[PATCH v6 7/7] arm64: KVM: Implement 4 levels of translation tables for HYP and stage2

From: Jungseok Lee
Date: Mon May 12 2014 - 05:41:35 EST

Next message: Jungseok Lee: "[PATCH v6 3/7] arm64: Add a description on 48-bit address space with 4KB pages"
Previous message: Jungseok Lee: "[PATCH v6 4/7] arm64: Add 4 levels of page tables definition with 4KB pages"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This patch adds 4 levels of translation tables implementation for both
HYP and stage2.

Both symmetric and asymmetric configurations for page size and translation
levels are are validated on Fast Models:

1) 4KB + 3 levels guest on 4KB + 4 levels host
2) 4KB + 4 levels guest on 4KB + 4 levels host
3) 64KB + 2 levels guest on 4KB + 4 levels host
4) 4KB + 3 levels guest on 64KB + 2 levels host
5) 4KB + 4 levels guest on 64KB + 2 levels host
6) 64KB + 2 levels guest on 64KB + 2 levels host

Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
Cc: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
Signed-off-by: Jungseok Lee <jays.lee@xxxxxxxxxxx>
Reviewed-by: Sungjinn Chung <sungjinn.chung@xxxxxxxxxxx>
Acked-by: Kukjin Kim <kgene.kim@xxxxxxxxxxx>
---
arch/arm/include/asm/kvm_mmu.h | 10 +++++
arch/arm/kvm/arm.c | 8 ++++
arch/arm/kvm/mmu.c | 77 ++++++++++++++++++++++++++++++++------
arch/arm64/include/asm/kvm_arm.h | 12 ++++++
arch/arm64/include/asm/kvm_mmu.h | 12 ++++++
5 files changed, 108 insertions(+), 11 deletions(-)

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 5c7aa3c..36b9835 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -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 MMU_CACHE_MIN_PAGES 2
+
#ifndef __ASSEMBLY__

#include <asm/cacheflush.h>
@@ -94,6 +99,11 @@ 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);
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9f19f2c..0785291 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -473,11 +473,19 @@ static int set_vttbr_baddr_mask(void)
* 21 <= T0SZ <= 30 is valid under 3 level of translation tables
* 30 <= T0SZ <= 39 is valid under 2 level of translation tables
*/
+#ifdef CONFIG_ARM64_3_LEVELS
if (t0sz <= 20) {
kvm_err("Cannot support %d-bit address space\n", 64 - t0sz);
return -EINVAL;
}
vttbr_x = 37 - t0sz;
+#else
+ if (t0sz <= 15) {
+ kvm_err("Cannot support %d-bit address space\n", 64 - t0sz);
+ return -EINVAL;
+ }
+ vttbr_x = 28 - t0sz;
+#endif
#endif
vttbr_baddr_mask = (((1LLU << (48 - vttbr_x)) - 1) << (vttbr_x - 1));
#endif
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 16f8049..6e2a0b0 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -390,13 +390,44 @@ 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;
+
+ 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);
+
+ create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+ 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;

@@ -405,22 +436,21 @@ 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;
@@ -565,6 +595,24 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
kvm->arch.pgd = NULL;
}

+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;
+
+ pgd = kvm->arch.pgd + pgd_index(addr);
+ if (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)
{
@@ -616,9 +664,15 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte, bool iomap)
{
+ pud_t *pud;
pmd_t *pmd;
pte_t *pte, old_pte;

+ /* Create stage-2 page table mapping - Level 0 */
+ pud = stage2_get_pud(kvm, cache, addr);
+ if (!pud)
+ return 0;
+
/* Create stage-2 page table mapping - Level 1 */
pmd = stage2_get_pmd(kvm, cache, addr);
if (!pmd) {
@@ -677,7 +731,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);

- ret = mmu_topup_memory_cache(&cache, 2, 2);
+ ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
+ KVM_MMU_CACHE_MIN_PAGES);
if (ret)
goto out;
spin_lock(&kvm->mmu_lock);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8dbef70..ac796d0 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -114,6 +114,7 @@
#define VTCR_EL2_IRGN0_MASK (3 << 8)
#define VTCR_EL2_IRGN0_WBWA (1 << 8)
#define VTCR_EL2_SL0_MASK (3 << 6)
+#define VTCR_EL2_SL0_LVL0 (2 << 6)
#define VTCR_EL2_SL0_LVL1 (1 << 6)
#define VTCR_EL2_T0SZ_MASK 0x3f
#define VTCR_EL2_T0SZ(bits) (64 - (bits))
@@ -128,6 +129,7 @@
VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
VTCR_EL2_SL0_LVL1)
#else
+#ifdef CONFIG_ARM64_3_LEVELS
/*
* Stage2 translation configuration:
* 4kB pages (TG0 = 0)
@@ -136,6 +138,16 @@
#define VTCR_EL2_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
VTCR_EL2_SL0_LVL1)
+#else
+/*
+ * Stage2 translation configuration:
+ * 4kB pages (TG0 = 0)
+ * 4 level page tables (SL = 2)
+ */
+#define VTCR_EL2_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
+ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+ VTCR_EL2_SL0_LVL0)
+#endif
#endif

#define VTTBR_VMID_SHIFT (48LLU)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 7d29847..778bf42 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -41,6 +41,17 @@
*/
#define TRAMPOLINE_VA (HYP_PAGE_OFFSET_MASK & PAGE_MASK)

+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
+ */
+#ifdef CONFIG_ARM64_2_LEVELS
+#define KVM_MMU_CACHE_MIN_PAGES 1
+#elif defined(CONFIG_ARM64_3_LEVELS)
+#define KVM_MMU_CACHE_MIN_PAGES 2
+#else
+#define KVM_MMU_CACHE_MIN_PAGES 3
+#endif
+
#ifdef __ASSEMBLY__

/*
@@ -107,6 +118,7 @@ static inline bool kvm_is_write_fault(unsigned long esr)
}

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) {}
--
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Jungseok Lee: "[PATCH v6 3/7] arm64: Add a description on 48-bit address space with 4KB pages"
Previous message: Jungseok Lee: "[PATCH v6 4/7] arm64: Add 4 levels of page tables definition with 4KB pages"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]