From 40fde70d0df993d1a652d6cc69f8b4e967656170 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Wed, 7 Aug 2013 15:33:46 +0530 Subject: [PATCH] kvm: ppc: booke: check range page invalidation progress on page setup When the MM code is invalidating a range of pages, it calls the KVM kvm_mmu_notifier_invalidate_range_start() notifier function, which calls kvm_unmap_hva_range(), which arranges to flush all the TLBs for guest pages. However, the Linux PTEs for the range being flushed are still valid at that point. We are not supposed to establish any new references to pages in the range until the ...range_end() notifier gets called. The PPC-specific KVM code doesn't get any explicit notification of that; instead, we are supposed to use mmu_notifier_retry() to test whether we are or have been inside a range flush notifier pair while we have been referencing a page. This patch calls the mmu_notifier_retry() while mapping the guest page to ensure we are not referencing a page when in range invalidation. This call is inside a region locked with kvm->mmu_lock, which is the same lock that is called by the KVM MMU notifier functions, thus ensuring that no new notification can proceed while we are in the locked region. Signed-off-by: Bharat Bhushan Acked-by: Alexander Graf [Backported to 3.12 - Paolo] Reviewed-by: Bharat Bhushan Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/e500_mmu_host.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 1c6a9d729df4..c65593abae8e 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -332,6 +332,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, unsigned long hva; int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; + int ret = 0; + unsigned long mmu_seq; + struct kvm *kvm = vcpu_e500->vcpu.kvm; + + /* used to check for invalidations in progress */ + mmu_seq = kvm->mmu_notifier_seq; + smp_rmb(); /* * Translate guest physical to true physical, acquiring @@ -449,6 +456,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } + spin_lock(&kvm->mmu_lock); + if (mmu_notifier_retry(kvm, mmu_seq)) { + ret = -EAGAIN; + goto out; + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -457,10 +470,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, /* Clear i-cache for new pages */ kvmppc_mmu_flush_icache(pfn); +out: + spin_unlock(&kvm->mmu_lock); + /* Drop refcount on page, so that mmu notifiers can clear it */ kvm_release_pfn_clean(pfn); - return 0; + return ret; } /* XXX only map the one-one case, for now use TLB0 */