[v7,4/8] KVM: x86/mmu: Migrate to __kvm_follow_pfn

Message ID	20230704075054.3344915-5-stevensd@google.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <kvm-owner@vger.kernel.org> From: David Stevens <stevensd@chromium.org> To: Sean Christopherson <seanjc@google.com> Cc: Marc Zyngier <maz@kernel.org>, Michael Ellerman <mpe@ellerman.id.au>, Peter Xu <peterx@redhat.com>, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm@vger.kernel.org, David Stevens <stevensd@chromium.org> Subject: [PATCH v7 4/8] KVM: x86/mmu: Migrate to __kvm_follow_pfn Date: Tue, 4 Jul 2023 16:50:49 +0900 Message-ID: <20230704075054.3344915-5-stevensd@google.com> In-Reply-To: <20230704075054.3344915-1-stevensd@google.com> References: <20230704075054.3344915-1-stevensd@google.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk
Series	KVM: allow mapping non-refcounted pages \| expand [v7,0/8] KVM: allow mapping non-refcounted pages [v7,1/8] KVM: Assert that a page's refcount is elevated when marking accessed/dirty [v7,2/8] KVM: Introduce __kvm_follow_pfn function [v7,3/8] KVM: Make __kvm_follow_pfn not imply FOLL_GET [v7,4/8] KVM: x86/mmu: Migrate to __kvm_follow_pfn [v7,5/8] KVM: x86/mmu: Don't pass FOLL_GET to __kvm_follow_pfn [v7,6/8] KVM: arm64: Migrate to __kvm_follow_pfn [v7,7/8] KVM: PPC: Migrate to __kvm_follow_pfn [v7,8/8] KVM: remove __gfn_to_pfn_memslot

Message ID

20230704075054.3344915-5-stevensd@google.com (mailing list archive)

State

New, archived

Headers

From: David Stevens <stevensd@chromium.org>
To: Sean Christopherson <seanjc@google.com>
Cc: Marc Zyngier <maz@kernel.org>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Peter Xu <peterx@redhat.com>,
        linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev,
        linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
        kvm@vger.kernel.org, David Stevens <stevensd@chromium.org>
Subject: [PATCH v7 4/8] KVM: x86/mmu: Migrate to __kvm_follow_pfn
Date: Tue,  4 Jul 2023 16:50:49 +0900
Message-ID: <20230704075054.3344915-5-stevensd@google.com>
In-Reply-To: <20230704075054.3344915-1-stevensd@google.com>
References: <20230704075054.3344915-1-stevensd@google.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Series

KVM: allow mapping non-refcounted pages | expand

Commit Message

David Stevens July 4, 2023, 7:50 a.m. UTC

From: David Stevens <stevensd@chromium.org>

Migrate from __gfn_to_pfn_memslot to __kvm_follow_pfn.

Signed-off-by: David Stevens <stevensd@chromium.org>
---
 arch/x86/kvm/mmu/mmu.c | 35 +++++++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 10 deletions(-)

Comments

Yu Zhang July 5, 2023, 8:07 a.m. UTC | #1

On Tue, Jul 04, 2023 at 04:50:49PM +0900, David Stevens wrote:
> From: David Stevens <stevensd@chromium.org>
> 
> Migrate from __gfn_to_pfn_memslot to __kvm_follow_pfn.
> 
> Signed-off-by: David Stevens <stevensd@chromium.org>
> ---
>  arch/x86/kvm/mmu/mmu.c | 35 +++++++++++++++++++++++++----------
>  1 file changed, 25 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index ec169f5c7dce..e44ab512c3a1 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -4296,7 +4296,12 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
>  static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>  {
>  	struct kvm_memory_slot *slot = fault->slot;
> -	bool async;
> +	struct kvm_follow_pfn foll = {
> +		.slot = slot,
> +		.gfn = fault->gfn,
> +		.flags = FOLL_GET | (fault->write ? FOLL_WRITE : 0),
> +		.allow_write_mapping = true,
> +	};
>  
>  	/*
>  	 * Retry the page fault if the gfn hit a memslot that is being deleted
> @@ -4325,12 +4330,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>  			return RET_PF_EMULATE;
>  	}
>  
> -	async = false;
> -	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
> -					  fault->write, &fault->map_writable,
> -					  &fault->hva);
> -	if (!async)
> -		return RET_PF_CONTINUE; /* *pfn has correct page already */
> +	foll.flags |= FOLL_NOWAIT;
> +	fault->pfn = __kvm_follow_pfn(&foll);
> +
> +	if (!is_error_noslot_pfn(fault->pfn))
> +		goto success;
> +
> +	if (fault->pfn != KVM_PFN_ERR_NEEDS_IO)
> +		return RET_PF_CONTINUE;

IIUC, FOLL_NOWAIT is set only when we wanna an async fault. So
KVM_PFN_ERR_NEEDS_IO may not be necessary? 

B.R.
Yu

Isaku Yamahata July 6, 2023, 1:54 a.m. UTC | #2

On Tue, Jul 04, 2023 at 04:50:49PM +0900,
David Stevens <stevensd@chromium.org> wrote:

> From: David Stevens <stevensd@chromium.org>
> 
> Migrate from __gfn_to_pfn_memslot to __kvm_follow_pfn.
> 
> Signed-off-by: David Stevens <stevensd@chromium.org>
> ---
>  arch/x86/kvm/mmu/mmu.c | 35 +++++++++++++++++++++++++----------
>  1 file changed, 25 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index ec169f5c7dce..e44ab512c3a1 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -4296,7 +4296,12 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
>  static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>  {
>  	struct kvm_memory_slot *slot = fault->slot;
> -	bool async;
> +	struct kvm_follow_pfn foll = {
> +		.slot = slot,
> +		.gfn = fault->gfn,
> +		.flags = FOLL_GET | (fault->write ? FOLL_WRITE : 0),
> +		.allow_write_mapping = true,
> +	};
>  
>  	/*
>  	 * Retry the page fault if the gfn hit a memslot that is being deleted
> @@ -4325,12 +4330,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>  			return RET_PF_EMULATE;
>  	}
>  
> -	async = false;
> -	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
> -					  fault->write, &fault->map_writable,
> -					  &fault->hva);
> -	if (!async)
> -		return RET_PF_CONTINUE; /* *pfn has correct page already */
> +	foll.flags |= FOLL_NOWAIT;
> +	fault->pfn = __kvm_follow_pfn(&foll);
> +
> +	if (!is_error_noslot_pfn(fault->pfn))

We have pfn in struct kvm_follow_pfn as output. Can we make __kvm_follow_pfn()
return int instead of kvm_pfn_t?  KVM_PFN_* seems widely used, though.


> +		goto success;
> +
> +	if (fault->pfn != KVM_PFN_ERR_NEEDS_IO)
> +		return RET_PF_CONTINUE;
>  
>  	if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) {
>  		trace_kvm_try_async_get_page(fault->addr, fault->gfn);
> @@ -4348,9 +4355,17 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>  	 * to wait for IO.  Note, gup always bails if it is unable to quickly
>  	 * get a page and a fatal signal, i.e. SIGKILL, is pending.
>  	 */
> -	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
> -					  fault->write, &fault->map_writable,
> -					  &fault->hva);
> +	foll.flags |= FOLL_INTERRUPTIBLE;
> +	foll.flags &= ~FOLL_NOWAIT;
> +	fault->pfn = __kvm_follow_pfn(&foll);
> +
> +	if (!is_error_noslot_pfn(fault->pfn))
> +		goto success;
> +
> +	return RET_PF_CONTINUE;
> +success:
> +	fault->hva = foll.hva;
> +	fault->map_writable = foll.writable;
>  	return RET_PF_CONTINUE;
>  }
>  
> -- 
> 2.41.0.255.g8b1d071c50-goog
>

Sean Christopherson Aug. 4, 2023, 10:30 p.m. UTC | #3

On Wed, Jul 05, 2023, Yu Zhang wrote:
> On Tue, Jul 04, 2023 at 04:50:49PM +0900, David Stevens wrote:
> > From: David Stevens <stevensd@chromium.org>
> > 
> > Migrate from __gfn_to_pfn_memslot to __kvm_follow_pfn.

Please turn up your changelog verbosity from ~2 to ~8.  E.g. explain the transition
from async => FOLL_NOWAIT+KVM_PFN_ERR_NEEDS_IO, there's no reason to force readers
to suss that out on their own.

> > Signed-off-by: David Stevens <stevensd@chromium.org>
> > ---
> >  arch/x86/kvm/mmu/mmu.c | 35 +++++++++++++++++++++++++----------
> >  1 file changed, 25 insertions(+), 10 deletions(-)
> > 
> > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > index ec169f5c7dce..e44ab512c3a1 100644
> > --- a/arch/x86/kvm/mmu/mmu.c
> > +++ b/arch/x86/kvm/mmu/mmu.c
> > @@ -4296,7 +4296,12 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> >  static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> >  {
> >  	struct kvm_memory_slot *slot = fault->slot;
> > -	bool async;
> > +	struct kvm_follow_pfn foll = {
> > +		.slot = slot,
> > +		.gfn = fault->gfn,
> > +		.flags = FOLL_GET | (fault->write ? FOLL_WRITE : 0),
> > +		.allow_write_mapping = true,
> > +	};
> >  
> >  	/*
> >  	 * Retry the page fault if the gfn hit a memslot that is being deleted
> > @@ -4325,12 +4330,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> >  			return RET_PF_EMULATE;
> >  	}
> >  
> > -	async = false;
> > -	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
> > -					  fault->write, &fault->map_writable,
> > -					  &fault->hva);
> > -	if (!async)
> > -		return RET_PF_CONTINUE; /* *pfn has correct page already */
> > +	foll.flags |= FOLL_NOWAIT;
> > +	fault->pfn = __kvm_follow_pfn(&foll);
> > +
> > +	if (!is_error_noslot_pfn(fault->pfn))
> > +		goto success;
> > +
> > +	if (fault->pfn != KVM_PFN_ERR_NEEDS_IO)
> > +		return RET_PF_CONTINUE;
> 
> IIUC, FOLL_NOWAIT is set only when we wanna an async fault. So
> KVM_PFN_ERR_NEEDS_IO may not be necessary? 

But FOLL_NOWAIT is set above.  This logic is essentially saying "bail immediately
if __gfn_to_pfn_memslot() returned a fatal error".

A commented would definitely be helpful though.  How about?

	/*
	 * If __kvm_follow_pfn() failed because I/O is needed to fault in the
	 * page, then either set up an asynchronous #PF to do the I/O, or if
	 * doing an async #PF isn't possible, retry __kvm_follow_pfn() with
	  I/O allowed. All other failures are fatal, i.e. retrying won't help.
	 */
	if (fault->pfn != KVM_PFN_ERR_NEEDS_IO)
		return RET_PF_CONTINUE;

David Stevens Aug. 24, 2023, 8:03 a.m. UTC | #4

On Thu, Jul 6, 2023 at 10:54 AM Isaku Yamahata <isaku.yamahata@gmail.com> wrote:
>
> On Tue, Jul 04, 2023 at 04:50:49PM +0900,
> David Stevens <stevensd@chromium.org> wrote:
>
> > From: David Stevens <stevensd@chromium.org>
> >
> > Migrate from __gfn_to_pfn_memslot to __kvm_follow_pfn.
> >
> > Signed-off-by: David Stevens <stevensd@chromium.org>
> > ---
> >  arch/x86/kvm/mmu/mmu.c | 35 +++++++++++++++++++++++++----------
> >  1 file changed, 25 insertions(+), 10 deletions(-)
> >
> > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > index ec169f5c7dce..e44ab512c3a1 100644
> > --- a/arch/x86/kvm/mmu/mmu.c
> > +++ b/arch/x86/kvm/mmu/mmu.c
> > @@ -4296,7 +4296,12 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> >  static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> >  {
> >       struct kvm_memory_slot *slot = fault->slot;
> > -     bool async;
> > +     struct kvm_follow_pfn foll = {
> > +             .slot = slot,
> > +             .gfn = fault->gfn,
> > +             .flags = FOLL_GET | (fault->write ? FOLL_WRITE : 0),
> > +             .allow_write_mapping = true,
> > +     };
> >
> >       /*
> >        * Retry the page fault if the gfn hit a memslot that is being deleted
> > @@ -4325,12 +4330,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> >                       return RET_PF_EMULATE;
> >       }
> >
> > -     async = false;
> > -     fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
> > -                                       fault->write, &fault->map_writable,
> > -                                       &fault->hva);
> > -     if (!async)
> > -             return RET_PF_CONTINUE; /* *pfn has correct page already */
> > +     foll.flags |= FOLL_NOWAIT;
> > +     fault->pfn = __kvm_follow_pfn(&foll);
> > +
> > +     if (!is_error_noslot_pfn(fault->pfn))
>
> We have pfn in struct kvm_follow_pfn as output. Can we make __kvm_follow_pfn()
> return int instead of kvm_pfn_t?  KVM_PFN_* seems widely used, though.

Switching __kvm_follow_pfn to return an int isn't difficult, but doing
is cleanly would require reworking the kvm_pfn_t/KVM_PFN_ERR_* api,
which as you said is quite widely used. That's a bit larger scope than
I want to do in this patch series.

-David

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..e44ab512c3a1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4296,7 +4296,12 @@  void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
-	bool async;
+	struct kvm_follow_pfn foll = {
+		.slot = slot,
+		.gfn = fault->gfn,
+		.flags = FOLL_GET | (fault->write ? FOLL_WRITE : 0),
+		.allow_write_mapping = true,
+	};
 
 	/*
 	 * Retry the page fault if the gfn hit a memslot that is being deleted
@@ -4325,12 +4330,14 @@  static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			return RET_PF_EMULATE;
 	}
 
-	async = false;
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
-	if (!async)
-		return RET_PF_CONTINUE; /* *pfn has correct page already */
+	foll.flags |= FOLL_NOWAIT;
+	fault->pfn = __kvm_follow_pfn(&foll);
+
+	if (!is_error_noslot_pfn(fault->pfn))
+		goto success;
+
+	if (fault->pfn != KVM_PFN_ERR_NEEDS_IO)
+		return RET_PF_CONTINUE;
 
 	if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(fault->addr, fault->gfn);
@@ -4348,9 +4355,17 @@  static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * to wait for IO.  Note, gup always bails if it is unable to quickly
 	 * get a page and a fatal signal, i.e. SIGKILL, is pending.
 	 */
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
+	foll.flags |= FOLL_INTERRUPTIBLE;
+	foll.flags &= ~FOLL_NOWAIT;
+	fault->pfn = __kvm_follow_pfn(&foll);
+
+	if (!is_error_noslot_pfn(fault->pfn))
+		goto success;
+
+	return RET_PF_CONTINUE;
+success:
+	fault->hva = foll.hva;
+	fault->map_writable = foll.writable;
 	return RET_PF_CONTINUE;
 }

[v7,4/8] KVM: x86/mmu: Migrate to __kvm_follow_pfn

Commit Message

Comments

Patch