -136,6 +136,7 @@ enum cpuhp_state {
/* Must be the last timer callback */
CPUHP_AP_DUMMY_TIMER_STARTING,
CPUHP_AP_ARM_XEN_STARTING,
+ CPUHP_AP_ARM_KVMPV_STARTING,
CPUHP_AP_ARM_CORESIGHT_STARTING,
CPUHP_AP_ARM64_ISNDEP_STARTING,
CPUHP_AP_SMPCFD_DYING,
--
2.20.1
next prev parent reply other threads:[~2019-11-20 16:52 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-20 16:42 [GIT PULL] KVM/arm updates for 5.5 Marc Zyngier
2019-11-20 16:42 ` [PATCH 01/22] KVM: arm/arm64: Allow reporting non-ISV data aborts to userspace Marc Zyngier
2019-11-20 16:42 ` [PATCH 02/22] KVM: arm/arm64: Allow user injection of external data aborts Marc Zyngier
2019-11-20 16:42 ` [PATCH 03/22] KVM: arm64: Document PV-time interface Marc Zyngier
2019-11-20 16:42 ` [PATCH 04/22] KVM: arm/arm64: Factor out hypercall handling from PSCI code Marc Zyngier
2019-11-20 16:42 ` [PATCH 05/22] KVM: arm64: Implement PV_TIME_FEATURES call Marc Zyngier
2019-11-20 16:42 ` [PATCH 06/22] KVM: Implement kvm_put_guest() Marc Zyngier
2019-11-20 16:42 ` [PATCH 07/22] KVM: arm64: Support stolen time reporting via shared structure Marc Zyngier
2019-11-20 16:42 ` [PATCH 08/22] KVM: Allow kvm_device_ops to be const Marc Zyngier
2019-11-20 16:42 ` [PATCH 09/22] KVM: arm64: Provide VCPU attributes for stolen time Marc Zyngier
2019-11-20 16:42 ` [PATCH 10/22] arm/arm64: Provide a wrapper for SMCCC 1.1 calls Marc Zyngier
2019-11-20 16:42 ` [PATCH 11/22] arm/arm64: Make use of the SMCCC 1.1 wrapper Marc Zyngier
2019-11-20 16:42 ` Marc Zyngier [this message]
2019-11-20 16:42 ` [PATCH 13/22] KVM: arm64: Select TASK_DELAY_ACCT+TASKSTATS rather than SCHEDSTATS Marc Zyngier
2019-11-20 16:42 ` [PATCH 14/22] KVM: arm/arm64: Show halt poll counters in debugfs Marc Zyngier
2019-11-20 16:42 ` [PATCH 15/22] KVM: arm64: Don't set HCR_EL2.TVM when S2FWB is supported Marc Zyngier
2019-11-20 16:42 ` [PATCH 16/22] KVM: arm64: vgic-v4: Move the GICv4 residency flow to be driven by vcpu_load/put Marc Zyngier
2019-11-20 16:42 ` [PATCH 17/22] KVM: arm/arm64: vgic: Remove the declaration of kvm_send_userspace_msi() Marc Zyngier
2019-11-20 16:42 ` [PATCH 18/22] KVM: arm/arm64: vgic: Fix some comments typo Marc Zyngier
2019-11-20 16:42 ` [PATCH 19/22] KVM: arm/arm64: vgic: Don't rely on the wrong pending table Marc Zyngier
2019-11-20 16:42 ` [PATCH 20/22] KVM: arm/arm64: Let the timer expire in hardirq context on RT Marc Zyngier
2019-11-20 16:42 ` [PATCH 21/22] KVM: vgic-v4: Track the number of VLPIs per vcpu Marc Zyngier
2019-11-20 16:42 ` [PATCH 22/22] KVM: arm64: Opportunistically turn off WFI trapping when using direct LPI injection Marc Zyngier
2019-11-21 8:58 ` [GIT PULL] KVM/arm updates for 5.5 Paolo Bonzini
2019-11-21 9:06 ` Marc Zyngier
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=20191120164236.29359-13-maz@kernel.org \
--to=maz@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=borntraeger@de.ibm.com \
--cc=christoffer.dall@arm.com \
--cc=drjones@redhat.com \
--cc=eric.auger@redhat.com \
--cc=graf@amazon.com \
--cc=james.morse@arm.com \
--cc=julien.grall@arm.com \
--cc=julien.thierry.kdev@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=mark.rutland@arm.com \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
--cc=steven.price@arm.com \
--cc=suzuki.poulose@arm.com \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
--cc=xypron.glpk@gmx.de \
--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).