From: David Matlack <dmatlack@google.com> To: Sean Christopherson <seanjc@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com>, Marc Zyngier <maz@kernel.org>, Huacai Chen <chenhuacai@kernel.org>, Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>, Anup Patel <anup@brainfault.org>, Paul Walmsley <paul.walmsley@sifive.com>, Palmer Dabbelt <palmer@dabbelt.com>, Albert Ou <aou@eecs.berkeley.edu>, Andrew Jones <drjones@redhat.com>, Ben Gardon <bgardon@google.com>, Peter Xu <peterx@redhat.com>, maciej.szmigiero@oracle.com, "moderated list:KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)" <kvmarm@lists.cs.columbia.edu>, "open list:KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)" <linux-mips@vger.kernel.org>, "open list:KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)" <kvm@vger.kernel.org>, "open list:KERNEL VIRTUAL MACHINE FOR RISC-V (KVM/riscv)" <kvm-riscv@lists.infradead.org>, Peter Feiner <pfeiner@google.com>, Lai Jiangshan <jiangshanlai@gmail.com> Subject: Re: [PATCH v5 20/21] KVM: Allow for different capacities in kvm_mmu_memory_cache structs Date: Mon, 16 May 2022 09:39:07 -0700 [thread overview] Message-ID: <CALzav=d-O5KWDC356cdpoJAUvKSSNOMtn_n7G6Yc342-VQFJNQ@mail.gmail.com> (raw) In-Reply-To: <YoJkb7oMEz0v1dnp@google.com> On Mon, May 16, 2022 at 7:49 AM Sean Christopherson <seanjc@google.com> wrote: > > On Fri, May 13, 2022, David Matlack wrote: > > diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c > > index 53ae2c0640bc..2f2ef6b60ff4 100644 > > --- a/arch/arm64/kvm/mmu.c > > +++ b/arch/arm64/kvm/mmu.c > > @@ -764,7 +764,10 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, > > { > > phys_addr_t addr; > > int ret = 0; > > - struct kvm_mmu_memory_cache cache = { 0, __GFP_ZERO, NULL, }; > > + struct kvm_mmu_memory_cache cache = { > > + .capacity = KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, > > + .gfp_zero = __GFP_ZERO, > > I dislike requiring all users to specificy the capacity. It largely defeats the > purpose of KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, and bleeds details into code that > really doesn't care all that much about the details. > > Rather than force the capacity to be set before topup, what about adding a custom > capacity topup helper? That allows keeping a default capacity, better documents > the caches that are special, and provides an opportunity to sanity check that the > capacity isn't incorrectly changed by the user. Even simpler: If mc->capacity is 0 in topup, set it to KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE. This is what I had before when I was laying out the storage for objects in a separate array. It was risky then because it was too easy for someone to accidentally corrupt memory (call topup with capacity==0 but without allocating the objects array). Now that topup takes care of allocation automatically, that risk is gone. > > And then I believe this code becomes: > > struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; > > E.g. (completely untested) > > static int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, > int capacity, int min) > { > gfp_t gfp = GFP_KERNEL_ACCOUNT; > void *obj; > > if (mc->nobjs >= min) > return 0; > > if (likely(mc->capacity)) { > if (WARN_ON_ONCE(mc->capacity != capacity || !mc->objects)) > return -EIO; > } else { > mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp); > if (!mc->objects) > return -ENOMEM; > > mc->capacity = capacity; > } > > while (mc->nobjs < mc->capacity) { > obj = mmu_memory_cache_alloc_obj(mc, gfp); > if (!obj) > return mc->nobjs >= min ? 0 : -ENOMEM; > mc->objects[mc->nobjs++] = obj; > } > return 0; > } > > int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) > { > const int capacity = KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE; > > return __kvm_mmu_topup_memory_cache(mc, capacity, min); > } > > int kvm_mmu_topup_custom_memory_cache(struct kvm_mmu_memory_cache *mc, > int capacity) > { > return __kvm_mmu_topup_memory_cache(mc, capacity, capacity); > } >
WARNING: multiple messages have this Message-ID (diff)
From: David Matlack <dmatlack@google.com> To: Sean Christopherson <seanjc@google.com> Cc: Marc Zyngier <maz@kernel.org>, Albert Ou <aou@eecs.berkeley.edu>, "open list:KERNEL VIRTUAL MACHINE FOR MIPS \(KVM/mips\)" <kvm@vger.kernel.org>, Huacai Chen <chenhuacai@kernel.org>, Lai Jiangshan <jiangshanlai@gmail.com>, "open list:KERNEL VIRTUAL MACHINE FOR MIPS \(KVM/mips\)" <linux-mips@vger.kernel.org>, Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>, Palmer Dabbelt <palmer@dabbelt.com>, "open list:KERNEL VIRTUAL MACHINE FOR RISC-V \(KVM/riscv\)" <kvm-riscv@lists.infradead.org>, Paul Walmsley <paul.walmsley@sifive.com>, Ben Gardon <bgardon@google.com>, Paolo Bonzini <pbonzini@redhat.com>, maciej.szmigiero@oracle.com, "moderated list:KERNEL VIRTUAL MACHINE FOR ARM64 \(KVM/arm64\)" <kvmarm@lists.cs.columbia.edu>, Peter Feiner <pfeiner@google.com> Subject: Re: [PATCH v5 20/21] KVM: Allow for different capacities in kvm_mmu_memory_cache structs Date: Mon, 16 May 2022 09:39:07 -0700 [thread overview] Message-ID: <CALzav=d-O5KWDC356cdpoJAUvKSSNOMtn_n7G6Yc342-VQFJNQ@mail.gmail.com> (raw) In-Reply-To: <YoJkb7oMEz0v1dnp@google.com> On Mon, May 16, 2022 at 7:49 AM Sean Christopherson <seanjc@google.com> wrote: > > On Fri, May 13, 2022, David Matlack wrote: > > diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c > > index 53ae2c0640bc..2f2ef6b60ff4 100644 > > --- a/arch/arm64/kvm/mmu.c > > +++ b/arch/arm64/kvm/mmu.c > > @@ -764,7 +764,10 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, > > { > > phys_addr_t addr; > > int ret = 0; > > - struct kvm_mmu_memory_cache cache = { 0, __GFP_ZERO, NULL, }; > > + struct kvm_mmu_memory_cache cache = { > > + .capacity = KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, > > + .gfp_zero = __GFP_ZERO, > > I dislike requiring all users to specificy the capacity. It largely defeats the > purpose of KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, and bleeds details into code that > really doesn't care all that much about the details. > > Rather than force the capacity to be set before topup, what about adding a custom > capacity topup helper? That allows keeping a default capacity, better documents > the caches that are special, and provides an opportunity to sanity check that the > capacity isn't incorrectly changed by the user. Even simpler: If mc->capacity is 0 in topup, set it to KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE. This is what I had before when I was laying out the storage for objects in a separate array. It was risky then because it was too easy for someone to accidentally corrupt memory (call topup with capacity==0 but without allocating the objects array). Now that topup takes care of allocation automatically, that risk is gone. > > And then I believe this code becomes: > > struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; > > E.g. (completely untested) > > static int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, > int capacity, int min) > { > gfp_t gfp = GFP_KERNEL_ACCOUNT; > void *obj; > > if (mc->nobjs >= min) > return 0; > > if (likely(mc->capacity)) { > if (WARN_ON_ONCE(mc->capacity != capacity || !mc->objects)) > return -EIO; > } else { > mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp); > if (!mc->objects) > return -ENOMEM; > > mc->capacity = capacity; > } > > while (mc->nobjs < mc->capacity) { > obj = mmu_memory_cache_alloc_obj(mc, gfp); > if (!obj) > return mc->nobjs >= min ? 0 : -ENOMEM; > mc->objects[mc->nobjs++] = obj; > } > return 0; > } > > int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) > { > const int capacity = KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE; > > return __kvm_mmu_topup_memory_cache(mc, capacity, min); > } > > int kvm_mmu_topup_custom_memory_cache(struct kvm_mmu_memory_cache *mc, > int capacity) > { > return __kvm_mmu_topup_memory_cache(mc, capacity, capacity); > } > _______________________________________________ kvmarm mailing list kvmarm@lists.cs.columbia.edu https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
next prev parent reply other threads:[~2022-05-16 16:39 UTC|newest] Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-05-13 20:27 [PATCH v5 00/21] KVM: Extend Eager Page Splitting to the shadow MMU David Matlack 2022-05-13 20:27 ` David Matlack 2022-05-13 20:27 ` [PATCH v5 01/21] KVM: x86/mmu: Optimize MMU page cache lookup for all direct SPs David Matlack 2022-05-13 20:27 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 02/21] KVM: x86/mmu: Use a bool for direct David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 03/21] KVM: x86/mmu: Derive shadow MMU page role from parent David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-16 6:54 ` Lai Jiangshan 2022-05-16 6:54 ` Lai Jiangshan 2022-05-16 21:38 ` David Matlack 2022-05-16 21:38 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 04/21] KVM: x86/mmu: Always pass 0 for @quadrant when gptes are 8 bytes David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 05/21] KVM: x86/mmu: Decompose kvm_mmu_get_page() into separate functions David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 06/21] KVM: x86/mmu: Consolidate shadow page allocation and initialization David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 07/21] KVM: x86/mmu: Rename shadow MMU functions that deal with shadow pages David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 08/21] KVM: x86/mmu: Move guest PT write-protection to account_shadowed() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 09/21] KVM: x86/mmu: Pass memory caches to allocate SPs separately David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 10/21] KVM: x86/mmu: Replace vcpu with kvm in kvm_mmu_alloc_shadow_page() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 11/21] KVM: x86/mmu: Pass kvm pointer separately from vcpu to kvm_mmu_find_shadow_page() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 12/21] KVM: x86/mmu: Allow NULL @vcpu in kvm_mmu_find_shadow_page() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 13/21] KVM: x86/mmu: Pass const memslot to rmap_add() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 14/21] KVM: x86/mmu: Decouple rmap_add() and link_shadow_page() from kvm_vcpu David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 15/21] KVM: x86/mmu: Update page stats in __rmap_add() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 16/21] KVM: x86/mmu: Cache the access bits of shadowed translations David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 17/21] KVM: x86/mmu: Extend make_huge_page_split_spte() for the shadow MMU David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 18/21] KVM: x86/mmu: Zap collapsible SPTEs in shadow MMU at all possible levels David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 19/21] KVM: x86/mmu: Refactor drop_large_spte() David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-13 20:28 ` [PATCH v5 20/21] KVM: Allow for different capacities in kvm_mmu_memory_cache structs David Matlack 2022-05-13 20:28 ` David Matlack 2022-05-15 11:42 ` Marc Zyngier 2022-05-15 11:42 ` Marc Zyngier 2022-05-16 3:31 ` Anup Patel 2022-05-16 3:31 ` Anup Patel 2022-05-16 23:23 ` David Matlack 2022-05-16 23:23 ` David Matlack 2022-05-16 14:49 ` Sean Christopherson 2022-05-16 14:49 ` Sean Christopherson 2022-05-16 16:39 ` David Matlack [this message] 2022-05-16 16:39 ` David Matlack 2022-05-16 17:53 ` Sean Christopherson 2022-05-16 17:53 ` Sean Christopherson 2022-05-13 20:28 ` [PATCH v5 21/21] KVM: x86/mmu: Extend Eager Page Splitting to nested MMUs David Matlack 2022-05-13 20:28 ` David Matlack
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='CALzav=d-O5KWDC356cdpoJAUvKSSNOMtn_n7G6Yc342-VQFJNQ@mail.gmail.com' \ --to=dmatlack@google.com \ --cc=aleksandar.qemu.devel@gmail.com \ --cc=anup@brainfault.org \ --cc=aou@eecs.berkeley.edu \ --cc=bgardon@google.com \ --cc=chenhuacai@kernel.org \ --cc=drjones@redhat.com \ --cc=jiangshanlai@gmail.com \ --cc=kvm-riscv@lists.infradead.org \ --cc=kvm@vger.kernel.org \ --cc=kvmarm@lists.cs.columbia.edu \ --cc=linux-mips@vger.kernel.org \ --cc=maciej.szmigiero@oracle.com \ --cc=maz@kernel.org \ --cc=palmer@dabbelt.com \ --cc=paul.walmsley@sifive.com \ --cc=pbonzini@redhat.com \ --cc=peterx@redhat.com \ --cc=pfeiner@google.com \ --cc=seanjc@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: 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.