Received-SPF: pass (google.com: domain of linux-kernel+bounces-194548-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Wed, 29 May 2024 18:05:06 +0000
In-Reply-To: <20240529180510.2295118-1-jthoughton@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240529180510.2295118-1-jthoughton@google.com>
Message-ID: <20240529180510.2295118-4-jthoughton@google.com>
Subject: [PATCH v4 3/7] KVM: Add lockless memslot walk to KVM
From: James Houghton <jthoughton@google.com>
To: Andrew Morton <akpm@linux-foundation.org>, Paolo Bonzini <pbonzini@redhat.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>, Ankit Agrawal <ankita@nvidia.com>, 
	Anup Patel <anup@brainfault.org>, Atish Patra <atishp@atishpatra.org>, 
	Axel Rasmussen <axelrasmussen@google.com>, Bibo Mao <maobibo@loongson.cn>, 
	Catalin Marinas <catalin.marinas@arm.com>, David Matlack <dmatlack@google.com>, 
	David Rientjes <rientjes@google.com>, Huacai Chen <chenhuacai@kernel.org>, 
	James Houghton <jthoughton@google.com>, James Morse <james.morse@arm.com>, 
	Jonathan Corbet <corbet@lwn.net>, Marc Zyngier <maz@kernel.org>, Michael Ellerman <mpe@ellerman.id.au>, 
	Nicholas Piggin <npiggin@gmail.com>, Oliver Upton <oliver.upton@linux.dev>, 
	Palmer Dabbelt <palmer@dabbelt.com>, Paul Walmsley <paul.walmsley@sifive.com>, 
	Raghavendra Rao Ananta <rananta@google.com>, Ryan Roberts <ryan.roberts@arm.com>, 
	Sean Christopherson <seanjc@google.com>, Shaoqin Huang <shahuang@redhat.com>, Shuah Khan <shuah@kernel.org>, 
	Suzuki K Poulose <suzuki.poulose@arm.com>, Tianrui Zhao <zhaotianrui@loongson.cn>, 
	Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>, Zenghui Yu <yuzenghui@huawei.com>, 
	kvm-riscv@lists.infradead.org, kvm@vger.kernel.org, kvmarm@lists.linux.dev, 
	linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org, 
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, 
	linux-mips@vger.kernel.org, linux-mm@kvack.org, 
	linux-riscv@lists.infradead.org, linuxppc-dev@lists.ozlabs.org, 
	loongarch@lists.linux.dev
Content-Type: text/plain; charset="UTF-8"

Provide flexibility to the architecture to synchronize as optimally as
they can instead of always taking the MMU lock for writing.

The immediate application is to allow architectures to implement the
test/clear_young MMU notifiers more cheaply.

Suggested-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: James Houghton <jthoughton@google.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 38 +++++++++++++++++++++++++-------------
 2 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 692c01e41a18..4d7c3e8632e6 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -266,6 +266,7 @@ struct kvm_gfn_range {
 	gfn_t end;
 	union kvm_mmu_notifier_arg arg;
 	bool may_block;
+	bool lockless;
 };
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 14841acb8b95..d197b6725cb3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -558,6 +558,7 @@ struct kvm_mmu_notifier_range {
 	on_lock_fn_t on_lock;
 	bool flush_on_ret;
 	bool may_block;
+	bool lockless;
 };
 
 /*
@@ -612,6 +613,10 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
 			 IS_KVM_NULL_FN(range->handler)))
 		return r;
 
+	/* on_lock will never be called for lockless walks */
+	if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock)))
+		return r;
+
 	idx = srcu_read_lock(&kvm->srcu);
 
 	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
@@ -643,15 +648,18 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
 			gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
 			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
 			gfn_range.slot = slot;
+			gfn_range.lockless = range->lockless;
 
 			if (!r.found_memslot) {
 				r.found_memslot = true;
-				KVM_MMU_LOCK(kvm);
-				if (!IS_KVM_NULL_FN(range->on_lock))
-					range->on_lock(kvm);
-
-				if (IS_KVM_NULL_FN(range->handler))
-					break;
+				if (!range->lockless) {
+					KVM_MMU_LOCK(kvm);
+					if (!IS_KVM_NULL_FN(range->on_lock))
+						range->on_lock(kvm);
+
+					if (IS_KVM_NULL_FN(range->handler))
+						break;
+				}
 			}
 			r.ret |= range->handler(kvm, &gfn_range);
 		}
@@ -660,7 +668,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && r.ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (r.found_memslot)
+	if (r.found_memslot && !range->lockless)
 		KVM_MMU_UNLOCK(kvm);
 
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -686,10 +694,12 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
-static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
-							 unsigned long start,
-							 unsigned long end,
-							 gfn_handler_t handler)
+static __always_inline int kvm_handle_hva_range_no_flush(
+		struct mmu_notifier *mn,
+		unsigned long start,
+		unsigned long end,
+		gfn_handler_t handler,
+		bool lockless)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 	const struct kvm_mmu_notifier_range range = {
@@ -699,6 +709,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
+		.lockless	= lockless,
 	};
 
 	return __kvm_handle_hva_range(kvm, &range).ret;
@@ -889,7 +900,8 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
 	 * cadence. If we find this inaccurate, we might come up with a
 	 * more sophisticated heuristic later.
 	 */
-	return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn);
+	return kvm_handle_hva_range_no_flush(mn, start, end,
+					     kvm_age_gfn, false);
 }
 
 static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
@@ -899,7 +911,7 @@ static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
 	trace_kvm_test_age_hva(address);
 
 	return kvm_handle_hva_range_no_flush(mn, address, address + 1,
-					     kvm_test_age_gfn);
+					     kvm_test_age_gfn, false);
 }
 
 static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
-- 
2.45.1.288.g0e0cd299f1-goog