| 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: Tue, 29 Sep 2020 23:15:33 -0700
From: Sean Christopherson <sean.j.christopherson@...el.com>
To: Ben Gardon <bgardon@...gle.com>
Cc: linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
Cannon Matthews <cannonmatthews@...gle.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Peter Xu <peterx@...hat.com>, Peter Shier <pshier@...gle.com>,
Peter Feiner <pfeiner@...gle.com>,
Junaid Shahid <junaids@...gle.com>,
Jim Mattson <jmattson@...gle.com>,
Yulei Zhang <yulei.kernel@...il.com>,
Wanpeng Li <kernellwp@...il.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Xiao Guangrong <xiaoguangrong.eric@...il.com>
Subject: Re: [PATCH 07/22] kvm: mmu: Support zapping SPTEs in the TDP MMU
On Fri, Sep 25, 2020 at 02:22:47PM -0700, Ben Gardon wrote:
> Add functions to zap SPTEs to the TDP MMU. These are needed to tear down
> TDP MMU roots properly and implement other MMU functions which require
> tearing down mappings. Future patches will add functions to populate the
> page tables, but as for this patch there will not be any work for these
> functions to do.
>
> Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
> machine. This series introduced no new failures.
>
> This series can be viewed in Gerrit at:
> https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538
>
> Signed-off-by: Ben Gardon <bgardon@...gle.com>
> ---
> arch/x86/kvm/mmu/mmu.c | 15 +++++
> arch/x86/kvm/mmu/tdp_iter.c | 17 ++++++
> arch/x86/kvm/mmu/tdp_iter.h | 1 +
> arch/x86/kvm/mmu/tdp_mmu.c | 106 ++++++++++++++++++++++++++++++++++++
> arch/x86/kvm/mmu/tdp_mmu.h | 2 +
> 5 files changed, 141 insertions(+)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index f09081f9137b0..7a17cca19b0c1 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -5852,6 +5852,10 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
> kvm_reload_remote_mmus(kvm);
>
> kvm_zap_obsolete_pages(kvm);
> +
> + if (kvm->arch.tdp_mmu_enabled)
> + kvm_tdp_mmu_zap_all(kvm);
Haven't looked into how this works; is kvm_tdp_mmu_zap_all() additive to
what is done by the legacy zapping, or is it a replacement?
> +
> spin_unlock(&kvm->mmu_lock);
> }
> @@ -57,8 +58,13 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
> return root->tdp_mmu_page;
> }
>
> +static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
> + gfn_t start, gfn_t end);
> +
> static void free_tdp_mmu_root(struct kvm *kvm, struct kvm_mmu_page *root)
> {
> + gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
BIT_ULL(...)
> +
> lockdep_assert_held(&kvm->mmu_lock);
>
> WARN_ON(root->root_count);
> @@ -66,6 +72,8 @@ static void free_tdp_mmu_root(struct kvm *kvm, struct kvm_mmu_page *root)
>
> list_del(&root->link);
>
> + zap_gfn_range(kvm, root, 0, max_gfn);
> +
> free_page((unsigned long)root->spt);
> kmem_cache_free(mmu_page_header_cache, root);
> }
> @@ -193,6 +201,11 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
> static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
> u64 old_spte, u64 new_spte, int level);
>
> +static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
> +{
> + return sp->role.smm ? 1 : 0;
> +}
> +
> /**
> * handle_changed_spte - handle bookkeeping associated with an SPTE change
> * @kvm: kvm instance
> @@ -294,3 +307,96 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
> free_page((unsigned long)pt);
> }
> }
> +
> +#define for_each_tdp_pte_root(_iter, _root, _start, _end) \
> + for_each_tdp_pte(_iter, _root->spt, _root->role.level, _start, _end)
> +
> +/*
> + * If the MMU lock is contended or this thread needs to yield, flushes
> + * the TLBs, releases, the MMU lock, yields, reacquires the MMU lock,
> + * restarts the tdp_iter's walk from the root, and returns true.
> + * If no yield is needed, returns false.
> + */
> +static bool tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
> +{
> + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
> + kvm_flush_remote_tlbs(kvm);
> + cond_resched_lock(&kvm->mmu_lock);
> + tdp_iter_refresh_walk(iter);
> + return true;
> + } else {
> + return false;
> + }
Kernel style is to not bother with an "else" if the "if" returns.
> +}
> +
> +/*
> + * Tears down the mappings for the range of gfns, [start, end), and frees the
> + * non-root pages mapping GFNs strictly within that range. Returns true if
> + * SPTEs have been cleared and a TLB flush is needed before releasing the
> + * MMU lock.
> + */
> +static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
> + gfn_t start, gfn_t end)
> +{
> + struct tdp_iter iter;
> + bool flush_needed = false;
> + int as_id = kvm_mmu_page_as_id(root);
> +
> + for_each_tdp_pte_root(iter, root, start, end) {
> + if (!is_shadow_present_pte(iter.old_spte))
> + continue;
> +
> + /*
> + * If this is a non-last-level SPTE that covers a larger range
> + * than should be zapped, continue, and zap the mappings at a
> + * lower level.
> + */
> + if ((iter.gfn < start ||
> + iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) &&
> + !is_last_spte(iter.old_spte, iter.level))
> + continue;
> +
> + *iter.sptep = 0;
> + handle_changed_spte(kvm, as_id, iter.gfn, iter.old_spte, 0,
> + iter.level);
> +
> + flush_needed = !tdp_mmu_iter_cond_resched(kvm, &iter);
> + }
> + return flush_needed;
> +}
> +
> +/*
> + * Tears down the mappings for the range of gfns, [start, end), and frees the
> + * non-root pages mapping GFNs strictly within that range. Returns true if
> + * SPTEs have been cleared and a TLB flush is needed before releasing the
> + * MMU lock.
> + */
> +bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
> +{
> + struct kvm_mmu_page *root;
> + bool flush = false;
> +
> + for_each_tdp_mmu_root(kvm, root) {
> + /*
> + * Take a reference on the root so that it cannot be freed if
> + * this thread releases the MMU lock and yields in this loop.
> + */
> + get_tdp_mmu_root(kvm, root);
> +
> + flush = zap_gfn_range(kvm, root, start, end) || flush;
> +
> + put_tdp_mmu_root(kvm, root);
> + }
> +
> + return flush;
> +}
> +
> +void kvm_tdp_mmu_zap_all(struct kvm *kvm)
> +{
> + gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
BIT_ULL
> + bool flush;
> +
> + flush = kvm_tdp_mmu_zap_gfn_range(kvm, 0, max_gfn);
> + if (flush)
> + kvm_flush_remote_tlbs(kvm);
> +}
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
> index 9274debffeaa1..cb86f9fe69017 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.h
> +++ b/arch/x86/kvm/mmu/tdp_mmu.h
> @@ -12,4 +12,6 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t root);
> hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
> void kvm_tdp_mmu_put_root_hpa(struct kvm *kvm, hpa_t root_hpa);
>
> +bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
> +void kvm_tdp_mmu_zap_all(struct kvm *kvm);
> #endif /* __KVM_X86_MMU_TDP_MMU_H */
> --
> 2.28.0.709.gb0816b6eb0-goog
>
Powered by blists - more mailing lists