From: Avi Kivity <avi@qumranet.com> To: Joerg Roedel <joerg.roedel@amd.com> Cc: kvm-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org Subject: Re: [kvm-devel] [PATCH 8/8] SVM: add support for Nested Paging Date: Sun, 27 Jan 2008 10:52:30 +0200 [thread overview] Message-ID: <479C464E.2060009@qumranet.com> (raw) In-Reply-To: <1201294393-22613-9-git-send-email-joerg.roedel@amd.com> Joerg Roedel wrote: > This patch contains the SVM architecture dependent changes for KVM to enable > support for the Nested Paging feature of AMD Barcelona and Phenom processors. > > +#ifdef CONFIG_X86_64 > +static bool npt_enabled = true; > +#else > static bool npt_enabled = false; > +#endif > I think that i386 + pae can also support npt, with no changes, no? So we should check CONFIG_X86_PAE, not X86_64. > + > + if (npt_enabled) { > + /* Setup VMCB for Nested Paging */ > + control->nested_ctl = 1; > + control->intercept_exceptions &= ~(1 << PF_VECTOR); > + control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK| > + INTERCEPT_CR3_MASK| > + INTERCEPT_CR4_MASK); > + control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| > + INTERCEPT_CR3_MASK| > + INTERCEPT_CR4_MASK); > What happens to lazy fpu if we don't trap cr0 changes? Perhaps it's worth disabling lazy fpu with npt. > static int svm_vcpu_reset(struct kvm_vcpu *vcpu) > @@ -789,6 +812,15 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > { > struct vcpu_svm *svm = to_svm(vcpu); > > + if (npt_enabled) { > + /* > + * re-enable caching here because the QEMU bios > + * does not do it - this results in some delay at > + * reboot > + */ > + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); > + goto set; > + } > #ifdef CONFIG_X86_64 > if (vcpu->arch.shadow_efer & EFER_LME) { > if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { > @@ -812,13 +844,16 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > cr0 &= ~(X86_CR0_CD | X86_CR0_NW); > if (!vcpu->fpu_active) > cr0 |= X86_CR0_TS; > +set: > svm->vmcb->save.cr0 = cr0; > } > You could move 'cr0 &= ~(X86_CR0_CD | X86_CR0_NW);' from three lines above the 'set' label downwards, and avoid it in the if () above. > static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) > { > struct vcpu_svm *svm = to_svm(vcpu); > u32 exit_code = svm->vmcb->control.exit_code; > > + if (npt_enabled) { > + int mmu_reload = 0; > blank line > + if (((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) > + || ((vcpu->arch.cr4 ^ svm->vmcb->save.cr4) & > + (X86_CR4_PGE|X86_CR4_PAE))) > + mmu_reload = 1; > + vcpu->arch.cr0 = svm->vmcb->save.cr0; > + vcpu->arch.cr4 = svm->vmcb->save.cr4; > + vcpu->arch.cr3 = svm->vmcb->save.cr3; > + if (mmu_reload) { > + kvm_mmu_reset_context(vcpu); > + kvm_mmu_load(vcpu); > + } > + if (is_pae(vcpu) && !is_long_mode(vcpu)) > + load_pdptrs(vcpu, vcpu->arch.cr3); > load_pdptrs() may fail; you need to check that. -- error compiling committee.c: too many arguments to function
WARNING: multiple messages have this Message-ID (diff)
From: Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org> To: Joerg Roedel <joerg.roedel-5C7GfCeVMHo@public.gmane.org> Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Subject: Re: [PATCH 8/8] SVM: add support for Nested Paging Date: Sun, 27 Jan 2008 10:52:30 +0200 [thread overview] Message-ID: <479C464E.2060009@qumranet.com> (raw) In-Reply-To: <1201294393-22613-9-git-send-email-joerg.roedel-5C7GfCeVMHo@public.gmane.org> Joerg Roedel wrote: > This patch contains the SVM architecture dependent changes for KVM to enable > support for the Nested Paging feature of AMD Barcelona and Phenom processors. > > +#ifdef CONFIG_X86_64 > +static bool npt_enabled = true; > +#else > static bool npt_enabled = false; > +#endif > I think that i386 + pae can also support npt, with no changes, no? So we should check CONFIG_X86_PAE, not X86_64. > + > + if (npt_enabled) { > + /* Setup VMCB for Nested Paging */ > + control->nested_ctl = 1; > + control->intercept_exceptions &= ~(1 << PF_VECTOR); > + control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK| > + INTERCEPT_CR3_MASK| > + INTERCEPT_CR4_MASK); > + control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| > + INTERCEPT_CR3_MASK| > + INTERCEPT_CR4_MASK); > What happens to lazy fpu if we don't trap cr0 changes? Perhaps it's worth disabling lazy fpu with npt. > static int svm_vcpu_reset(struct kvm_vcpu *vcpu) > @@ -789,6 +812,15 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > { > struct vcpu_svm *svm = to_svm(vcpu); > > + if (npt_enabled) { > + /* > + * re-enable caching here because the QEMU bios > + * does not do it - this results in some delay at > + * reboot > + */ > + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); > + goto set; > + } > #ifdef CONFIG_X86_64 > if (vcpu->arch.shadow_efer & EFER_LME) { > if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { > @@ -812,13 +844,16 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) > cr0 &= ~(X86_CR0_CD | X86_CR0_NW); > if (!vcpu->fpu_active) > cr0 |= X86_CR0_TS; > +set: > svm->vmcb->save.cr0 = cr0; > } > You could move 'cr0 &= ~(X86_CR0_CD | X86_CR0_NW);' from three lines above the 'set' label downwards, and avoid it in the if () above. > static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) > { > struct vcpu_svm *svm = to_svm(vcpu); > u32 exit_code = svm->vmcb->control.exit_code; > > + if (npt_enabled) { > + int mmu_reload = 0; > blank line > + if (((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) > + || ((vcpu->arch.cr4 ^ svm->vmcb->save.cr4) & > + (X86_CR4_PGE|X86_CR4_PAE))) > + mmu_reload = 1; > + vcpu->arch.cr0 = svm->vmcb->save.cr0; > + vcpu->arch.cr4 = svm->vmcb->save.cr4; > + vcpu->arch.cr3 = svm->vmcb->save.cr3; > + if (mmu_reload) { > + kvm_mmu_reset_context(vcpu); > + kvm_mmu_load(vcpu); > + } > + if (is_pae(vcpu) && !is_long_mode(vcpu)) > + load_pdptrs(vcpu, vcpu->arch.cr3); > load_pdptrs() may fail; you need to check that. -- error compiling committee.c: too many arguments to function ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
next prev parent reply other threads:[~2008-01-27 8:52 UTC|newest] Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top 2008-01-25 20:53 [PATCH][RFC] SVM: Add Support for Nested Paging in AMD Fam16 CPUs Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 20:53 ` [PATCH 1/8] SVM: move feature detection to hardware setup code Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 20:53 ` [PATCH 2/8] SVM: add detection of Nested Paging feature Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 20:53 ` [PATCH 3/8] SVM: add module parameter to disable Nested Paging Joerg Roedel 2008-01-25 21:35 ` [kvm-devel] " Anthony Liguori 2008-01-25 21:35 ` Anthony Liguori 2008-01-25 22:10 ` [kvm-devel] " Joerg Roedel 2008-01-25 22:10 ` Joerg Roedel 2008-01-26 18:38 ` [kvm-devel] " Avi Kivity 2008-01-26 18:38 ` Avi Kivity 2008-01-26 1:47 ` [kvm-devel] [PATCH 3/8] SVM: add module parameter to disable NestedPaging Nakajima, Jun 2008-01-26 1:47 ` Nakajima, Jun 2008-01-26 7:25 ` [kvm-devel] " Joerg Roedel 2008-01-26 7:25 ` Joerg Roedel 2008-01-26 9:49 ` [kvm-devel] " Alexey Eremenko 2008-01-26 9:49 ` Alexey Eremenko 2008-01-26 10:06 ` [kvm-devel] " Joerg Roedel 2008-01-26 10:06 ` Joerg Roedel 2008-01-26 16:36 ` [kvm-devel] " Anthony Liguori 2008-01-26 16:36 ` Anthony Liguori 2008-01-26 18:23 ` [kvm-devel] " Avi Kivity 2008-01-25 20:53 ` [PATCH 4/8] X86: export information about NPT to generic x86 code Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 21:37 ` [kvm-devel] " Anthony Liguori 2008-01-25 21:37 ` Anthony Liguori 2008-01-25 21:40 ` [kvm-devel] " Anthony Liguori 2008-01-25 21:40 ` Anthony Liguori 2008-01-27 8:40 ` [kvm-devel] " Avi Kivity 2008-01-27 8:40 ` Avi Kivity 2008-01-25 20:53 ` [PATCH 5/8] MMU: make the __nonpaging_map function generic Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 20:53 ` [PATCH 6/8] X86: export the load_pdptrs() function to modules Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 20:53 ` [PATCH 7/8] MMU: add HAP support to the KVM MMU Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-25 20:53 ` [PATCH 8/8] SVM: add support for Nested Paging Joerg Roedel 2008-01-25 20:53 ` Joerg Roedel 2008-01-27 8:52 ` Avi Kivity [this message] 2008-01-27 8:52 ` Avi Kivity 2008-01-27 9:41 ` [kvm-devel] " Joerg Roedel 2008-01-27 9:41 ` Joerg Roedel 2008-01-27 9:51 ` [kvm-devel] " Avi Kivity 2008-01-27 9:51 ` Avi Kivity 2008-01-27 10:05 ` [kvm-devel] " Joerg Roedel 2008-01-27 10:05 ` Joerg Roedel 2008-01-27 10:24 ` [kvm-devel] " Avi Kivity 2008-01-27 10:24 ` Avi Kivity 2008-01-25 21:32 ` [kvm-devel] [PATCH][RFC] SVM: Add Support for Nested Paging in AMD Fam16 CPUs Anthony Liguori 2008-01-25 21:32 ` Anthony Liguori 2008-01-25 22:47 ` [kvm-devel] " Joerg Roedel 2008-01-25 22:47 ` Joerg Roedel 2008-01-26 1:57 ` [kvm-devel] " Nakajima, Jun 2008-01-26 1:57 ` Nakajima, Jun 2008-01-27 8:57 ` [kvm-devel] " Avi Kivity 2008-01-27 8:57 ` Avi Kivity 2008-01-27 9:51 ` [kvm-devel] " Joerg Roedel 2008-01-27 9:51 ` Joerg Roedel 2008-01-28 3:20 ` [kvm-devel] " Jeremy Fitzhardinge 2008-01-28 3:20 ` Jeremy Fitzhardinge 2008-01-28 11:08 ` [kvm-devel] " Avi Kivity 2008-01-28 11:08 ` Avi Kivity 2008-02-07 12:09 ` [kvm-devel] " Joerg Roedel 2008-02-07 12:09 ` Joerg Roedel 2008-02-10 10:35 ` [kvm-devel] " Avi Kivity 2008-02-10 10:35 ` Avi Kivity
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=479C464E.2060009@qumranet.com \ --to=avi@qumranet.com \ --cc=joerg.roedel@amd.com \ --cc=kvm-devel@lists.sourceforge.net \ --cc=linux-kernel@vger.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.