KVM: riscv: Use an rwlock for mmu_lock

RISC-V KVM currently uses a spinlock for mmu_lock. That serializes all
G-stage MMU operations, including permission-only updates that do not
allocate or free page-table pages.

Use KVM's rwlock form of mmu_lock, as x86 and arm64 already do. Keep the
existing map, unmap and teardown paths on the write side. This prepares
RISC-V for read-side handling of G-stage permission updates.

Signed-off-by: Jinyu Tang <tjytimi@163.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260517153427.94889-3-tjytimi@163.com
Signed-off-by: Anup Patel <anup@brainfault.org>

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 75b0a951c1bc6f4111d7b44063b4c1852cd66a02..60017ceec9d2afe166cdea9d4ad2ecde4831a0ff 100644 (file)
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -48,6 +48,8 @@
 
 #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
 
+#define KVM_HAVE_MMU_RWLOCK
+
 #define KVM_DIRTY_LOG_MANUAL_CAPS      (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
                                         KVM_DIRTY_LOG_INITIALLY_SET)
 

diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c
index e020b334ae6f0dcfd02e3ca5a4b051346346d2c8..d4ce5e76989c85fd5327655b890886596daa80a0 100644 (file)
--- a/arch/riscv/kvm/gstage.c
+++ b/arch/riscv/kvm/gstage.c
@@ -414,7 +414,7 @@ next:
                 * to prevent starvation and lockup detector warnings.
                 */
                if (!(gstage->flags & KVM_GSTAGE_FLAGS_LOCAL) && may_block && addr < end)
-                       cond_resched_lock(&gstage->kvm->mmu_lock);
+                       cond_resched_rwlock_write(&gstage->kvm->mmu_lock);
        }
 
        return flush;

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index da944cb684045c2653ac826e928dcffea7d864aa..514f06a1f688671a52760f7271746d97c474b5c1 100644 (file)
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -27,9 +27,9 @@ static void mmu_wp_memory_region(struct kvm *kvm, int slot)
 
        kvm_riscv_gstage_init(&gstage, kvm);
 
-       spin_lock(&kvm->mmu_lock);
+       write_lock(&kvm->mmu_lock);
        flush = kvm_riscv_gstage_wp_range(&gstage, start, end);
-       spin_unlock(&kvm->mmu_lock);
+       write_unlock(&kvm->mmu_lock);
        if (flush)
                kvm_flush_remote_tlbs_memslot(kvm, memslot);
 }
@@ -67,9 +67,9 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
                if (ret)
                        goto out;
 
-               spin_lock(&kvm->mmu_lock);
+               write_lock(&kvm->mmu_lock);
                ret = kvm_riscv_gstage_set_pte(&gstage, &pcache, &map);
-               spin_unlock(&kvm->mmu_lock);
+               write_unlock(&kvm->mmu_lock);
                if (ret)
                        goto out;
 
@@ -88,9 +88,9 @@ void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size)
 
        kvm_riscv_gstage_init(&gstage, kvm);
 
-       spin_lock(&kvm->mmu_lock);
+       write_lock(&kvm->mmu_lock);
        flush = kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
-       spin_unlock(&kvm->mmu_lock);
+       write_unlock(&kvm->mmu_lock);
 
        if (flush)
                kvm_flush_remote_tlbs_range(kvm, gpa >> PAGE_SHIFT,
@@ -143,9 +143,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
        kvm_riscv_gstage_init(&gstage, kvm);
 
-       spin_lock(&kvm->mmu_lock);
+       write_lock(&kvm->mmu_lock);
        flush = kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
-       spin_unlock(&kvm->mmu_lock);
+       write_unlock(&kvm->mmu_lock);
        if (flush)
                kvm_flush_remote_tlbs_range(kvm, gpa >> PAGE_SHIFT,
                                            size >> PAGE_SHIFT);
@@ -523,7 +523,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
        if (logging && !is_write)
                writable = false;
 
-       spin_lock(&kvm->mmu_lock);
+       write_lock(&kvm->mmu_lock);
 
        if (mmu_invalidate_retry(kvm, mmu_seq))
                goto out_unlock;
@@ -546,7 +546,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 
 out_unlock:
        kvm_release_faultin_page(kvm, page, ret && ret != -EEXIST, writable);
-       spin_unlock(&kvm->mmu_lock);
+       write_unlock(&kvm->mmu_lock);
        return ret;
 }
 
@@ -576,7 +576,7 @@ void kvm_riscv_mmu_free_pgd(struct kvm *kvm)
        void *pgd = NULL;
        bool flush = false;
 
-       spin_lock(&kvm->mmu_lock);
+       write_lock(&kvm->mmu_lock);
        if (kvm->arch.pgd) {
                kvm_riscv_gstage_init(&gstage, kvm);
                flush = kvm_riscv_gstage_unmap_range(&gstage, 0UL,
@@ -586,7 +586,7 @@ void kvm_riscv_mmu_free_pgd(struct kvm *kvm)
                kvm->arch.pgd_phys = 0;
                kvm->arch.pgd_levels = 0;
        }
-       spin_unlock(&kvm->mmu_lock);
+       write_unlock(&kvm->mmu_lock);
 
        if (flush)
                kvm_flush_remote_tlbs(kvm);