From: Steven Price <steven.price@arm.com>
To: Marc Zyngier <maz@kernel.org>
Cc: kvm@vger.kernel.org, Catalin Marinas <catalin.marinas@arm.com>,
linux-doc@vger.kernel.org, Russell King <linux@armlinux.org.uk>,
linux-kernel@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Paolo Bonzini <pbonzini@redhat.com>,
Will Deacon <will@kernel.org>,
kvmarm@lists.cs.columbia.edu
Subject: Re: [PATCH v6 05/10] KVM: arm64: Support stolen time reporting via shared structure
Date: Mon, 21 Oct 2019 11:21:59 +0100 [thread overview]
Message-ID: <1bb10eb5-0fe8-57c9-3b67-9b3661a73d29@arm.com> (raw)
In-Reply-To: <86eez9yoog.wl-maz@kernel.org>
On 19/10/2019 12:12, Marc Zyngier wrote:
> On Fri, 11 Oct 2019 13:59:25 +0100,
> Steven Price <steven.price@arm.com> wrote:
>>
>> Implement the service call for configuring a shared structure between a
>> VCPU and the hypervisor in which the hypervisor can write the time
>> stolen from the VCPU's execution time by other tasks on the host.
>>
>> User space allocates memory which is placed at an IPA also chosen by user
>> space. The hypervisor then updates the shared structure using
>> kvm_put_guest() to ensure single copy atomicity of the 64-bit value
>> reporting the stolen time in nanoseconds.
>>
>> Whenever stolen time is enabled by the guest, the stolen time counter is
>> reset.
>>
>> The stolen time itself is retrieved from the sched_info structure
>> maintained by the Linux scheduler code. We enable SCHEDSTATS when
>> selecting KVM Kconfig to ensure this value is meaningful.
>>
>> Signed-off-by: Steven Price <steven.price@arm.com>
>> ---
>> arch/arm/include/asm/kvm_host.h | 20 +++++++++++
>> arch/arm64/include/asm/kvm_host.h | 21 +++++++++++-
>> arch/arm64/kvm/Kconfig | 1 +
>> include/linux/kvm_types.h | 2 ++
>> virt/kvm/arm/arm.c | 11 ++++++
>> virt/kvm/arm/hypercalls.c | 3 ++
>> virt/kvm/arm/pvtime.c | 56 +++++++++++++++++++++++++++++++
>> 7 files changed, 113 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
>> index 5a0c3569ebde..5c401482d62d 100644
>> --- a/arch/arm/include/asm/kvm_host.h
>> +++ b/arch/arm/include/asm/kvm_host.h
>> @@ -39,6 +39,7 @@
>> KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
>> #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1)
>> #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2)
>> +#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3)
>>
>> DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
>>
>> @@ -329,6 +330,25 @@ static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
>> return SMCCC_RET_NOT_SUPPORTED;
>> }
>>
>> +static inline long kvm_hypercall_stolen_time(struct kvm_vcpu *vcpu)
>> +{
>> + return SMCCC_RET_NOT_SUPPORTED;
>> +}
>> +
>> +static inline int kvm_update_stolen_time(struct kvm_vcpu *vcpu, bool init)
>> +{
>> + return -ENOTSUPP;
>> +}
>> +
>> +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
>> +{
>> +}
>> +
>> +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
>> +{
>> + return false;
>> +}
>> +
>> void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
>>
>> struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
>> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
>> index 93b46d9526d0..1697e63f6dd8 100644
>> --- a/arch/arm64/include/asm/kvm_host.h
>> +++ b/arch/arm64/include/asm/kvm_host.h
>> @@ -44,6 +44,7 @@
>> KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
>> #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1)
>> #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2)
>> +#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3)
>>
>> DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
>>
>> @@ -338,8 +339,14 @@ struct kvm_vcpu_arch {
>> /* True when deferrable sysregs are loaded on the physical CPU,
>> * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
>> bool sysregs_loaded_on_cpu;
>> -};
>>
>> + /* Guest PV state */
>> + struct {
>> + u64 steal;
>> + u64 last_steal;
>> + gpa_t base;
>> + } steal;
>> +};
>
> nit: Please keep an empty line at the end of the structure.
>
>> /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
>> #define vcpu_sve_pffr(vcpu) ((void *)((char *)((vcpu)->arch.sve_state) + \
>> sve_ffr_offset((vcpu)->arch.sve_max_vl)))
>> @@ -479,6 +486,18 @@ int kvm_perf_init(void);
>> int kvm_perf_teardown(void);
>>
>> long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
>> +long kvm_hypercall_stolen_time(struct kvm_vcpu *vcpu);
>> +int kvm_update_stolen_time(struct kvm_vcpu *vcpu, bool init);
>> +
>> +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
>> +{
>> + vcpu_arch->steal.base = GPA_INVALID;
>> +}
>> +
>> +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
>> +{
>> + return (vcpu_arch->steal.base != GPA_INVALID);
>> +}
>>
>> void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
>>
>> diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
>> index a67121d419a2..d8b88e40d223 100644
>> --- a/arch/arm64/kvm/Kconfig
>> +++ b/arch/arm64/kvm/Kconfig
>> @@ -39,6 +39,7 @@ config KVM
>> select IRQ_BYPASS_MANAGER
>> select HAVE_KVM_IRQ_BYPASS
>> select HAVE_KVM_VCPU_RUN_PID_CHANGE
>> + select SCHEDSTATS
>> ---help---
>> Support hosting virtualized guest machines.
>> We don't support KVM with 16K page tables yet, due to the multiple
>> diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
>> index bde5374ae021..1c88e69db3d9 100644
>> --- a/include/linux/kvm_types.h
>> +++ b/include/linux/kvm_types.h
>> @@ -35,6 +35,8 @@ typedef unsigned long gva_t;
>> typedef u64 gpa_t;
>> typedef u64 gfn_t;
>>
>> +#define GPA_INVALID (~(gpa_t)0)
>> +
>> typedef unsigned long hva_t;
>> typedef u64 hpa_t;
>> typedef u64 hfn_t;
>> diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
>> index 86c6aa1cb58e..5d3059aeadb1 100644
>> --- a/virt/kvm/arm/arm.c
>> +++ b/virt/kvm/arm/arm.c
>> @@ -40,6 +40,10 @@
>> #include <asm/kvm_coproc.h>
>> #include <asm/sections.h>
>>
>> +#include <kvm/arm_hypercalls.h>
>> +#include <kvm/arm_pmu.h>
>> +#include <kvm/arm_psci.h>
>> +
>> #ifdef REQUIRES_VIRT
>> __asm__(".arch_extension virt");
>> #endif
>> @@ -351,6 +355,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
>>
>> kvm_arm_reset_debug_ptr(vcpu);
>>
>> + kvm_arm_pvtime_vcpu_init(&vcpu->arch);
>> +
>> return kvm_vgic_vcpu_init(vcpu);
>> }
>>
>> @@ -380,6 +386,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>> kvm_vcpu_load_sysregs(vcpu);
>> kvm_arch_vcpu_load_fp(vcpu);
>> kvm_vcpu_pmu_restore_guest(vcpu);
>> + if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
>> + kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
>>
>> if (single_task_running())
>> vcpu_clear_wfe_traps(vcpu);
>> @@ -645,6 +653,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
>> * that a VCPU sees new virtual interrupts.
>> */
>> kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);
>> +
>> + if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu))
>> + kvm_update_stolen_time(vcpu, false);
>> }
>> }
>>
>> diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c
>> index 97ea8b133e77..5c333a64390e 100644
>> --- a/virt/kvm/arm/hypercalls.c
>> +++ b/virt/kvm/arm/hypercalls.c
>> @@ -56,6 +56,9 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
>> case ARM_SMCCC_HV_PV_TIME_FEATURES:
>> val = kvm_hypercall_pv_features(vcpu);
>> break;
>> + case ARM_SMCCC_HV_PV_TIME_ST:
>> + val = kvm_hypercall_stolen_time(vcpu);
>> + break;
>> default:
>> return kvm_psci_call(vcpu);
>> }
>> diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c
>> index 8d0fad671dcf..a90f1b4ebd13 100644
>> --- a/virt/kvm/arm/pvtime.c
>> +++ b/virt/kvm/arm/pvtime.c
>> @@ -3,8 +3,45 @@
>>
>> #include <linux/arm-smccc.h>
>>
>> +#include <asm/pvclock-abi.h>
>> +
>> #include <kvm/arm_hypercalls.h>
>>
>> +int kvm_update_stolen_time(struct kvm_vcpu *vcpu, bool init)
>> +{
>> + struct kvm *kvm = vcpu->kvm;
>> + u64 steal;
>> + u64 steal_le;
>
> This should be __le64.
>
>> + u64 offset;
>> + int idx;
>> + u64 base = vcpu->arch.steal.base;
>> +
>> + if (base == GPA_INVALID)
>> + return -ENOTSUPP;
>> +
>> + /* Let's do the local bookkeeping */
>> + steal = vcpu->arch.steal.steal;
>> + steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
>> + vcpu->arch.steal.last_steal = current->sched_info.run_delay;
>> + vcpu->arch.steal.steal = steal;
>> +
>> + steal_le = cpu_to_le64(steal);
>> + idx = srcu_read_lock(&kvm->srcu);
>> + if (init) {
>> + struct pvclock_vcpu_stolen_time init_values = {
>> + .revision = 0,
>> + .attributes = 0
>
> nit: 0 is the default initialiser.
>
>> + };
>> + kvm_write_guest(kvm, base, &init_values,
>> + sizeof(init_values));
>> + }
>
> I'm not convinced by this init phase right in the middle of the normal
> path. It looks ugly, and it'd be better if moved out of line. I'd
> suggest:
>
> static void kvm_init_stolen_time(struct kvm_vcpu *vcpu)
> {
> struct pvclock_vcpu_stolen_time init_values = { };
>
> vcpu->arch.steal.steal = 0;
> vcpu->arch.steal.last_steal = current->sched_info.run_delay;
>
> idx = srcu_read_lock(&kvm->srcu);
> kvm_write_guest(kvm, base, &init_values, sizeof(init_values));
> srcu_read_unlock(&kvm->srcu, idx);
> }
>
> and change the two callers accordingly. Or even better, move this code
> to the hypercall handling function, because that's where it actually
> belongs.
Ok, it does add a little bit of duplicated code. But it also gets rid of
the boolean argument that I never liked. As you suggest I might as well
move this into kvm_hypercall_stolen_time().
>> + offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
>> + kvm_put_guest(kvm, base + offset, steal_le, u64);
>> + srcu_read_unlock(&kvm->srcu, idx);
>> +
>> + return 0;
>> +}
>> +
>> long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
>> {
>> u32 feature = smccc_get_arg1(vcpu);
>> @@ -12,6 +49,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
>>
>> switch (feature) {
>> case ARM_SMCCC_HV_PV_TIME_FEATURES:
>> + case ARM_SMCCC_HV_PV_TIME_ST:
>> val = SMCCC_RET_SUCCESS;
>> break;
>> }
>> @@ -19,3 +57,21 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
>> return val;
>> }
>>
>> +long kvm_hypercall_stolen_time(struct kvm_vcpu *vcpu)
>
> Why long? If that's a base address, then it is either a phys_addr_t or
> a gpa_t. I'd suggest you move the error check to the caller.
This is a bit more tricky. It's a long because that's the declared type
of the SMCCC return in kvm_hvc_call_handler(). I can't (easily) move the
code into kvm_hvc_call_handler() because that is compiled for arm (as
well as arm64) and we don't have the definitions for stolen time there.
The best option I could come up with is to have a dummy stub for arm and
use generic types for this function.
This means we need a type which can contain both a gpa_t and the
SMCCC_RET_NOT_SUPPORTED error code.
I'm open to alternative suggestions on how to make this work.
Thanks,
Steve
>> +{
>> + int err;
>> +
>> + /*
>> + * Start counting stolen time from the time the guest requests
>> + * the feature enabled.
>> + */
>> + vcpu->arch.steal.steal = 0;
>> + vcpu->arch.steal.last_steal = current->sched_info.run_delay;
>> +
>> + err = kvm_update_stolen_time(vcpu, true);
>> +
>> + if (err)
>> + return SMCCC_RET_NOT_SUPPORTED;
>> +
>> + return vcpu->arch.steal.base;
>> +}
>> --
>> 2.20.1
>>
>>
>
> Thanks,
>
> M.
>
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
next prev parent reply other threads:[~2019-10-21 10:22 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-11 12:59 [PATCH v6 00/10] arm64: Stolen time support Steven Price
2019-10-11 12:59 ` [PATCH v6 01/10] KVM: arm64: Document PV-time interface Steven Price
2019-10-11 12:59 ` [PATCH v6 02/10] KVM: arm/arm64: Factor out hypercall handling from PSCI code Steven Price
2019-10-11 12:59 ` [PATCH v6 03/10] KVM: arm64: Implement PV_TIME_FEATURES call Steven Price
2019-10-11 12:59 ` [PATCH v6 04/10] KVM: Implement kvm_put_guest() Steven Price
2019-10-11 12:59 ` [PATCH v6 05/10] KVM: arm64: Support stolen time reporting via shared structure Steven Price
2019-10-19 11:12 ` Marc Zyngier
2019-10-21 10:21 ` Steven Price [this message]
2019-10-21 10:40 ` Marc Zyngier
2019-10-21 11:24 ` Steven Price
2019-10-11 12:59 ` [PATCH v6 06/10] KVM: Allow kvm_device_ops to be const Steven Price
2019-10-11 12:59 ` [PATCH v6 07/10] KVM: arm64: Provide VCPU attributes for stolen time Steven Price
2019-10-19 11:28 ` Marc Zyngier
2019-10-21 11:00 ` Steven Price
2019-10-11 12:59 ` [PATCH v6 08/10] arm/arm64: Provide a wrapper for SMCCC 1.1 calls Steven Price
2019-10-21 11:42 ` Marc Zyngier
2019-10-21 13:43 ` Steven Price
2019-10-21 14:05 ` Marc Zyngier
2019-10-11 12:59 ` [PATCH v6 09/10] arm/arm64: Make use of the SMCCC 1.1 wrapper Steven Price
2019-10-11 12:59 ` [PATCH v6 10/10] arm64: Retrieve stolen time as paravirtualized guest Steven Price
2019-10-19 20:28 ` Marc Zyngier
2019-10-21 5:01 ` Jürgen Groß
2019-10-21 7:55 ` Marc Zyngier
2019-10-21 12:14 ` Steven Price
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=1bb10eb5-0fe8-57c9-3b67-9b3661a73d29@arm.com \
--to=steven.price@arm.com \
--cc=catalin.marinas@arm.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=maz@kernel.org \
--cc=pbonzini@redhat.com \
--cc=will@kernel.org \
/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).