arm64: KVM: Do not use pgd_index to index stage-2 pgd

The kernel's pgd_index macro is designed to index a normal, page
sized array. KVM is a bit diffferent, as we can use concatenated
pages to have a bigger address space (for example 40bit IPA with
4kB pages gives us an 8kB PGD.

In the above case, the use of pgd_index will always return an index
inside the first 4kB, which makes a guest that has memory above
0x8000000000 rather unhappy, as it spins forever in a page fault,
whist the host happilly corrupts the lower pgd.

The obvious fix is to get our own kvm_pgd_index that does the right
thing(tm).

Tested on X-Gene with a hacked kvmtool that put memory at a stupidly
high address.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index c57c41d..4cf48c3 100644 (file)
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -149,13 +149,14 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
        (__boundary - 1 < (end) - 1)? __boundary: (end);                \
 })
 
+#define kvm_pgd_index(addr)                    pgd_index(addr)
+
 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(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)

diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index a48a73c..5656d79 100644 (file)
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -290,7 +290,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
        phys_addr_t addr = start, end = start + size;
        phys_addr_t next;
 
-       pgd = pgdp + pgd_index(addr);
+       pgd = pgdp + kvm_pgd_index(addr);
        do {
                next = kvm_pgd_addr_end(addr, end);
                if (!pgd_none(*pgd))
@@ -355,7 +355,7 @@ static void stage2_flush_memslot(struct kvm *kvm,
        phys_addr_t next;
        pgd_t *pgd;
 
-       pgd = kvm->arch.pgd + pgd_index(addr);
+       pgd = kvm->arch.pgd + kvm_pgd_index(addr);
        do {
                next = kvm_pgd_addr_end(addr, end);
                stage2_flush_puds(kvm, pgd, addr, next);
@@ -830,7 +830,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
        pgd_t *pgd;
        pud_t *pud;
 
-       pgd = kvm->arch.pgd + pgd_index(addr);
+       pgd = kvm->arch.pgd + kvm_pgd_index(addr);
        if (WARN_ON(pgd_none(*pgd))) {
                if (!cache)
                        return NULL;
@@ -1120,7 +1120,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
        pgd_t *pgd;
        phys_addr_t next;
 
-       pgd = kvm->arch.pgd + pgd_index(addr);
+       pgd = kvm->arch.pgd + kvm_pgd_index(addr);
        do {
                /*
                 * Release kvm_mmu_lock periodically if the memory region is

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index a099cd9..bbfb600 100644 (file)
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #define PTRS_PER_S2_PGD                (1 << PTRS_PER_S2_PGD_SHIFT)
 #define S2_PGD_ORDER           get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
+#define kvm_pgd_index(addr)    (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
 /*
  * 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