KVM: MMU: make page walker aware of mapping levels

The page walker may be used with nested paging too when accessing mmio
areas.  Make it support the additional page-level too.

[ Marcelo: fix reserved bit check for 1gb pte ]

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

2 files changed, 44 insertions, 25 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 110c224ed1fb..09ab6433bf1d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -108,6 +108,9 @@ module_param(oos_shadow, bool, 0644);
 
 #define PT32_LEVEL_MASK(level) \
                 (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level))
+#define PT32_LVL_OFFSET_MASK(level) \
+        (PT32_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+                                                * PT32_LEVEL_BITS))) - 1))
 
 #define PT32_INDEX(address, level)\
         (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
@@ -116,10 +119,19 @@ module_param(oos_shadow, bool, 0644);
 #define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
 #define PT64_DIR_BASE_ADDR_MASK \
         (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
+#define PT64_LVL_ADDR_MASK(level) \
+        (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+                                                * PT64_LEVEL_BITS))) - 1))
+#define PT64_LVL_OFFSET_MASK(level) \
+        (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+                                                * PT64_LEVEL_BITS))) - 1))
 
 #define PT32_BASE_ADDR_MASK PAGE_MASK
 #define PT32_DIR_BASE_ADDR_MASK \
         (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1))
+#define PT32_LVL_ADDR_MASK(level) \
+        (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+                                            * PT32_LEVEL_BITS))) - 1))
 
 #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
                         | PT64_NX_MASK)
@@ -130,6 +142,7 @@ module_param(oos_shadow, bool, 0644);
 #define PFERR_RSVD_MASK (1U << 3)
 #define PFERR_FETCH_MASK (1U << 4)
 
+#define PT_PDPE_LEVEL 3
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
 
@@ -2273,7 +2286,9 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
                 context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
                         rsvd_bits(maxphyaddr, 51);
                 context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
-                context->rsvd_bits_mask[1][2] = context->rsvd_bits_mask[0][2];
+                context->rsvd_bits_mask[1][2] = exb_bit_rsvd |
+                        rsvd_bits(maxphyaddr, 51) |
+                        rsvd_bits(13, 29);
                 context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
                         rsvd_bits(maxphyaddr, 51) |
                         rsvd_bits(13, 20);              /* large page */
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index b167f0d57b54..578276e34bd9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -27,7 +27,8 @@
         #define guest_walker guest_walker64
         #define FNAME(name) paging##64_##name
         #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
-        #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK
+        #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
+        #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
         #define PT_INDEX(addr, level) PT64_INDEX(addr, level)
         #define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level)
         #define PT_LEVEL_BITS PT64_LEVEL_BITS
@@ -43,7 +44,8 @@
         #define guest_walker guest_walker32
         #define FNAME(name) paging##32_##name
         #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
-        #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK
+        #define PT_LVL_ADDR_MASK(lvl) PT32_LVL_ADDR_MASK(lvl)
+        #define PT_LVL_OFFSET_MASK(lvl) PT32_LVL_OFFSET_MASK(lvl)
         #define PT_INDEX(addr, level) PT32_INDEX(addr, level)
         #define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level)
         #define PT_LEVEL_BITS PT32_LEVEL_BITS
@@ -53,8 +55,8 @@
         #error Invalid PTTYPE value
 #endif
 
-#define gpte_to_gfn FNAME(gpte_to_gfn)
-#define gpte_to_gfn_pde FNAME(gpte_to_gfn_pde)
+#define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl)
+#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PT_PAGE_TABLE_LEVEL)
 
 /*
  * The guest_walker structure emulates the behavior of the hardware page
@@ -71,14 +73,9 @@ struct guest_walker {
         u32 error_code;
 };
 
-static gfn_t gpte_to_gfn(pt_element_t gpte)
+static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
 {
-        return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
-}
-
-static gfn_t gpte_to_gfn_pde(pt_element_t gpte)
-{
-        return (gpte & PT_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+        return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
 }
 
 static bool FNAME(cmpxchg_gpte)(struct kvm *kvm,
@@ -189,18 +186,24 @@ walk:
 
                 walker->ptes[walker->level - 1] = pte;
 
-                if (walker->level == PT_PAGE_TABLE_LEVEL) {
-                        walker->gfn = gpte_to_gfn(pte);
-                        break;
-                }
-
-                if (walker->level == PT_DIRECTORY_LEVEL
-                    && (pte & PT_PAGE_SIZE_MASK)
-                    && (PTTYPE == 64 || is_pse(vcpu))) {
-                        walker->gfn = gpte_to_gfn_pde(pte);
-                        walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL);
-                        if (PTTYPE == 32 && is_cpuid_PSE36())
+                if ((walker->level == PT_PAGE_TABLE_LEVEL) ||
+                    ((walker->level == PT_DIRECTORY_LEVEL) &&
+                                (pte & PT_PAGE_SIZE_MASK)  &&
+                                (PTTYPE == 64 || is_pse(vcpu))) ||
+                    ((walker->level == PT_PDPE_LEVEL) &&
+                                (pte & PT_PAGE_SIZE_MASK)  &&
+                                is_long_mode(vcpu))) {
+                        int lvl = walker->level;
+
+                        walker->gfn = gpte_to_gfn_lvl(pte, lvl);
+                        walker->gfn += (addr & PT_LVL_OFFSET_MASK(lvl))
+                                        >> PAGE_SHIFT;
+
+                        if (PTTYPE == 32 &&
+                            walker->level == PT_DIRECTORY_LEVEL &&
+                            is_cpuid_PSE36())
                                 walker->gfn += pse36_gfn_delta(pte);
+
                         break;
                 }
 
@@ -609,9 +612,10 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 #undef PT_BASE_ADDR_MASK
 #undef PT_INDEX
 #undef PT_LEVEL_MASK
-#undef PT_DIR_BASE_ADDR_MASK
+#undef PT_LVL_ADDR_MASK
+#undef PT_LVL_OFFSET_MASK
 #undef PT_LEVEL_BITS
 #undef PT_MAX_FULL_LEVELS
 #undef gpte_to_gfn
-#undef gpte_to_gfn_pde
+#undef gpte_to_gfn_lvl
 #undef CMPXCHG