[PATCH 14/14] KVM: arm64: Handle stage-2 faults in parallel

From: Oliver Upton <oliver.upton@linux.dev>
To: Marc Zyngier <maz@kernel.org>, James Morse <james.morse@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Oliver Upton <oliver.upton@linux.dev>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org,
	Quentin Perret <qperret@google.com>,
	Ricardo Koller <ricarkol@google.com>,
	Reiji Watanabe <reijiw@google.com>,
	David Matlack <dmatlack@google.com>,
	Ben Gardon <bgardon@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Gavin Shan <gshan@redhat.com>, Peter Xu <peterx@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	linux-kernel@vger.kernel.org
Subject: [PATCH 14/14] KVM: arm64: Handle stage-2 faults in parallel
Date: Tue, 30 Aug 2022 19:52:15 +0000	[thread overview]
Message-ID: <20220830195216.964988-1-oliver.upton@linux.dev> (raw)
In-Reply-To: <20220830194132.962932-1-oliver.upton@linux.dev>

The stage-2 map walker has been made parallel-aware, and as such can be
called while only holding the read side of the MMU lock. Rip out the
conditional locking in user_mem_abort() and instead grab the read lock.
Continue to take the write lock from other callsites to
kvm_pgtable_stage2_map().

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_pgtable.h  |  4 +++-
 arch/arm64/kvm/hyp/nvhe/mem_protect.c |  2 +-
 arch/arm64/kvm/hyp/pgtable.c          |  3 ++-
 arch/arm64/kvm/mmu.c                  | 31 ++++++---------------------
 4 files changed, 13 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 7d2de0a98ccb..dc839db86a1a 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -355,6 +355,8 @@ void kvm_pgtable_stage2_free_removed(void *pgtable, u32 level, void *arg);
  * @prot:	Permissions and attributes for the mapping.
  * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
  *		page-table pages.
+ * @shared:	true if multiple software walkers could be traversing the tables
+ *		in parallel
  *
  * The offset of @addr within a page is ignored, @size is rounded-up to
  * the next page boundary and @phys is rounded-down to the previous page
@@ -376,7 +378,7 @@ void kvm_pgtable_stage2_free_removed(void *pgtable, u32 level, void *arg);
  */
 int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   u64 phys, enum kvm_pgtable_prot prot,
-			   void *mc);
+			   void *mc, bool shared);
 
 /**
  * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 61cf223e0796..924d028af447 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -252,7 +252,7 @@ static inline int __host_stage2_idmap(u64 start, u64 end,
 				      enum kvm_pgtable_prot prot)
 {
 	return kvm_pgtable_stage2_map(&host_kvm.pgt, start, end - start, start,
-				      prot, &host_s2_pool);
+				      prot, &host_s2_pool, false);
 }
 
 /*
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 92e230e7bf3a..52ecaaa84b22 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -944,7 +944,7 @@ static int stage2_map_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, kvm_
 
 int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   u64 phys, enum kvm_pgtable_prot prot,
-			   void *mc)
+			   void *mc, bool shared)
 {
 	int ret;
 	struct stage2_map_data map_data = {
@@ -953,6 +953,7 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		.memcache	= mc,
 		.mm_ops		= pgt->mm_ops,
 		.force_pte	= pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot),
+		.shared		= shared,
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_map_walker,
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 265951c05879..a73adc35cf41 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -840,7 +840,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 		write_lock(&kvm->mmu_lock);
 		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
-					     &cache);
+					     &cache, false);
 		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
@@ -1135,7 +1135,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	bool use_read_lock = false;
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	unsigned long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
@@ -1170,8 +1169,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (logging_active) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
-		use_read_lock = (fault_status == FSC_PERM && write_fault &&
-				 fault_granule == PAGE_SIZE);
 	} else {
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
@@ -1270,15 +1267,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
-	/*
-	 * To reduce MMU contentions and enhance concurrency during dirty
-	 * logging dirty logging, only acquire read lock for permission
-	 * relaxation.
-	 */
-	if (use_read_lock)
-		read_lock(&kvm->mmu_lock);
-	else
-		write_lock(&kvm->mmu_lock);
+	read_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -1322,15 +1311,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == FSC_PERM && vma_pagesize == fault_granule) {
+	if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
-	} else {
-		WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n");
-
+	else
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
-					     memcache);
-	}
+					     memcache, true);
 
 	/* Mark the page dirty only if the fault is handled successfully */
 	if (writable && !ret) {
@@ -1339,10 +1325,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 out_unlock:
-	if (use_read_lock)
-		read_unlock(&kvm->mmu_lock);
-	else
-		write_unlock(&kvm->mmu_lock);
+	read_unlock(&kvm->mmu_lock);
 	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 	return ret != -EAGAIN ? ret : 0;
@@ -1548,7 +1531,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	 */
 	kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT,
 			       PAGE_SIZE, __pfn_to_phys(pfn),
-			       KVM_PGTABLE_PROT_R, NULL);
+			       KVM_PGTABLE_PROT_R, NULL, false);
 
 	return false;
 }
-- 
2.37.2.672.g94769d06f0-goog

