linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zenghui Yu <yuzenghui@huawei.com>
To: Steven Price <steven.price@arm.com>,
	Marc Zyngier <maz@kernel.org>, "Will Deacon" <will@kernel.org>,
	<linux-arm-kernel@lists.infradead.org>,
	<kvmarm@lists.cs.columbia.edu>
Cc: <linux-kernel@vger.kernel.org>, <kvm@vger.kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	<linux-doc@vger.kernel.org>, Russell King <linux@armlinux.org.uk>,
	Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: [PATCH v3 10/10] arm64: Retrieve stolen time as paravirtualized guest
Date: Fri, 23 Aug 2019 19:45:48 +0800	[thread overview]
Message-ID: <6040a45c-fc39-a33e-c6a4-7baa586c247c@huawei.com> (raw)
In-Reply-To: <20190821153656.33429-11-steven.price@arm.com>

Hi Steven,

On 2019/8/21 23:36, Steven Price wrote:
> 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>
> ---
>   arch/arm64/include/asm/paravirt.h |   9 +-
>   arch/arm64/kernel/paravirt.c      | 148 ++++++++++++++++++++++++++++++
>   arch/arm64/kernel/time.c          |   3 +
>   include/linux/cpuhotplug.h        |   1 +
>   4 files changed, 160 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
> index 799d9dd6f7cc..125c26c42902 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 kvm_guest_init(void);
> +
> +#else
> +
> +#define kvm_guest_init()
> +
> +#endif // CONFIG_PARAVIRT
>   
>   #endif
> diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
> index 4cfed91fe256..ea8dbbbd3293 100644
> --- a/arch/arm64/kernel/paravirt.c
> +++ b/arch/arm64/kernel/paravirt.c
> @@ -6,13 +6,161 @@
>    * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
>    */
>   
> +#define pr_fmt(fmt) "kvmarm-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 kvmarm_stolen_time_region {
> +	struct pvclock_vcpu_stolen_time *kaddr;
> +};
> +
> +static DEFINE_PER_CPU(struct kvmarm_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 kvm_steal_clock(int cpu)
> +{
> +	struct kvmarm_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 disable_stolen_time_current_cpu(void)
> +{
> +	struct kvmarm_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 stolen_time_dying_cpu(unsigned int cpu)
> +{
> +	return disable_stolen_time_current_cpu();
> +}
> +
> +static int init_stolen_time_cpu(unsigned int cpu)
> +{
> +	struct kvmarm_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 ((long)res.a0 < 0)
> +		return -EINVAL;
> +
> +	reg->kaddr = memremap(res.a0,
> +			      sizeof(struct pvclock_vcpu_stolen_time),
> +			      MEMREMAP_WB);

cpuhp callbacks can be invoked in atomic context (see:
	secondary_start_kernel ->
	notify_cpu_starting ->
	invoke callbacks),
but memremap might sleep...

Try to run a DEBUG_ATOMIC_SLEEP enabled PV guest, I guess we will be
greeted by the Sleep-in-Atomic-Context BUG.  We need an alternative
here?

> +
> +	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("Unexpected revision or attributes in stolen time data\n");
> +		return -ENXIO;
> +	}
> +
> +	return 0;
> +}
> +
> +static int kvm_arm_init_stolen_time(void)
> +{
> +	int ret;
> +
> +	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
> +				"hypervisor/kvmarm/pv:starting",
> +				init_stolen_time_cpu, stolen_time_dying_cpu);
> +	if (ret < 0)
> +		return ret;
> +	return 0;
> +}
> +
> +static bool has_kvm_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_FEATURES, &res);
> +
> +	if (res.a0 != SMCCC_RET_SUCCESS)
> +		return false;
> +
> +	arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_FEATURES,
> +			     ARM_SMCCC_HV_PV_TIME_ST, &res);
> +
> +	if (res.a0 != SMCCC_RET_SUCCESS)
> +		return false;
> +
> +	return true;
> +}
> +
> +int __init kvm_guest_init(void)
> +{
> +	int ret = 0;

And this look like a redundant initialization?


Thanks,
zenghui

> +
> +	if (!has_kvm_steal_clock())
> +		return 0;
> +
> +	ret = kvm_arm_init_stolen_time();
> +	if (ret)
> +		return ret;
> +
> +	pv_ops.time.steal_clock = kvm_steal_clock;
> +
> +	static_key_slow_inc(&paravirt_steal_enabled);
> +	if (steal_acc)
> +		static_key_slow_inc(&paravirt_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..a52aea14c6ec 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;
> +
> +	kvm_guest_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,
> 


  reply	other threads:[~2019-08-23 11:48 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-21 15:36 [PATCH v3 00/10] arm64: Stolen time support Steven Price
2019-08-21 15:36 ` [PATCH v3 01/10] KVM: arm64: Document PV-time interface Steven Price
2019-08-27  8:44   ` Christoffer Dall
2019-08-28 11:23     ` Steven Price
2019-08-27  8:57   ` Christoffer Dall
2019-08-28 12:09     ` Steven Price
2019-08-30  9:22       ` Christoffer Dall
2019-08-28 13:49     ` Christoffer Dall
2019-08-29 15:21       ` Steven Price
2019-08-29 17:15   ` Andrew Jones
2019-08-30  8:35     ` Steven Price
2019-08-21 15:36 ` [PATCH v3 02/10] KVM: arm/arm64: Factor out hypercall handling from PSCI code Steven Price
2019-08-21 15:36 ` [PATCH v3 03/10] KVM: arm64: Implement PV_FEATURES call Steven Price
2019-08-21 15:36 ` [PATCH v3 04/10] KVM: Implement kvm_put_guest() Steven Price
2019-08-22 10:29   ` Jonathan Cameron
2019-08-22 10:37     ` Steven Price
2019-08-22 15:28   ` Sean Christopherson
2019-08-22 15:46     ` Steven Price
2019-08-22 16:24       ` Sean Christopherson
2019-08-23 10:33         ` Steven Price
2019-08-21 15:36 ` [PATCH v3 05/10] KVM: arm64: Support stolen time reporting via shared structure Steven Price
2019-08-22 10:39   ` Jonathan Cameron
2019-08-22 11:00     ` Steven Price
2019-08-23 12:07   ` Zenghui Yu
2019-08-23 13:23     ` Steven Price
2019-08-21 15:36 ` [PATCH v3 06/10] KVM: Allow kvm_device_ops to be const Steven Price
2019-08-21 15:36 ` [PATCH v3 07/10] KVM: arm64: Provide a PV_TIME device to user space Steven Price
2019-08-22 10:57   ` Jonathan Cameron
2019-08-22 11:11     ` Steven Price
2019-08-22 11:48       ` Jonathan Cameron
2019-08-21 15:36 ` [PATCH v3 08/10] arm/arm64: Provide a wrapper for SMCCC 1.1 calls Steven Price
2019-08-21 15:36 ` [PATCH v3 09/10] arm/arm64: Make use of the SMCCC 1.1 wrapper Steven Price
2019-08-21 15:36 ` [PATCH v3 10/10] arm64: Retrieve stolen time as paravirtualized guest Steven Price
2019-08-23 11:45   ` Zenghui Yu [this message]
2019-08-23 14:22     ` Steven Price
2019-08-27 12:43       ` Zenghui Yu

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=6040a45c-fc39-a33e-c6a4-7baa586c247c@huawei.com \
    --to=yuzenghui@huawei.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=steven.price@arm.com \
    --cc=will@kernel.org \
    --subject='Re: [PATCH v3 10/10] arm64: Retrieve stolen time as paravirtualized guest' \
    /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

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).