| 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, 22 Nov 2021 13:55:34 -0800
From: Ben Gardon <bgardon@...gle.com>
To: Sean Christopherson <seanjc@...gle.com>
Cc: Paolo Bonzini <pbonzini@...hat.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,
Hou Wenlong <houwenlong93@...ux.alibaba.com>
Subject: Re: [PATCH 14/28] KVM: x86/mmu: Add helpers to read/write TDP MMU
SPTEs and document RCU
On Fri, Nov 19, 2021 at 8:51 PM Sean Christopherson <seanjc@...gle.com> wrote:
>
> Add helpers to read and write TDP MMU SPTEs instead of open coding
> rcu_dereference() all over the place, and to provide a convenient
> location to document why KVM doesn't exempt holding mmu_lock for write
> from having to hold RCU (and any future changes to the rules).
>
> No functional change intended.
>
> Signed-off-by: Sean Christopherson <seanjc@...gle.com>
Reviewed-by: Ben Gardon <bgardon@...gle.com>
Modulo a couple nits below.
> ---
> arch/x86/kvm/mmu/tdp_iter.c | 6 +++---
> arch/x86/kvm/mmu/tdp_iter.h | 16 ++++++++++++++++
> arch/x86/kvm/mmu/tdp_mmu.c | 14 +++++++-------
> 3 files changed, 26 insertions(+), 10 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
> index b3ed302c1a35..1f7741c725f6 100644
> --- a/arch/x86/kvm/mmu/tdp_iter.c
> +++ b/arch/x86/kvm/mmu/tdp_iter.c
> @@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
> {
> iter->sptep = iter->pt_path[iter->level - 1] +
> SHADOW_PT_INDEX(iter->gfn << PAGE_SHIFT, iter->level);
> - iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
> + iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
> }
>
> static gfn_t round_gfn_for_level(gfn_t gfn, int level)
> @@ -86,7 +86,7 @@ static bool try_step_down(struct tdp_iter *iter)
> * Reread the SPTE before stepping down to avoid traversing into page
> * tables that are no longer linked from this entry.
> */
> - iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
> + iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
>
> child_pt = spte_to_child_pt(iter->old_spte, iter->level);
> if (!child_pt)
> @@ -120,7 +120,7 @@ static bool try_step_side(struct tdp_iter *iter)
> iter->gfn += KVM_PAGES_PER_HPAGE(iter->level);
> iter->next_last_level_gfn = iter->gfn;
> iter->sptep++;
> - iter->old_spte = READ_ONCE(*rcu_dereference(iter->sptep));
> + iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
>
> return true;
> }
> diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
> index b1748b988d3a..9c04d8677cb3 100644
> --- a/arch/x86/kvm/mmu/tdp_iter.h
> +++ b/arch/x86/kvm/mmu/tdp_iter.h
> @@ -9,6 +9,22 @@
>
> typedef u64 __rcu *tdp_ptep_t;
>
> +/*
> + * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs)
> + * to be zapped while holding mmu_lock for read. Holding RCU isn't required for
> + * correctness if mmu_lock is held for write, but plumbing "struct kvm" down to
> + * the lower* depths of the TDP MMU just to make lockdep happy is a nightmare,
> + * so all* accesses to SPTEs are must be done under RCU protection.
Nit: Are those extra asterisks intentional? I think this line should also be:
so all accesses to SPTEs must be done under RCU protection.
> + */
> +static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
Nit: function names could also be tdp_iter_read/write_spte. It's a
little shorter, and in the tdp_iter file, but doesn't matter too much
either way.
> +{
> + return READ_ONCE(*rcu_dereference(sptep));
> +}
> +static inline void kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 val)
> +{
> + WRITE_ONCE(*rcu_dereference(sptep), val);
> +}
> +
> /*
> * A TDP iterator performs a pre-order walk over a TDP paging structure.
> */
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 3ff7b4cd7d0e..ca6b30a7130d 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -572,7 +572,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
> * here since the SPTE is going from non-present
> * to non-present.
> */
> - WRITE_ONCE(*rcu_dereference(iter->sptep), 0);
> + kvm_tdp_mmu_write_spte(iter->sptep, 0);
>
> return true;
> }
> @@ -609,7 +609,7 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
> */
> WARN_ON(is_removed_spte(iter->old_spte));
>
> - WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
> + kvm_tdp_mmu_write_spte(iter->sptep, new_spte);
>
> __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
> new_spte, iter->level, false);
> @@ -775,7 +775,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
> * The iter must explicitly re-read the SPTE because
> * the atomic cmpxchg failed.
> */
> - iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
> + iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
> goto retry;
> }
> }
> @@ -1012,7 +1012,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> * because the new value informs the !present
> * path below.
> */
> - iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
> + iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
> }
>
> if (!is_shadow_present_pte(iter.old_spte)) {
> @@ -1225,7 +1225,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
> * The iter must explicitly re-read the SPTE because
> * the atomic cmpxchg failed.
> */
> - iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
> + iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
> goto retry;
> }
> spte_set = true;
> @@ -1296,7 +1296,7 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
> * The iter must explicitly re-read the SPTE because
> * the atomic cmpxchg failed.
> */
> - iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
> + iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
> goto retry;
> }
> spte_set = true;
> @@ -1427,7 +1427,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
> * The iter must explicitly re-read the SPTE because
> * the atomic cmpxchg failed.
> */
> - iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
> + iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
Wow this was open coded in a LOT of places. Thanks for cleaning it up.
> goto retry;
> }
> }
> --
> 2.34.0.rc2.393.gf8c9666880-goog
>
Powered by blists - more mailing lists