KVM: Allow for different capacities in kvm_mmu_memory_cache structs

Allow the capacity of the kvm_mmu_memory_cache struct to be chosen at
declaration time rather than being fixed for all declarations. This will
be used in a follow-up commit to declare an cache in x86 with a capacity
of 512+ objects without having to increase the capacity of all caches in
KVM.

This change requires each cache now specify its capacity at runtime,
since the cache struct itself no longer has a fixed capacity known at
compile time. To protect against someone accidentally defining a
kvm_mmu_memory_cache struct directly (without the extra storage), this
commit includes a WARN_ON() in kvm_mmu_topup_memory_cache().

In order to support different capacities, this commit changes the
objects pointer array to be dynamically allocated the first time the
cache is topped-up.

While here, opportunistically clean up the stack-allocated
kvm_mmu_memory_cache structs in riscv and arm64 to use designated
initializers.

No functional change intended.

Reviewed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220516232138.1783324-22-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index f5651a05b6a85a77f8be96480d517f093cf3fd9c..87f1cd0df36ea7360ac5e3b597009292bc9ef45a 100644 (file)
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -786,7 +786,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 {
        phys_addr_t addr;
        int ret = 0;
-       struct kvm_mmu_memory_cache cache = { 0, __GFP_ZERO, NULL, };
+       struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO };
        struct kvm_pgtable *pgt = kvm->arch.mmu.pgt;
        enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE |
                                     KVM_PGTABLE_PROT_R |

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 1c00695ebee7ee1d41d36e6cff40322efa3a3f99..081f8d2b9cf3dd6194af92dd0c25c9b7921375bc 100644 (file)
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -350,10 +350,7 @@ static int gstage_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
        int ret = 0;
        unsigned long pfn;
        phys_addr_t addr, end;
-       struct kvm_mmu_memory_cache pcache;
-
-       memset(&pcache, 0, sizeof(pcache));
-       pcache.gfp_zero = __GFP_ZERO;
+       struct kvm_mmu_memory_cache pcache = { .gfp_zero = __GFP_ZERO };
 
        end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
        pfn = __phys_to_pfn(hpa);

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a2bbdf3ab086e73effd8cae6605d26a911e34afd..3554e48406e495ed83290b1db5b097e676f8bdd8 100644 (file)
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1356,6 +1356,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
+int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min);
 int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc);
 void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);

diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index f328a01db4fe977bc7458e4a0299ce0951e9379f..4d933518060fa66e53dbf7b7d304484c32161ee5 100644 (file)
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -85,12 +85,16 @@ struct gfn_to_pfn_cache {
  * MMU flows is problematic, as is triggering reclaim, I/O, etc... while
  * holding MMU locks.  Note, these caches act more like prefetch buffers than
  * classical caches, i.e. objects are not returned to the cache on being freed.
+ *
+ * The @capacity field and @objects array are lazily initialized when the cache
+ * is topped up (__kvm_mmu_topup_memory_cache()).
  */
 struct kvm_mmu_memory_cache {
        int nobjs;
        gfp_t gfp_zero;
        struct kmem_cache *kmem_cache;
-       void *objects[KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE];
+       int capacity;
+       void **objects;
 };
 #endif
 

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5b8ae83e09d76f5cf6d4449b0fd3d3add73ba99d..45188d11812c17414f804e983184d44e53509d3e 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -396,14 +396,31 @@ static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
                return (void *)__get_free_page(gfp_flags);
 }
 
-int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
 {
+       gfp_t gfp = GFP_KERNEL_ACCOUNT;
        void *obj;
 
        if (mc->nobjs >= min)
                return 0;
-       while (mc->nobjs < ARRAY_SIZE(mc->objects)) {
-               obj = mmu_memory_cache_alloc_obj(mc, GFP_KERNEL_ACCOUNT);
+
+       if (unlikely(!mc->objects)) {
+               if (WARN_ON_ONCE(!capacity))
+                       return -EIO;
+
+               mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp);
+               if (!mc->objects)
+                       return -ENOMEM;
+
+               mc->capacity = capacity;
+       }
+
+       /* It is illegal to request a different capacity across topups. */
+       if (WARN_ON_ONCE(mc->capacity != capacity))
+               return -EIO;
+
+       while (mc->nobjs < mc->capacity) {
+               obj = mmu_memory_cache_alloc_obj(mc, gfp);
                if (!obj)
                        return mc->nobjs >= min ? 0 : -ENOMEM;
                mc->objects[mc->nobjs++] = obj;
@@ -411,6 +428,11 @@ int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
        return 0;
 }
 
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+{
+       return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min);
+}
+
 int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
 {
        return mc->nobjs;
@@ -424,6 +446,11 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
                else
                        free_page((unsigned long)mc->objects[--mc->nobjs]);
        }
+
+       kvfree(mc->objects);
+
+       mc->objects = NULL;
+       mc->capacity = 0;
 }
 
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)