[PATCH 04/18] KVM: x86/mmu: Coalesce TLB flushes across address spaces for gfn range zap

From: Sean Christopherson <seanjc@google.com>
To: Marc Zyngier <maz@kernel.org>,
	Huacai Chen <chenhuacai@kernel.org>,
	Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>,
	Paul Mackerras <paulus@ozlabs.org>,
	Paolo Bonzini <pbonzini@redhat.com>
Cc: James Morse <james.morse@arm.com>,
	Julien Thierry <julien.thierry.kdev@gmail.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, linux-mips@vger.kernel.org,
	kvm@vger.kernel.org, kvm-ppc@vger.kernel.org,
	linux-kernel@vger.kernel.org, Ben Gardon <bgardon@google.com>
Subject: [PATCH 04/18] KVM: x86/mmu: Coalesce TLB flushes across address spaces for gfn range zap
Date: Thu, 25 Mar 2021 19:19:43 -0700	[thread overview]
Message-ID: <20210326021957.1424875-5-seanjc@google.com> (raw)
In-Reply-To: <20210326021957.1424875-1-seanjc@google.com>

Gather pending TLB flushes across both address spaces when zapping a
given gfn range.  This requires feeding "flush" back into subsequent
calls, but on the plus side sets the stage for further batching
between the legacy MMU and TDP MMU.  It also allows refactoring the
address space iteration to cover the legacy and TDP MMUs without
introducing truly ugly code.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 37e2432c78ca..e6e02360ef67 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5227,10 +5227,10 @@ typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_
 static __always_inline bool
 slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			slot_level_handler fn, int start_level, int end_level,
-			gfn_t start_gfn, gfn_t end_gfn, bool flush_on_yield)
+			gfn_t start_gfn, gfn_t end_gfn, bool flush_on_yield,
+			bool flush)
 {
 	struct slot_rmap_walk_iterator iterator;
-	bool flush = false;
 
 	for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
 			end_gfn, &iterator) {
@@ -5259,7 +5259,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	return slot_handle_level_range(kvm, memslot, fn, start_level,
 			end_level, memslot->base_gfn,
 			memslot->base_gfn + memslot->npages - 1,
-			flush_on_yield);
+			flush_on_yield, false);
 }
 
 static __always_inline bool
@@ -5490,7 +5490,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i;
-	bool flush;
+	bool flush = false;
 
 	write_lock(&kvm->mmu_lock);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
@@ -5506,14 +5506,13 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 			flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
 							PG_LEVEL_4K,
 							KVM_MAX_HUGEPAGE_LEVEL,
-							start, end - 1, true);
-
-			if (flush)
-				kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
-								   gfn_end);
+							start, end - 1, true, flush);
 		}
 	}
 
+	if (flush)
+		kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end);
+
 	if (is_tdp_mmu_enabled(kvm)) {
 		flush = kvm_tdp_mmu_zap_gfn_range(kvm, gfn_start, gfn_end);
 		if (flush)
-- 
2.31.0.291.g576ba9dcdaf-goog

