| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 2 Aug 2021 22:41:09 +0000
From: David Matlack <dmatlack@...gle.com>
To: Mingwei Zhang <mizhang@...gle.com>
Cc: Paolo Bonzini <pbonzini@...hat.com>,
Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org, Ben Gardon <bgardon@...gle.com>,
Jing Zhang <jingzhangos@...gle.com>
Subject: Re: [PATCH v3 3/3] KVM: x86/mmu: Add detailed page size stats
On Fri, Jul 30, 2021 at 03:59:39PM -0700, Mingwei Zhang wrote:
> Existing KVM code tracks the number of large pages regardless of their
> sizes. Therefore, when large page of 1GB (or larger) is adopted, the
> information becomes less useful because lpages counts a mix of 1G and 2M
> pages.
>
> So remove the lpages since it is easy for user space to aggregate the info.
> Instead, provide a comprehensive page stats of all sizes from 4K to 512G.
>
> Suggested-by: Ben Gardon <bgardon@...gle.com>
> Reviewed-by: Ben Gardon <bgardon@...gle.com>
> Signed-off-by: Mingwei Zhang <mizhang@...gle.com>
> Cc: Jing Zhang <jingzhangos@...gle.com>
> Cc: David Matlack <dmatlack@...gle.com>
> Cc: Sean Christopherson <seanjc@...gle.com>
> ---
Reviewed-by: David Matlack <dmatlack@...gle.com>
> arch/x86/include/asm/kvm_host.h | 10 +++++++++-
> arch/x86/kvm/mmu.h | 4 ++++
> arch/x86/kvm/mmu/mmu.c | 26 +++++++++++++-------------
> arch/x86/kvm/mmu/tdp_mmu.c | 15 ++-------------
> arch/x86/kvm/x86.c | 7 +++++--
> 5 files changed, 33 insertions(+), 29 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 974cbfb1eefe..eb6edc36b3ed 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1206,9 +1206,17 @@ struct kvm_vm_stat {
> u64 mmu_recycled;
> u64 mmu_cache_miss;
> u64 mmu_unsync;
> - u64 lpages;
> u64 nx_lpage_splits;
> u64 max_mmu_page_hash_collisions;
> + union {
> + struct {
> + atomic64_t pages_4k;
> + atomic64_t pages_2m;
> + atomic64_t pages_1g;
> + atomic64_t pages_512g;
> + };
> + atomic64_t pages[4];
> + };
> };
>
> struct kvm_vcpu_stat {
> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
> index 83e6c6965f1e..2883789fb5fb 100644
> --- a/arch/x86/kvm/mmu.h
> +++ b/arch/x86/kvm/mmu.h
> @@ -240,4 +240,8 @@ static inline bool kvm_memslots_have_rmaps(struct kvm *kvm)
> return smp_load_acquire(&kvm->arch.memslots_have_rmaps);
> }
>
> +static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count)
> +{
> + atomic64_add(count, &kvm->stat.pages[level - 1]);
> +}
> #endif
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 442cc554ebd6..2308537b1807 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -594,10 +594,11 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte)
> * state bits, it is used to clear the last level sptep.
> * Returns non-zero if the PTE was previously valid.
> */
> -static int mmu_spte_clear_track_bits(u64 *sptep)
> +static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
> {
> kvm_pfn_t pfn;
> u64 old_spte = *sptep;
> + int level = sptep_to_sp(sptep)->role.level;
>
> if (!spte_has_volatile_bits(old_spte))
> __update_clear_spte_fast(sptep, 0ull);
> @@ -607,6 +608,8 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
> if (!is_shadow_present_pte(old_spte))
> return 0;
>
> + kvm_update_page_stats(kvm, level, -1);
> +
> pfn = spte_to_pfn(old_spte);
>
> /*
> @@ -984,9 +987,10 @@ static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
> }
> }
>
> -static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep)
> +static void pte_list_remove(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
> + u64 *sptep)
> {
> - mmu_spte_clear_track_bits(sptep);
> + mmu_spte_clear_track_bits(kvm, sptep);
> __pte_list_remove(sptep, rmap_head);
> }
>
> @@ -1119,7 +1123,7 @@ static u64 *rmap_get_next(struct rmap_iterator *iter)
>
> static void drop_spte(struct kvm *kvm, u64 *sptep)
> {
> - if (mmu_spte_clear_track_bits(sptep))
> + if (mmu_spte_clear_track_bits(kvm, sptep))
> rmap_remove(kvm, sptep);
> }
>
> @@ -1129,7 +1133,6 @@ static bool __drop_large_spte(struct kvm *kvm, u64 *sptep)
> if (is_large_pte(*sptep)) {
> WARN_ON(sptep_to_sp(sptep)->role.level == PG_LEVEL_4K);
> drop_spte(kvm, sptep);
> - --kvm->stat.lpages;
> return true;
> }
>
> @@ -1386,7 +1389,7 @@ static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
> while ((sptep = rmap_get_first(rmap_head, &iter))) {
> rmap_printk("spte %p %llx.\n", sptep, *sptep);
>
> - pte_list_remove(rmap_head, sptep);
> + pte_list_remove(kvm, rmap_head, sptep);
> flush = true;
> }
>
> @@ -1421,13 +1424,13 @@ static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
> need_flush = 1;
>
> if (pte_write(pte)) {
> - pte_list_remove(rmap_head, sptep);
> + pte_list_remove(kvm, rmap_head, sptep);
> goto restart;
> } else {
> new_spte = kvm_mmu_changed_pte_notifier_make_spte(
> *sptep, new_pfn);
>
> - mmu_spte_clear_track_bits(sptep);
> + mmu_spte_clear_track_bits(kvm, sptep);
> mmu_spte_set(sptep, new_spte);
> }
> }
> @@ -2232,8 +2235,6 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
> if (is_shadow_present_pte(pte)) {
> if (is_last_spte(pte, sp->role.level)) {
> drop_spte(kvm, spte);
> - if (is_large_pte(pte))
> - --kvm->stat.lpages;
> } else {
> child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
> drop_parent_pte(child, spte);
> @@ -2692,8 +2693,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
> trace_kvm_mmu_set_spte(level, gfn, sptep);
>
> if (!was_rmapped) {
> - if (is_large_pte(*sptep))
> - ++vcpu->kvm->stat.lpages;
> + kvm_update_page_stats(vcpu->kvm, level, 1);
> rmap_count = rmap_add(vcpu, sptep, gfn);
> if (rmap_count > RMAP_RECYCLE_THRESHOLD)
> rmap_recycle(vcpu, sptep, gfn);
> @@ -5669,7 +5669,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
> sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> pfn, PG_LEVEL_NUM)) {
> - pte_list_remove(rmap_head, sptep);
> + pte_list_remove(kvm, rmap_head, sptep);
>
> if (kvm_available_flush_tlb_with_range())
> kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index cba2ab5db2a0..eae404c15364 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -413,7 +413,6 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
> bool was_leaf = was_present && is_last_spte(old_spte, level);
> bool is_leaf = is_present && is_last_spte(new_spte, level);
> bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
> - bool was_large, is_large;
>
> WARN_ON(level > PT64_ROOT_MAX_LEVEL);
> WARN_ON(level < PG_LEVEL_4K);
> @@ -472,18 +471,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
> return;
> }
>
> - /*
> - * Update large page stats if a large page is being zapped, created, or
> - * is replacing an existing shadow page.
> - */
> - was_large = was_leaf && is_large_pte(old_spte);
> - is_large = is_leaf && is_large_pte(new_spte);
> - if (was_large != is_large) {
> - if (was_large)
> - atomic64_sub(1, (atomic64_t *)&kvm->stat.lpages);
> - else
> - atomic64_add(1, (atomic64_t *)&kvm->stat.lpages);
> - }
> + if (is_leaf != was_leaf)
> + kvm_update_page_stats(kvm, level, is_leaf ? 1 : -1);
>
> if (was_leaf && is_dirty_spte(old_spte) &&
> (!is_present || !is_dirty_spte(new_spte) || pfn_changed))
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 8166ad113fb2..e4dfcd5d83ad 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -235,9 +235,12 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
> STATS_DESC_COUNTER(VM, mmu_recycled),
> STATS_DESC_COUNTER(VM, mmu_cache_miss),
> STATS_DESC_ICOUNTER(VM, mmu_unsync),
> - STATS_DESC_ICOUNTER(VM, lpages),
> STATS_DESC_ICOUNTER(VM, nx_lpage_splits),
> - STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions)
> + STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions),
> + STATS_DESC_ICOUNTER(VM, pages_4k),
> + STATS_DESC_ICOUNTER(VM, pages_2m),
> + STATS_DESC_ICOUNTER(VM, pages_1g),
> + STATS_DESC_ICOUNTER(VM, pages_512g)
> };
> static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
> sizeof(struct kvm_vm_stat) / sizeof(u64));
> --
> 2.32.0.554.ge1b32706d8-goog
>
Powered by blists - more mailing lists