From 691e95fd7396905a38d98919e9c150dbc3ea21a3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 30 Mar 2015 10:41:03 +0530 Subject: powerpc/mm/thp: Make page table walk safe against thp split/collapse We can disable a THP split or a hugepage collapse by disabling irq. We do send IPI to all the cpus in the early part of split/collapse, and disabling local irq ensure we don't make progress with split/collapse. If the THP is getting split we return NULL from find_linux_pte_or_hugepte(). For all the current callers it should be ok. We need to be careful if we want to use returned pte_t pointer outside the irq disabled region. W.r.t to THP split, the pfn remains the same, but then a hugepage collapse will result in a pfn change. There are few steps we can take to avoid a hugepage collapse.One way is to take page reference inside the irq disable region. Other option is to take mmap_sem so that a parallel collapse will not happen. We can also disable collapse by taking pmd_lock. Another method used by kvm subsystem is to check whether we had a mmu_notifer update in between using mmu_notifier_retry(). Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kvm/book3s_64_mmu_hv.c') diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 534acb3c6c3d..26df3864d85a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -539,12 +539,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (!writing && hpte_is_writable(r)) { unsigned int hugepage_shift; pte_t *ptep, pte; + unsigned long flags; /* * We need to protect against page table destruction * while looking up and updating the pte. */ - rcu_read_lock_sched(); + local_irq_save(flags); ptep = find_linux_pte_or_hugepte(current->mm->pgd, hva, &hugepage_shift); if (ptep) { @@ -553,7 +554,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (pte_write(pte)) write_ok = 1; } - rcu_read_unlock_sched(); + local_irq_restore(flags); } } -- cgit v1.2.3 From 7d6e7f7ffaba4e013c7a0589140431799bc17985 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 30 Mar 2015 10:41:04 +0530 Subject: powerpc/mm/thp: Return pte address if we find trans_splitting. For THP that is marked trans splitting, we return the pte. This require the callers to handle the pmd_trans_splitting scenario, if they care. All the current callers are either looking at pfn or write_ok, hence we don't need to update them. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kvm/book3s_64_mmu_hv.c') diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 26df3864d85a..0fe9c92e78ed 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -537,20 +537,17 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } /* if the guest wants write access, see if that is OK */ if (!writing && hpte_is_writable(r)) { - unsigned int hugepage_shift; pte_t *ptep, pte; unsigned long flags; - /* * We need to protect against page table destruction - * while looking up and updating the pte. + * hugepage split and collapse. */ local_irq_save(flags); ptep = find_linux_pte_or_hugepte(current->mm->pgd, - hva, &hugepage_shift); + hva, NULL); if (ptep) { - pte = kvmppc_read_update_linux_pte(ptep, 1, - hugepage_shift); + pte = kvmppc_read_update_linux_pte(ptep, 1); if (pte_write(pte)) write_ok = 1; } -- cgit v1.2.3