KVM: MMU: Use slab caches for shadow pages and their headers

[~andy/linux] / drivers / kvm / mmu.c

diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index a96c9ae54f3c4bfefd34dd0bd279b42ac673373d..46491b4cd859158e9ffbc81d2fa8f28889a71254 100644 (file)
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -165,6 +165,8 @@ struct kvm_rmap_desc {
 
 static struct kmem_cache *pte_chain_cache;
 static struct kmem_cache *rmap_desc_cache;
+static struct kmem_cache *mmu_page_cache;
+static struct kmem_cache *mmu_page_header_cache;
 
 static int is_write_protection(struct kvm_vcpu *vcpu)
 {
@@ -235,6 +237,14 @@ static int __mmu_topup_memory_caches(struct kvm_vcpu *vcpu, gfp_t gfp_flags)
                goto out;
        r = mmu_topup_memory_cache(&vcpu->mmu_rmap_desc_cache,
                                   rmap_desc_cache, 1, gfp_flags);
+       if (r)
+               goto out;
+       r = mmu_topup_memory_cache(&vcpu->mmu_page_cache,
+                                  mmu_page_cache, 4, gfp_flags);
+       if (r)
+               goto out;
+       r = mmu_topup_memory_cache(&vcpu->mmu_page_header_cache,
+                                  mmu_page_header_cache, 4, gfp_flags);
 out:
        return r;
 }
@@ -258,6 +268,8 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
 {
        mmu_free_memory_cache(&vcpu->mmu_pte_chain_cache);
        mmu_free_memory_cache(&vcpu->mmu_rmap_desc_cache);
+       mmu_free_memory_cache(&vcpu->mmu_page_cache);
+       mmu_free_memory_cache(&vcpu->mmu_page_header_cache);
 }
 
 static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc,
@@ -439,13 +451,12 @@ static void rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
 }
 
 #ifdef MMU_DEBUG
-static int is_empty_shadow_page(hpa_t page_hpa)
+static int is_empty_shadow_page(u64 *spt)
 {
        u64 *pos;
        u64 *end;
 
-       for (pos = __va(page_hpa), end = pos + PAGE_SIZE / sizeof(u64);
-                     pos != end; pos++)
+       for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
                if (*pos != 0) {
                        printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__,
                               pos, *pos);
@@ -458,8 +469,10 @@ static int is_empty_shadow_page(hpa_t page_hpa)
 static void kvm_mmu_free_page(struct kvm_vcpu *vcpu,
                              struct kvm_mmu_page *page_head)
 {
-       ASSERT(is_empty_shadow_page(page_head->page_hpa));
-       list_move(&page_head->link, &vcpu->free_pages);
+       ASSERT(is_empty_shadow_page(page_head->spt));
+       list_del(&page_head->link);
+       mmu_memory_cache_free(&vcpu->mmu_page_cache, page_head->spt);
+       mmu_memory_cache_free(&vcpu->mmu_page_header_cache, page_head);
        ++vcpu->kvm->n_free_mmu_pages;
 }
 
@@ -473,12 +486,15 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 {
        struct kvm_mmu_page *page;
 
-       if (list_empty(&vcpu->free_pages))
+       if (!vcpu->kvm->n_free_mmu_pages)
                return NULL;
 
-       page = list_entry(vcpu->free_pages.next, struct kvm_mmu_page, link);
-       list_move(&page->link, &vcpu->kvm->active_mmu_pages);
-       ASSERT(is_empty_shadow_page(page->page_hpa));
+       page = mmu_memory_cache_alloc(&vcpu->mmu_page_header_cache,
+                                     sizeof *page);
+       page->spt = mmu_memory_cache_alloc(&vcpu->mmu_page_cache, PAGE_SIZE);
+       set_page_private(virt_to_page(page->spt), (unsigned long)page);
+       list_add(&page->link, &vcpu->kvm->active_mmu_pages);
+       ASSERT(is_empty_shadow_page(page->spt));
        page->slot_bitmap = 0;
        page->multimapped = 0;
        page->parent_pte = parent_pte;
@@ -636,7 +652,7 @@ static void kvm_mmu_page_unlink_children(struct kvm_vcpu *vcpu,
        u64 *pt;
        u64 ent;
 
-       pt = __va(page->page_hpa);
+       pt = page->spt;
 
        if (page->role.level == PT_PAGE_TABLE_LEVEL) {
                for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
@@ -803,7 +819,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, hpa_t p)
                                return -ENOMEM;
                        }
 
-                       table[index] = new_table->page_hpa | PT_PRESENT_MASK
+                       table[index] = __pa(new_table->spt) | PT_PRESENT_MASK
                                | PT_WRITABLE_MASK | PT_USER_MASK;
                }
                table_addr = table[index] & PT64_BASE_ADDR_MASK;
@@ -855,7 +871,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
                ASSERT(!VALID_PAGE(root));
                page = kvm_mmu_get_page(vcpu, root_gfn, 0,
                                        PT64_ROOT_LEVEL, 0, 0, NULL);
-               root = page->page_hpa;
+               root = __pa(page->spt);
                ++page->root_count;
                vcpu->mmu.root_hpa = root;
                return;
@@ -876,7 +892,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
                page = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
                                        PT32_ROOT_LEVEL, !is_paging(vcpu),
                                        0, NULL);
-               root = page->page_hpa;
+               root = __pa(page->spt);
                ++page->root_count;
                vcpu->mmu.pae_root[i] = root | PT_PRESENT_MASK;
        }
@@ -1084,6 +1100,7 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu)
        ASSERT(vcpu);
        ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
 
+       mmu_topup_memory_caches(vcpu);
        if (!is_paging(vcpu))
                return nonpaging_init_context(vcpu);
        else if (is_long_mode(vcpu))
@@ -1220,8 +1237,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
                        if (quadrant != page->role.quadrant)
                                continue;
                }
-               spte = __va(page->page_hpa);
-               spte += page_offset / sizeof(*spte);
+               spte = &page->spt[page_offset / sizeof(*spte)];
                while (npte--) {
                        mmu_pte_write_zap_pte(vcpu, page, spte);
                        mmu_pte_write_new_pte(vcpu, page, spte, new, bytes);
@@ -1258,13 +1274,6 @@ static void free_mmu_pages(struct kvm_vcpu *vcpu)
                                    struct kvm_mmu_page, link);
                kvm_mmu_zap_page(vcpu, page);
        }
-       while (!list_empty(&vcpu->free_pages)) {
-               page = list_entry(vcpu->free_pages.next,
-                                 struct kvm_mmu_page, link);
-               list_del(&page->link);
-               __free_page(pfn_to_page(page->page_hpa >> PAGE_SHIFT));
-               page->page_hpa = INVALID_PAGE;
-       }
        free_page((unsigned long)vcpu->mmu.pae_root);
 }
 
@@ -1275,18 +1284,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
 
        ASSERT(vcpu);
 
-       for (i = 0; i < KVM_NUM_MMU_PAGES; i++) {
-               struct kvm_mmu_page *page_header = &vcpu->page_header_buf[i];
-
-               INIT_LIST_HEAD(&page_header->link);
-               if ((page = alloc_page(GFP_KERNEL)) == NULL)
-                       goto error_1;
-               set_page_private(page, (unsigned long)page_header);
-               page_header->page_hpa = (hpa_t)page_to_pfn(page) << PAGE_SHIFT;
-               memset(__va(page_header->page_hpa), 0, PAGE_SIZE);
-               list_add(&page_header->link, &vcpu->free_pages);
-               ++vcpu->kvm->n_free_mmu_pages;
-       }
+       vcpu->kvm->n_free_mmu_pages = KVM_NUM_MMU_PAGES;
 
        /*
         * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
@@ -1311,7 +1309,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 {
        ASSERT(vcpu);
        ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
-       ASSERT(list_empty(&vcpu->free_pages));
 
        return alloc_mmu_pages(vcpu);
 }
@@ -1320,7 +1317,6 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu)
 {
        ASSERT(vcpu);
        ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa));
-       ASSERT(!list_empty(&vcpu->free_pages));
 
        return init_kvm_mmu(vcpu);
 }
@@ -1346,7 +1342,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm_vcpu *vcpu, int slot)
                if (!test_bit(slot, &page->slot_bitmap))
                        continue;
 
-               pt = __va(page->page_hpa);
+               pt = page->spt;
                for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
                        /* avoid RMW */
                        if (pt[i] & PT_WRITABLE_MASK) {
@@ -1379,6 +1375,10 @@ void kvm_mmu_module_exit(void)
                kmem_cache_destroy(pte_chain_cache);
        if (rmap_desc_cache)
                kmem_cache_destroy(rmap_desc_cache);
+       if (mmu_page_cache)
+               kmem_cache_destroy(mmu_page_cache);
+       if (mmu_page_header_cache)
+               kmem_cache_destroy(mmu_page_header_cache);
 }
 
 int kvm_mmu_module_init(void)
@@ -1394,6 +1394,18 @@ int kvm_mmu_module_init(void)
        if (!rmap_desc_cache)
                goto nomem;
 
+       mmu_page_cache = kmem_cache_create("kvm_mmu_page",
+                                          PAGE_SIZE,
+                                          PAGE_SIZE, 0, NULL, NULL);
+       if (!mmu_page_cache)
+               goto nomem;
+
+       mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header",
+                                                 sizeof(struct kvm_mmu_page),
+                                                 0, 0, NULL, NULL);
+       if (!mmu_page_header_cache)
+               goto nomem;
+
        return 0;
 
 nomem:
@@ -1497,7 +1509,7 @@ static int count_writable_mappings(struct kvm_vcpu *vcpu)
        int i;
 
        list_for_each_entry(page, &vcpu->kvm->active_mmu_pages, link) {
-               u64 *pt = __va(page->page_hpa);
+               u64 *pt = page->spt;
 
                if (page->role.level != PT_PAGE_TABLE_LEVEL)
                        continue;