| Message ID | 20210813031629.78670-1-jiangshanlai@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [V2] KVM: X86: Move PTE present check from loop body to __shadow_walk_next() | expand |
Hello, Paolo Could you have a review please. Thanks Lai On Fri, Aug 13, 2021 at 9:01 PM Lai Jiangshan <jiangshanlai@gmail.com> wrote: > > From: Lai Jiangshan <laijs@linux.alibaba.com> > > So far, the loop bodies already ensure the PTE is present before calling > __shadow_walk_next(): Some loop bodies simply exit with a !PRESENT > directly and some other loop bodies, i.e. FNAME(fetch) and __direct_map() > do not currently terminate their walks with a !PRESENT, but they get away > with it because they install present non-leaf SPTEs in the loop itself. > > But checking pte present in __shadow_walk_next() is a more prudent way of > programing and loop bodies will not need to always check it. It allows us > removing unneded is_shadow_present_pte() in the loop bodies. > > Terminating on !is_shadow_present_pte() is 100% the correct behavior, as > walking past a !PRESENT SPTE would lead to attempting to read a the next > level SPTE from a garbage iter->shadow_addr. Even some paths that do _not_ > currently have a !is_shadow_present_pte() in the loop body is Ok since > they will install present non-leaf SPTEs and the additinal present check > is just an NOP. > > The checking result in __shadow_walk_next() will be propagated to > shadow_walk_okay() for being used in any for(;;) loop. > > Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com> > --- > Changed from V1: > Merge the two patches > Update changelog > Remove !is_shadow_present_pte() in FNAME(invlpg) > arch/x86/kvm/mmu/mmu.c | 13 ++----------- > arch/x86/kvm/mmu/paging_tmpl.h | 2 +- > 2 files changed, 3 insertions(+), 12 deletions(-) > > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c > index a272ccbddfa1..42eebba6782e 100644 > --- a/arch/x86/kvm/mmu/mmu.c > +++ b/arch/x86/kvm/mmu/mmu.c > @@ -2231,7 +2231,7 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) > static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator, > u64 spte) > { > - if (is_last_spte(spte, iterator->level)) { > + if (!is_shadow_present_pte(spte) || is_last_spte(spte, iterator->level)) { > iterator->level = 0; > return; > } > @@ -3152,9 +3152,6 @@ static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte) > for_each_shadow_entry_lockless(vcpu, gpa, iterator, old_spte) { > sptep = iterator.sptep; > *spte = old_spte; > - > - if (!is_shadow_present_pte(old_spte)) > - break; > } > > return sptep; > @@ -3694,9 +3691,6 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level > spte = mmu_spte_get_lockless(iterator.sptep); > > sptes[leaf] = spte; > - > - if (!is_shadow_present_pte(spte)) > - break; > } > > return leaf; > @@ -3811,11 +3805,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) > u64 spte; > > walk_shadow_page_lockless_begin(vcpu); > - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { > + for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) > clear_sp_write_flooding_count(iterator.sptep); > - if (!is_shadow_present_pte(spte)) > - break; > - } > walk_shadow_page_lockless_end(vcpu); > } > > diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h > index f70afecbf3a2..13138b03cc69 100644 > --- a/arch/x86/kvm/mmu/paging_tmpl.h > +++ b/arch/x86/kvm/mmu/paging_tmpl.h > @@ -977,7 +977,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) > FNAME(update_pte)(vcpu, sp, sptep, &gpte); > } > > - if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) > + if (!sp->unsync_children) > break; > } > write_unlock(&vcpu->kvm->mmu_lock); > -- > 2.19.1.6.gb485710b >
On Fri, Aug 13, 2021, Lai Jiangshan wrote: > From: Lai Jiangshan <laijs@linux.alibaba.com> > > So far, the loop bodies already ensure the PTE is present before calling > __shadow_walk_next(): Some loop bodies simply exit with a !PRESENT > directly and some other loop bodies, i.e. FNAME(fetch) and __direct_map() > do not currently terminate their walks with a !PRESENT, but they get away > with it because they install present non-leaf SPTEs in the loop itself. > > But checking pte present in __shadow_walk_next() is a more prudent way of > programing and loop bodies will not need to always check it. It allows us > removing unneded is_shadow_present_pte() in the loop bodies. ^^^^^^^ unneeded > > Terminating on !is_shadow_present_pte() is 100% the correct behavior, as > walking past a !PRESENT SPTE would lead to attempting to read a the next > level SPTE from a garbage iter->shadow_addr. Even some paths that do _not_ > currently have a !is_shadow_present_pte() in the loop body is Ok since > they will install present non-leaf SPTEs and the additinal present check ^^^^^^^^^ additional > is just an NOP. > > The checking result in __shadow_walk_next() will be propagated to > shadow_walk_okay() for being used in any for(;;) loop. > > Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com> > --- Nits aside, Reviewed-by: Sean Christopherson <seanjc@google.com>
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a272ccbddfa1..42eebba6782e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2231,7 +2231,7 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator, u64 spte) { - if (is_last_spte(spte, iterator->level)) { + if (!is_shadow_present_pte(spte) || is_last_spte(spte, iterator->level)) { iterator->level = 0; return; } @@ -3152,9 +3152,6 @@ static u64 *fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gpa_t gpa, u64 *spte) for_each_shadow_entry_lockless(vcpu, gpa, iterator, old_spte) { sptep = iterator.sptep; *spte = old_spte; - - if (!is_shadow_present_pte(old_spte)) - break; } return sptep; @@ -3694,9 +3691,6 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level spte = mmu_spte_get_lockless(iterator.sptep); sptes[leaf] = spte; - - if (!is_shadow_present_pte(spte)) - break; } return leaf; @@ -3811,11 +3805,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) u64 spte; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { + for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) clear_sp_write_flooding_count(iterator.sptep); - if (!is_shadow_present_pte(spte)) - break; - } walk_shadow_page_lockless_end(vcpu); } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f70afecbf3a2..13138b03cc69 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -977,7 +977,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) FNAME(update_pte)(vcpu, sp, sptep, &gpte); } - if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) + if (!sp->unsync_children) break; } write_unlock(&vcpu->kvm->mmu_lock);