linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Nicholas Piggin" <npiggin@gmail.com>
To: "Yu Zhao" <yuzhao@google.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>
Cc: "Alistair Popple" <apopple@nvidia.com>,
	"Anup Patel" <anup@brainfault.org>,
	"Ben Gardon" <bgardon@google.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Chao Peng" <chao.p.peng@linux.intel.com>,
	"Christophe Leroy" <christophe.leroy@csgroup.eu>,
	"Dave Hansen" <dave.hansen@linux.intel.com>,
	"Fabiano Rosas" <farosas@linux.ibm.com>,
	"Gaosheng Cui" <cuigaosheng1@huawei.com>,
	"Gavin Shan" <gshan@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"James Morse" <james.morse@arm.com>,
	"Jason A. Donenfeld" <Jason@zx2c4.com>,
	"Jason Gunthorpe" <jgg@ziepe.ca>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Marc Zyngier" <maz@kernel.org>,
	"Masami Hiramatsu" <mhiramat@kernel.org>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Michael Larabel" <michael@michaellarabel.com>,
	"Mike Rapoport" <rppt@kernel.org>,
	"Oliver Upton" <oliver.upton@linux.dev>,
	"Paul Mackerras" <paulus@ozlabs.org>,
	"Peter Xu" <peterx@redhat.com>,
	"Sean Christopherson" <seanjc@google.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Suzuki K Poulose" <suzuki.poulose@arm.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Thomas Huth" <thuth@redhat.com>, "Will Deacon" <will@kernel.org>,
	"Zenghui Yu" <yuzenghui@huawei.com>, <kvmarm@lists.linux.dev>,
	<kvm@vger.kernel.org>, <linux-arm-kernel@lists.infradead.org>,
	<linux-doc@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<linux-mm@kvack.org>, <linuxppc-dev@lists.ozlabs.org>,
	<linux-trace-kernel@vger.kernel.org>, <x86@kernel.org>,
	<linux-mm@google.com>
Subject: Re: [PATCH mm-unstable v2 07/10] kvm/powerpc: add kvm_arch_test_clear_young()
Date: Tue, 20 Jun 2023 17:47:47 +1000	[thread overview]
Message-ID: <CTHB6A4EL3IH.3UJFAJ4LV85X6@wheely> (raw)
In-Reply-To: <20230526234435.662652-8-yuzhao@google.com>

On Sat May 27, 2023 at 9:44 AM AEST, Yu Zhao wrote:
> Implement kvm_arch_test_clear_young() to support the fast path in
> mmu_notifier_ops->test_clear_young().
>
> It focuses on a simple case, i.e., radix MMU sets the accessed bit in
> KVM PTEs and VMs are not nested, where it can rely on RCU and
> pte_xchg() to safely clear the accessed bit without taking
> kvm->mmu_lock. Complex cases fall back to the existing slow path
> where kvm->mmu_lock is then taken.
>
> Signed-off-by: Yu Zhao <yuzhao@google.com>
> ---
>  arch/powerpc/include/asm/kvm_host.h    |  8 ++++
>  arch/powerpc/include/asm/kvm_ppc.h     |  1 +
>  arch/powerpc/kvm/book3s.c              |  6 +++
>  arch/powerpc/kvm/book3s.h              |  1 +
>  arch/powerpc/kvm/book3s_64_mmu_radix.c | 59 ++++++++++++++++++++++++++
>  arch/powerpc/kvm/book3s_hv.c           |  5 +++
>  6 files changed, 80 insertions(+)
>
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index 14ee0dece853..75c260ea8a9e 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -883,4 +883,12 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
>  static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
>  
> +#define kvm_arch_has_test_clear_young kvm_arch_has_test_clear_young
> +static inline bool kvm_arch_has_test_clear_young(void)
> +{
> +	return IS_ENABLED(CONFIG_KVM_BOOK3S_HV_POSSIBLE) &&
> +	       cpu_has_feature(CPU_FTR_HVMODE) && cpu_has_feature(CPU_FTR_ARCH_300) &&
> +	       radix_enabled();

This could probably be radix_enabled() && !kvmhv_on_pseries(). Although
unclear why not nested hypervisor... I'd have to think about it a bit
more. Do you have any idea what might go wrong, or just didn't have the
time to consider it? (Not just powerpc nested but any others).

> +}
> +
>  #endif /* __POWERPC_KVM_HOST_H__ */
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 79a9c0bb8bba..ff1af6a7b44f 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -287,6 +287,7 @@ struct kvmppc_ops {
>  	bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);
>  	bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
>  	bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
> +	bool (*test_clear_young)(struct kvm *kvm, struct kvm_gfn_range *range);
>  	bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
>  	void (*free_memslot)(struct kvm_memory_slot *slot);
>  	int (*init_vm)(struct kvm *kvm);
> diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
> index 686d8d9eda3e..37bf40b0c4ff 100644
> --- a/arch/powerpc/kvm/book3s.c
> +++ b/arch/powerpc/kvm/book3s.c
> @@ -899,6 +899,12 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
>  	return kvm->arch.kvm_ops->test_age_gfn(kvm, range);
>  }
>  
> +bool kvm_arch_test_clear_young(struct kvm *kvm, struct kvm_gfn_range *range)
> +{
> +	return !kvm->arch.kvm_ops->test_clear_young ||
> +	       kvm->arch.kvm_ops->test_clear_young(kvm, range);
> +}
> +
>  bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
>  {
>  	return kvm->arch.kvm_ops->set_spte_gfn(kvm, range);
> diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
> index 58391b4b32ed..fa2659e21ccc 100644
> --- a/arch/powerpc/kvm/book3s.h
> +++ b/arch/powerpc/kvm/book3s.h
> @@ -12,6 +12,7 @@ extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
>  extern bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range);
>  extern bool kvm_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
>  extern bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
> +extern bool kvm_test_clear_young_hv(struct kvm *kvm, struct kvm_gfn_range *range);
>  extern bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
>  
>  extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu);
> diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
> index 3b65b3b11041..0a392e9a100a 100644
> --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
> +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
> @@ -1088,6 +1088,65 @@ bool kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
>  	return ref;
>  }
>  
> +bool kvm_test_clear_young_hv(struct kvm *kvm, struct kvm_gfn_range *range)
> +{
> +	bool err;
> +	gfn_t gfn = range->start;
> +
> +	rcu_read_lock();
> +
> +	err = !kvm_is_radix(kvm);
> +	if (err)
> +		goto unlock;
> +
> +	/*
> +	 * Case 1:  This function          kvmppc_switch_mmu_to_hpt()
> +	 *
> +	 *          rcu_read_lock()
> +	 *          Test kvm_is_radix()    kvm->arch.radix = 0
> +	 *          Use kvm->arch.pgtable  synchronize_rcu()
> +	 *          rcu_read_unlock()
> +	 *                                 kvmppc_free_radix()
> +	 *
> +	 *
> +	 * Case 2:  This function          kvmppc_switch_mmu_to_radix()
> +	 *
> +	 *                                 kvmppc_init_vm_radix()
> +	 *                                 smp_wmb()
> +	 *          Test kvm_is_radix()    kvm->arch.radix = 1
> +	 *          smp_rmb()
> +	 *          Use kvm->arch.pgtable
> +	 */
> +	smp_rmb();

Comment could stand to expand slightly on what you are solving, in
words.

If you use synchronize_rcu() on both sides, you wouldn't need the
barrier, right?

> +	while (gfn < range->end) {
> +		pte_t *ptep;
> +		pte_t old, new;
> +		unsigned int shift;
> +
> +		ptep = find_kvm_secondary_pte_unlocked(kvm, gfn * PAGE_SIZE, &shift);
> +		if (!ptep)
> +			goto next;
> +
> +		VM_WARN_ON_ONCE(!page_count(virt_to_page(ptep)));

Not really appropriate at the KVM level. mm enforces this kind of
thing (with notifiers).

> +
> +		old = READ_ONCE(*ptep);
> +		if (!pte_present(old) || !pte_young(old))
> +			goto next;
> +
> +		new = pte_mkold(old);
> +
> +		if (kvm_should_clear_young(range, gfn))
> +			pte_xchg(ptep, old, new);

*Probably* will work. I can't think of a reason why not at the
moment anyway :)

Thanks,
Nick
> +next:
> +		gfn += shift ? BIT(shift - PAGE_SHIFT) : 1;
> +	}
> +unlock:
> +	rcu_read_unlock();
> +
> +	return err;
> +}
> +
>  /* Returns the number of PAGE_SIZE pages that are dirty */
>  static int kvm_radix_test_clear_dirty(struct kvm *kvm,
>  				struct kvm_memory_slot *memslot, int pagenum)
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 130bafdb1430..20a81ec9fde8 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -5262,6 +5262,8 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
>  	spin_lock(&kvm->mmu_lock);
>  	kvm->arch.radix = 0;
>  	spin_unlock(&kvm->mmu_lock);
> +	/* see the comments in kvm_test_clear_young_hv() */

I'm guilty of such comments at times, but it wouldn't hurt to say
	/* Finish concurrent kvm_test_clear_young_hv access to page tables */

Then you know where to look for more info and you have a vague
idea what it's for.

> +	synchronize_rcu();

>  	kvmppc_free_radix(kvm);
>  
>  	lpcr = LPCR_VPM1;
> @@ -5286,6 +5288,8 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
>  	if (err)
>  		return err;
>  	kvmppc_rmap_reset(kvm);
> +	/* see the comments in kvm_test_clear_young_hv() */
> +	smp_wmb();
>  	/* Mutual exclusion with kvm_unmap_gfn_range etc. */
>  	spin_lock(&kvm->mmu_lock);
>  	kvm->arch.radix = 1;
> @@ -6185,6 +6189,7 @@ static struct kvmppc_ops kvm_ops_hv = {
>  	.unmap_gfn_range = kvm_unmap_gfn_range_hv,
>  	.age_gfn = kvm_age_gfn_hv,
>  	.test_age_gfn = kvm_test_age_gfn_hv,
> +	.test_clear_young = kvm_test_clear_young_hv,
>  	.set_spte_gfn = kvm_set_spte_gfn_hv,
>  	.free_memslot = kvmppc_core_free_memslot_hv,
>  	.init_vm =  kvmppc_core_init_vm_hv,

Thanks for looking at the powerpc conversion!

Thanks,
Nick

  reply	other threads:[~2023-06-20  7:49 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-26 23:44 [PATCH mm-unstable v2 00/10] mm/kvm: locklessly clear the accessed bit Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 01/10] mm/kvm: add mmu_notifier_ops->test_clear_young() Yu Zhao
2023-06-06  8:34   ` Tzung-Bi Shih
2023-06-09  1:00     ` Yu Zhao
     [not found]   ` <ZHedMX470b7EMwbe@ziepe.ca>
2023-06-09  9:04     ` Paolo Bonzini
2023-06-15 17:42   ` Sean Christopherson
2023-06-20  7:30   ` Nicholas Piggin
2023-05-26 23:44 ` [PATCH mm-unstable v2 02/10] mm/kvm: use mmu_notifier_ops->test_clear_young() Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 03/10] kvm/arm64: export stage2_try_set_pte() and macros Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 04/10] kvm/arm64: make stage2 page tables RCU safe Yu Zhao
2023-05-27 18:08   ` Oliver Upton
2023-05-27 20:13     ` Yu Zhao
2023-05-30 19:37       ` Oliver Upton
2023-05-30 20:06         ` Yu Zhao
     [not found]           ` <ZHef0VsZvZ1Vnz0u@linux.dev>
2023-05-31 23:10             ` Yu Zhao
2023-05-31 23:22               ` Oliver Upton
2023-05-31 23:41                 ` Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 05/10] kvm/arm64: add kvm_arch_test_clear_young() Yu Zhao
2023-05-26 23:44 ` [PATCH mm-unstable v2 06/10] kvm/powerpc: make radix page tables RCU safe Yu Zhao
2023-06-20  6:32   ` Nicholas Piggin
2023-06-20  8:00     ` Yu Zhao
2023-06-20 10:49       ` Nicholas Piggin
2023-05-26 23:44 ` [PATCH mm-unstable v2 07/10] kvm/powerpc: add kvm_arch_test_clear_young() Yu Zhao
2023-06-20  7:47   ` Nicholas Piggin [this message]
2023-06-21  0:38     ` Yu Zhao
2023-06-21  2:51       ` Nicholas Piggin
2023-05-26 23:44 ` [PATCH mm-unstable v2 08/10] kvm/x86: move tdp_mmu_enabled and shadow_accessed_mask Yu Zhao
2023-06-15 16:59   ` Sean Christopherson
2023-05-26 23:44 ` [PATCH mm-unstable v2 09/10] kvm/x86: add kvm_arch_test_clear_young() Yu Zhao
2023-06-09  9:06   ` Paolo Bonzini
2023-06-15 18:26   ` Sean Christopherson
2023-05-26 23:44 ` [PATCH mm-unstable v2 10/10] mm: multi-gen LRU: use mmu_notifier_test_clear_young() Yu Zhao
2023-06-09  0:59 ` kvm/arm64: Spark benchmark Yu Zhao
2023-06-09 13:04   ` Marc Zyngier
2023-06-18 20:11     ` Yu Zhao
2023-06-09  0:59 ` kvm/powerpc: memcached benchmark Yu Zhao
2023-06-09  0:59 ` kvm/x86: multichase benchmark Yu Zhao
2023-06-18 19:19   ` Yu Zhao
2023-06-09  9:07 ` [PATCH mm-unstable v2 00/10] mm/kvm: locklessly clear the accessed bit Paolo Bonzini
2023-06-20  2:19   ` Yu Zhao

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=CTHB6A4EL3IH.3UJFAJ4LV85X6@wheely \
    --to=npiggin@gmail.com \
    --cc=Jason@zx2c4.com \
    --cc=akpm@linux-foundation.org \
    --cc=anup@brainfault.org \
    --cc=apopple@nvidia.com \
    --cc=bgardon@google.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=chao.p.peng@linux.intel.com \
    --cc=christophe.leroy@csgroup.eu \
    --cc=corbet@lwn.net \
    --cc=cuigaosheng1@huawei.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=farosas@linux.ibm.com \
    --cc=gshan@redhat.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jgg@ziepe.ca \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@google.com \
    --cc=linux-mm@kvack.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maz@kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=michael@michaellarabel.com \
    --cc=mingo@redhat.com \
    --cc=mpe@ellerman.id.au \
    --cc=oliver.upton@linux.dev \
    --cc=paulus@ozlabs.org \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=seanjc@google.com \
    --cc=suzuki.poulose@arm.com \
    --cc=tglx@linutronix.de \
    --cc=thuth@redhat.com \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=yuzenghui@huawei.com \
    --cc=yuzhao@google.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).