From mboxrd@z Thu Jan 1 00:00:00 1970 From: Leonardo Bras Subject: [PATCH v4 08/11] powerpc/kvm/book3s_hv: Applies counting method to monitor lockless pgtbl walks Date: Fri, 27 Sep 2019 20:40:05 -0300 Message-ID: <20190927234008.11513-9-leonardo@linux.ibm.com> References: <20190927234008.11513-1-leonardo@linux.ibm.com> Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Return-path: In-Reply-To: <20190927234008.11513-1-leonardo@linux.ibm.com> Sender: linux-kernel-owner@vger.kernel.org To: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, kvm-ppc@vger.kernel.org, linux-arch@vger.kernel.org, linux-mm@kvack.org Cc: Leonardo Bras , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Arnd Bergmann , "Aneesh Kumar K.V" , Christophe Leroy , Andrew Morton , Dan Williams , Nicholas Piggin , Mahesh Salgaonkar , Allison Randal , Thomas Gleixner , Ganesh Goudar , Mike Rapoport , YueHaibing , Greg Kroah-Hartman , Ira Weiny , Jason Gunthorpe List-Id: linux-arch.vger.kernel.org Applies the counting-based method for monitoring all book3s_hv related functions that do lockless pagetable walks. Adds comments explaining that some lockless pagetable walks don't need protection due to guest pgd not being a target of THP collapse/split, or due to being called from Realmode + MSR_EE = 0 kvmppc_do_h_enter: Fixes where local_irq_restore() must be placed (after the last usage of ptep). Signed-off-by: Leonardo Bras --- arch/powerpc/kvm/book3s_hv_nested.c | 22 ++++++++++++++++++++-- arch/powerpc/kvm/book3s_hv_rm_mmu.c | 18 ++++++++++++++---- 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 735e0ac6f5b2..5a641b559de7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -803,7 +803,11 @@ static void kvmhv_update_nest_rmap_rc(struct kvm *kvm, u64 n_rmap, if (!gp) return; - /* Find the pte */ + /* Find the pte: + * We are walking the nested guest (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift); /* * If the pte is present and the pfn is still the same, update the pte. @@ -853,7 +857,11 @@ static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap, if (!gp) return; - /* Find and invalidate the pte */ + /* Find and invalidate the pte: + * We are walking the nested guest (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift); /* Don't spuriously invalidate ptes if the pfn has changed */ if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa)) @@ -921,6 +929,11 @@ static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu, int shift; spin_lock(&kvm->mmu_lock); + /* + * We are walking the nested guest (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift); if (!shift) shift = PAGE_SHIFT; @@ -1362,6 +1375,11 @@ static long int __kvmhv_nested_page_fault(struct kvm_run *run, /* See if can find translation in our partition scoped tables for L1 */ pte = __pte(0); spin_lock(&kvm->mmu_lock); + /* + * We are walking the secondary (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ pte_p = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (!shift) shift = PAGE_SHIFT; diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 63e0ce91e29d..2076a7ac230a 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -252,6 +252,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, * If we had a page table table change after lookup, we would * retry via mmu_notifier_retry. */ + start_lockless_pgtbl_walk(kvm->mm); if (!realmode) local_irq_save(irq_flags); /* @@ -287,8 +288,6 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, pa |= gpa & ~PAGE_MASK; } } - if (!realmode) - local_irq_restore(irq_flags); ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1); ptel |= pa; @@ -311,6 +310,9 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G); ptel |= HPTE_R_M; } + if (!realmode) + local_irq_restore(irq_flags); + end_lockless_pgtbl_walk(kvm->mm); /* Find and lock the HPTEG slot to use */ do_insert: @@ -885,11 +887,19 @@ static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa, /* Translate to host virtual address */ hva = __gfn_to_hva_memslot(memslot, gfn); - /* Try to find the host pte for that virtual address */ + /* Try to find the host pte for that virtual address : + * Called by hcall_real_table (real mode + MSR_EE=0) + * Interrupts are disabled here. + */ + start_lockless_pgtbl_walk(kvm->mm); ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); - if (!ptep) + if (!ptep) { + end_lockless_pgtbl_walk(kvm->mm); return H_TOO_HARD; + } pte = kvmppc_read_update_linux_pte(ptep, writing); + end_lockless_pgtbl_walk(kvm->mm); + if (!pte_present(pte)) return H_TOO_HARD; -- 2.20.1 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0a-001b2d01.pphosted.com ([148.163.156.1]:53936 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728558AbfI0Xle (ORCPT ); Fri, 27 Sep 2019 19:41:34 -0400 From: Leonardo Bras Subject: [PATCH v4 08/11] powerpc/kvm/book3s_hv: Applies counting method to monitor lockless pgtbl walks Date: Fri, 27 Sep 2019 20:40:05 -0300 Message-ID: <20190927234008.11513-9-leonardo@linux.ibm.com> In-Reply-To: <20190927234008.11513-1-leonardo@linux.ibm.com> References: <20190927234008.11513-1-leonardo@linux.ibm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: linux-arch-owner@vger.kernel.org List-ID: To: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, kvm-ppc@vger.kernel.org, linux-arch@vger.kernel.org, linux-mm@kvack.org Cc: Leonardo Bras , Benjamin Herrenschmidt , Paul Mackerras , Michael Ellerman , Arnd Bergmann , "Aneesh Kumar K.V" , Christophe Leroy , Andrew Morton , Dan Williams , Nicholas Piggin , Mahesh Salgaonkar , Allison Randal , Thomas Gleixner , Ganesh Goudar , Mike Rapoport , YueHaibing , Greg Kroah-Hartman , Ira Weiny , Jason Gunthorpe , John Hubbard , Keith Busch Message-ID: <20190927234005.nktZ8Ni4HHf4cCrSb4RCtXecaPSAWoWdvHiev6Xsypo@z> Applies the counting-based method for monitoring all book3s_hv related functions that do lockless pagetable walks. Adds comments explaining that some lockless pagetable walks don't need protection due to guest pgd not being a target of THP collapse/split, or due to being called from Realmode + MSR_EE = 0 kvmppc_do_h_enter: Fixes where local_irq_restore() must be placed (after the last usage of ptep). Signed-off-by: Leonardo Bras --- arch/powerpc/kvm/book3s_hv_nested.c | 22 ++++++++++++++++++++-- arch/powerpc/kvm/book3s_hv_rm_mmu.c | 18 ++++++++++++++---- 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 735e0ac6f5b2..5a641b559de7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -803,7 +803,11 @@ static void kvmhv_update_nest_rmap_rc(struct kvm *kvm, u64 n_rmap, if (!gp) return; - /* Find the pte */ + /* Find the pte: + * We are walking the nested guest (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift); /* * If the pte is present and the pfn is still the same, update the pte. @@ -853,7 +857,11 @@ static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap, if (!gp) return; - /* Find and invalidate the pte */ + /* Find and invalidate the pte: + * We are walking the nested guest (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift); /* Don't spuriously invalidate ptes if the pfn has changed */ if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa)) @@ -921,6 +929,11 @@ static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu, int shift; spin_lock(&kvm->mmu_lock); + /* + * We are walking the nested guest (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift); if (!shift) shift = PAGE_SHIFT; @@ -1362,6 +1375,11 @@ static long int __kvmhv_nested_page_fault(struct kvm_run *run, /* See if can find translation in our partition scoped tables for L1 */ pte = __pte(0); spin_lock(&kvm->mmu_lock); + /* + * We are walking the secondary (partition-scoped) page table here. + * We can do this without disabling irq because the Linux MM + * subsystem doesn't do THP splits and collapses on this tree. + */ pte_p = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (!shift) shift = PAGE_SHIFT; diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 63e0ce91e29d..2076a7ac230a 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -252,6 +252,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, * If we had a page table table change after lookup, we would * retry via mmu_notifier_retry. */ + start_lockless_pgtbl_walk(kvm->mm); if (!realmode) local_irq_save(irq_flags); /* @@ -287,8 +288,6 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, pa |= gpa & ~PAGE_MASK; } } - if (!realmode) - local_irq_restore(irq_flags); ptel &= HPTE_R_KEY | HPTE_R_PP0 | (psize-1); ptel |= pa; @@ -311,6 +310,9 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G); ptel |= HPTE_R_M; } + if (!realmode) + local_irq_restore(irq_flags); + end_lockless_pgtbl_walk(kvm->mm); /* Find and lock the HPTEG slot to use */ do_insert: @@ -885,11 +887,19 @@ static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa, /* Translate to host virtual address */ hva = __gfn_to_hva_memslot(memslot, gfn); - /* Try to find the host pte for that virtual address */ + /* Try to find the host pte for that virtual address : + * Called by hcall_real_table (real mode + MSR_EE=0) + * Interrupts are disabled here. + */ + start_lockless_pgtbl_walk(kvm->mm); ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); - if (!ptep) + if (!ptep) { + end_lockless_pgtbl_walk(kvm->mm); return H_TOO_HARD; + } pte = kvmppc_read_update_linux_pte(ptep, writing); + end_lockless_pgtbl_walk(kvm->mm); + if (!pte_present(pte)) return H_TOO_HARD; -- 2.20.1