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

commit 04b8dc85bf4a64517e3cf20e409eeaa503b15cc1 upstream.

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>
Signed-off-by: Shannon Zhao <shannon.zhao@linaro.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index f949cb61d52773fdc07c62bd68aa8fc53fddef57..16d9d788d0b89baa5df2953a9f062f3086a0e256 100644 (file)
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -128,13 +128,14 @@ static inline void kvm_set_s2pmd_writable(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 203c5ac3bd04f90d24f1a7038d66a7a3b4974f27..cba52cf6ed3fdeb96cb4f94977c22d9c0892bcd8 100644 (file)
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -251,7 +251,7 @@ 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))
@@ -316,7 +316,7 @@ 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);
@@ -791,7 +791,7 @@ 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;

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 93f1a4cfc61f51e8b5bd83917ff0296da84f4b25..a205e957d5c49c57e0a3f91e26ae2b3487b514e3 100644 (file)
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -137,6 +137,8 @@ static inline void kvm_set_s2pmd_writable(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