@@ -37,6 +37,11 @@
*/
#define TRAMPOLINE_VA UL(CONFIG_VECTORS_BASE)
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES 2
+
#ifndef __ASSEMBLY__
#include <asm/cacheflush.h>
@@ -83,6 +88,11 @@ static inline void kvm_clean_pgd(pgd_t *pgd)
clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
}
+static inline void kvm_clean_pmd(pmd_t *pmd)
+{
+ clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t));
+}
+
static inline void kvm_clean_pmd_entry(pmd_t *pmd)
{
clean_pmd_entry(pmd);
@@ -123,10 +133,23 @@ static inline bool kvm_page_empty(void *ptr)
}
-#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
-#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
-#define kvm_pud_table_empty(pudp) (0)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(kvm, pudp) (0)
+
+#define KVM_PREALLOC_LEVEL 0
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+ return 0;
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm) { }
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+ return kvm->arch.pgd;
+}
struct kvm;
@@ -409,7 +409,7 @@ static void update_vttbr(struct kvm *kvm)
kvm_next_vmid++;
/* update vttbr to be used with the new vmid */
- pgd_phys = virt_to_phys(kvm->arch.pgd);
+ pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
kvm->arch.vttbr = pgd_phys | vmid;
@@ -42,7 +42,7 @@ static unsigned long hyp_idmap_start;
static unsigned long hyp_idmap_end;
static phys_addr_t hyp_idmap_vector;
-#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
#define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x))
@@ -134,7 +134,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
}
} while (pte++, addr += PAGE_SIZE, addr != end);
- if (kvm_pte_table_empty(start_pte))
+ if (kvm_pte_table_empty(kvm, start_pte))
clear_pmd_entry(kvm, pmd, start_addr);
}
@@ -158,7 +158,7 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
}
} while (pmd++, addr = next, addr != end);
- if (kvm_pmd_table_empty(start_pmd))
+ if (kvm_pmd_table_empty(kvm, start_pmd))
clear_pud_entry(kvm, pud, start_addr);
}
@@ -182,7 +182,7 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
}
} while (pud++, addr = next, addr != end);
- if (kvm_pud_table_empty(start_pud))
+ if (kvm_pud_table_empty(kvm, start_pud))
clear_pgd_entry(kvm, pgd, start_addr);
}
@@ -306,7 +306,7 @@ void free_boot_hyp_pgd(void)
if (boot_hyp_pgd) {
unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
- free_pages((unsigned long)boot_hyp_pgd, pgd_order);
+ free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
boot_hyp_pgd = NULL;
}
@@ -343,7 +343,7 @@ void free_hyp_pgds(void)
for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
- free_pages((unsigned long)hyp_pgd, pgd_order);
+ free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
hyp_pgd = NULL;
}
@@ -401,13 +401,46 @@ static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
return 0;
}
+static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
+ unsigned long end, unsigned long pfn,
+ pgprot_t prot)
+{
+ pud_t *pud;
+ pmd_t *pmd;
+ unsigned long addr, next;
+ int ret;
+
+ addr = start;
+ do {
+ pud = pud_offset(pgd, addr);
+
+ if (pud_none_or_clear_bad(pud)) {
+ pmd = pmd_alloc_one(NULL, addr);
+ if (!pmd) {
+ kvm_err("Cannot allocate Hyp pmd\n");
+ return -ENOMEM;
+ }
+ pud_populate(NULL, pud, pmd);
+ get_page(virt_to_page(pud));
+ kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+ }
+
+ next = pud_addr_end(addr, end);
+ ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+ if (ret)
+ return ret;
+ pfn += (next - addr) >> PAGE_SHIFT;
+ } while (addr = next, addr != end);
+
+ return 0;
+}
+
static int __create_hyp_mappings(pgd_t *pgdp,
unsigned long start, unsigned long end,
unsigned long pfn, pgprot_t prot)
{
pgd_t *pgd;
pud_t *pud;
- pmd_t *pmd;
unsigned long addr, next;
int err = 0;
@@ -416,22 +449,21 @@ static int __create_hyp_mappings(pgd_t *pgdp,
end = PAGE_ALIGN(end);
do {
pgd = pgdp + pgd_index(addr);
- pud = pud_offset(pgd, addr);
- if (pud_none_or_clear_bad(pud)) {
- pmd = pmd_alloc_one(NULL, addr);
- if (!pmd) {
- kvm_err("Cannot allocate Hyp pmd\n");
+ if (pgd_none(*pgd)) {
+ pud = pud_alloc_one(NULL, addr);
+ if (!pud) {
+ kvm_err("Cannot allocate Hyp pud\n");
err = -ENOMEM;
goto out;
}
- pud_populate(NULL, pud, pmd);
- get_page(virt_to_page(pud));
- kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+ pgd_populate(NULL, pgd, pud);
+ get_page(virt_to_page(pgd));
+ kvm_flush_dcache_to_poc(pgd, sizeof(*pgd));
}
next = pgd_addr_end(addr, end);
- err = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+ err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot);
if (err)
goto out;
pfn += (next - addr) >> PAGE_SHIFT;
@@ -521,6 +553,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
*/
int kvm_alloc_stage2_pgd(struct kvm *kvm)
{
+ int ret;
pgd_t *pgd;
if (kvm->arch.pgd != NULL) {
@@ -528,14 +561,38 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
return -EINVAL;
}
- pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+ if (KVM_PREALLOC_LEVEL > 0) {
+ /*
+ * Allocate fake pgd for the page table manipulation macros to
+ * work. This is not used by the hardware and we have no
+ * alignment requirement for this allocation.
+ */
+ pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+ GFP_KERNEL | __GFP_ZERO);
+ } else {
+ /*
+ * Allocate actual first-level Stage-2 page table used by the
+ * hardware for Stage-2 page table walks.
+ */
+ pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+ }
+
if (!pgd)
return -ENOMEM;
+ ret = kvm_prealloc_hwpgd(kvm, pgd);
+ if (ret)
+ goto out_err;
+
kvm_clean_pgd(pgd);
kvm->arch.pgd = pgd;
-
return 0;
+out_err:
+ if (KVM_PREALLOC_LEVEL > 0)
+ kfree(pgd);
+ else
+ free_pages((unsigned long)pgd, S2_PGD_ORDER);
+ return ret;
}
/**
@@ -571,19 +628,39 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
return;
unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
- free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+ kvm_free_hwpgd(kvm);
+ if (KVM_PREALLOC_LEVEL > 0)
+ kfree(kvm->arch.pgd);
+ else
+ free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
kvm->arch.pgd = NULL;
}
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr)
{
pgd_t *pgd;
pud_t *pud;
- pmd_t *pmd;
pgd = kvm->arch.pgd + pgd_index(addr);
- pud = pud_offset(pgd, addr);
+ if (WARN_ON(pgd_none(*pgd))) {
+ if (!cache)
+ return NULL;
+ pud = mmu_memory_cache_alloc(cache);
+ pgd_populate(NULL, pgd, pud);
+ get_page(virt_to_page(pgd));
+ }
+
+ return pud_offset(pgd, addr);
+}
+
+static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+ phys_addr_t addr)
+{
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pud = stage2_get_pud(kvm, cache, addr);
if (pud_none(*pud)) {
if (!cache)
return NULL;
@@ -629,7 +706,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
pmd_t *pmd;
pte_t *pte, old_pte;
- /* Create stage-2 page table mapping - Level 1 */
+ /* Create stage-2 page table mapping - Levels 0 and 1 */
pmd = stage2_get_pmd(kvm, cache, addr);
if (!pmd) {
/*
@@ -690,7 +767,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
if (writable)
kvm_set_s2pte_writable(&pte);
- ret = mmu_topup_memory_cache(&cache, 2, 2);
+ ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
+ KVM_NR_MEM_OBJS);
if (ret)
goto out;
spin_lock(&kvm->mmu_lock);
@@ -805,7 +883,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
up_read(¤t->mm->mmap_sem);
/* We need minimum second+third level pages */
- ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
+ ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES,
+ KVM_NR_MEM_OBJS);
if (ret)
return ret;
@@ -1080,8 +1159,8 @@ int kvm_mmu_init(void)
(unsigned long)phys_base);
}
- hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
- boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+ hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+ boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
if (!hyp_pgd || !boot_hyp_pgd) {
kvm_err("Hyp mode PGD not allocated\n");
@@ -41,6 +41,18 @@
*/
#define TRAMPOLINE_VA (HYP_PAGE_OFFSET_MASK & PAGE_MASK)
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
+ * levels in addition to the PGD and potentially the PUD which are
+ * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2
+ * tables use one level of tables less than the kernel.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define KVM_MMU_CACHE_MIN_PAGES 1
+#else
+#define KVM_MMU_CACHE_MIN_PAGES 2
+#endif
+
#ifdef __ASSEMBLY__
/*
@@ -53,6 +65,7 @@
#else
+#include <asm/pgalloc.h>
#include <asm/cachetype.h>
#include <asm/cacheflush.h>
@@ -65,10 +78,6 @@
#define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT)
#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL)
-/* Make sure we get the right size, and thus the right alignment */
-#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT))
-#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
-
int create_hyp_mappings(void *from, void *to);
int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
void free_boot_hyp_pgd(void);
@@ -93,6 +102,7 @@ void kvm_clear_hyp_idmap(void);
#define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd)
static inline void kvm_clean_pgd(pgd_t *pgd) {}
+static inline void kvm_clean_pmd(pmd_t *pmd) {}
static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
static inline void kvm_clean_pte(pte_t *pte) {}
static inline void kvm_clean_pte_entry(pte_t *pte) {}
@@ -111,19 +121,116 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
#define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end)
#define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end)
+/*
+ * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
+ * the entire IPA input range with a single pgd entry, and we would only need
+ * one pgd entry. Note that in this case, the pgd is actually not used by
+ * the MMU for Stage-2 translations, but is merely a fake pgd used as a data
+ * structure for the kernel pgtable macros to work.
+ */
+#if PGDIR_SHIFT > KVM_PHYS_SHIFT
+#define PTRS_PER_S2_PGD_SHIFT 0
+#else
+#define PTRS_PER_S2_PGD_SHIFT (KVM_PHYS_SHIFT - PGDIR_SHIFT)
+#endif
+#define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT)
+#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
+/*
+ * If we are concatenating first level stage-2 page tables, we would have less
+ * than or equal to 16 pointers in the fake PGD, because that's what the
+ * architecture allows. In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS)
+ * represents the first level for the host, and we add 1 to go to the next
+ * level (which uses contatenation) for the stage-2 tables.
+ */
+#if PTRS_PER_S2_PGD <= 16
+#define KVM_PREALLOC_LEVEL (4 - CONFIG_ARM64_PGTABLE_LEVELS + 1)
+#else
+#define KVM_PREALLOC_LEVEL (0)
+#endif
+
+/**
+ * kvm_prealloc_hwpgd - allocate inital table for VTTBR
+ * @kvm: The KVM struct pointer for the VM.
+ * @pgd: The kernel pseudo pgd
+ *
+ * When the kernel uses more levels of page tables than the guest, we allocate
+ * a fake PGD and pre-populate it to point to the next-level page table, which
+ * will be the real initial page table pointed to by the VTTBR.
+ *
+ * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
+ * the kernel will use folded pud. When KVM_PREALLOC_LEVEL==1, we
+ * allocate 2 consecutive PUD pages.
+ */
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+ unsigned int i;
+ unsigned long hwpgd;
+
+ if (KVM_PREALLOC_LEVEL == 0)
+ return 0;
+
+ hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
+ if (!hwpgd)
+ return -ENOMEM;
+
+ for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+ if (KVM_PREALLOC_LEVEL == 1)
+ pgd_populate(NULL, pgd + i,
+ (pud_t *)hwpgd + i * PTRS_PER_PUD);
+ else if (KVM_PREALLOC_LEVEL == 2)
+ pud_populate(NULL, pud_offset(pgd, 0) + i,
+ (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+ }
+
+ return 0;
+}
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+ pgd_t *pgd = kvm->arch.pgd;
+ pud_t *pud;
+
+ if (KVM_PREALLOC_LEVEL == 0)
+ return pgd;
+
+ pud = pud_offset(pgd, 0);
+ if (KVM_PREALLOC_LEVEL == 1)
+ return pud;
+
+ BUG_ON(KVM_PREALLOC_LEVEL != 2);
+ return pmd_offset(pud, 0);
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm)
+{
+ if (KVM_PREALLOC_LEVEL > 0) {
+ unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
+ free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
+ }
+}
+
static inline bool kvm_page_empty(void *ptr)
{
struct page *ptr_page = virt_to_page(ptr);
return page_count(ptr_page) == 1;
}
-#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
-#ifndef CONFIG_ARM64_64K_PAGES
-#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+
+#ifdef __PAGETABLE_PMD_FOLDED
+#define kvm_pmd_table_empty(kvm, pmdp) (0)
+#else
+#define kvm_pmd_table_empty(kvm, pmdp) \
+ (kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2))
+#endif
+
+#ifdef __PAGETABLE_PUD_FOLDED
+#define kvm_pud_table_empty(kvm, pudp) (0)
#else
-#define kvm_pmd_table_empty(pmdp) (0)
+#define kvm_pud_table_empty(kvm, pudp) \
+ (kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1))
#endif
-#define kvm_pud_table_empty(pudp) (0)
struct kvm;