x86: implement la57 paging mode

The new paging more is extension of IA32e mode with more additional page
table level.

It brings support of 57-bit vitrual address space (128PB) and 52-bit
physical address space (4PB).

The structure of new page table level is identical to pml4.

The feature is enumerated with CPUID.(EAX=07H, ECX=0):ECX[bit 16].

CR4.LA57[bit 12] need to be set when pageing enables to activate 5-level
paging mode.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Message-Id: <20161215001305.146807-1-kirill.shutemov@linux.intel.com>
[Drop changes to target-i386/translate.c. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 180 insertions, 54 deletions

diff --git a/target/i386/monitor.c b/target/i386/monitor.c
index 9a3b4d746e..468aa073bc 100644
--- a/target/i386/monitor.c
+++ b/target/i386/monitor.c
@@ -30,13 +30,18 @@
 #include "hmp.h"
 
 
-static void print_pte(Monitor *mon, hwaddr addr,
-                      hwaddr pte,
-                      hwaddr mask)
+static void print_pte(Monitor *mon, CPUArchState *env, hwaddr addr,
+                      hwaddr pte, hwaddr mask)
 {
 #ifdef TARGET_X86_64
-    if (addr & (1ULL << 47)) {
-        addr |= -1LL << 48;
+    if (env->cr[4] & CR4_LA57_MASK) {
+        if (addr & (1ULL << 56)) {
+            addr |= -1LL << 57;
+        }
+    } else {
+        if (addr & (1ULL << 47)) {
+            addr |= -1LL << 48;
+        }
     }
 #endif
     monitor_printf(mon, TARGET_FMT_plx ": " TARGET_FMT_plx
@@ -66,13 +71,13 @@ static void tlb_info_32(Monitor *mon, CPUArchState *env)
         if (pde & PG_PRESENT_MASK) {
             if ((pde & PG_PSE_MASK) && (env->cr[4] & CR4_PSE_MASK)) {
                 /* 4M pages */
-                print_pte(mon, (l1 << 22), pde, ~((1 << 21) - 1));
+                print_pte(mon, env, (l1 << 22), pde, ~((1 << 21) - 1));
             } else {
                 for(l2 = 0; l2 < 1024; l2++) {
                     cpu_physical_memory_read((pde & ~0xfff) + l2 * 4, &pte, 4);
                     pte = le32_to_cpu(pte);
                     if (pte & PG_PRESENT_MASK) {
-                        print_pte(mon, (l1 << 22) + (l2 << 12),
+                        print_pte(mon, env, (l1 << 22) + (l2 << 12),
                                   pte & ~PG_PSE_MASK,
                                   ~0xfff);
                     }
@@ -100,7 +105,7 @@ static void tlb_info_pae32(Monitor *mon, CPUArchState *env)
                 if (pde & PG_PRESENT_MASK) {
                     if (pde & PG_PSE_MASK) {
                         /* 2M pages with PAE, CR4.PSE is ignored */
-                        print_pte(mon, (l1 << 30 ) + (l2 << 21), pde,
+                        print_pte(mon, env, (l1 << 30) + (l2 << 21), pde,
                                   ~((hwaddr)(1 << 20) - 1));
                     } else {
                         pt_addr = pde & 0x3fffffffff000ULL;
@@ -108,7 +113,7 @@ static void tlb_info_pae32(Monitor *mon, CPUArchState *env)
                             cpu_physical_memory_read(pt_addr + l3 * 8, &pte, 8);
                             pte = le64_to_cpu(pte);
                             if (pte & PG_PRESENT_MASK) {
-                                print_pte(mon, (l1 << 30 ) + (l2 << 21)
+                                print_pte(mon, env, (l1 << 30) + (l2 << 21)
                                           + (l3 << 12),
                                           pte & ~PG_PSE_MASK,
                                           ~(hwaddr)0xfff);
@@ -122,61 +127,82 @@ static void tlb_info_pae32(Monitor *mon, CPUArchState *env)
 }
 
 #ifdef TARGET_X86_64
-static void tlb_info_64(Monitor *mon, CPUArchState *env)
+static void tlb_info_la48(Monitor *mon, CPUArchState *env,
+        uint64_t l0, uint64_t pml4_addr)
 {
     uint64_t l1, l2, l3, l4;
     uint64_t pml4e, pdpe, pde, pte;
-    uint64_t pml4_addr, pdp_addr, pd_addr, pt_addr;
+    uint64_t pdp_addr, pd_addr, pt_addr;
 
-    pml4_addr = env->cr[3] & 0x3fffffffff000ULL;
     for (l1 = 0; l1 < 512; l1++) {
         cpu_physical_memory_read(pml4_addr + l1 * 8, &pml4e, 8);
         pml4e = le64_to_cpu(pml4e);
-        if (pml4e & PG_PRESENT_MASK) {
-            pdp_addr = pml4e & 0x3fffffffff000ULL;
-            for (l2 = 0; l2 < 512; l2++) {
-                cpu_physical_memory_read(pdp_addr + l2 * 8, &pdpe, 8);
-                pdpe = le64_to_cpu(pdpe);
-                if (pdpe & PG_PRESENT_MASK) {
-                    if (pdpe & PG_PSE_MASK) {
-                        /* 1G pages, CR4.PSE is ignored */
-                        print_pte(mon, (l1 << 39) + (l2 << 30), pdpe,
-                                  0x3ffffc0000000ULL);
-                    } else {
-                        pd_addr = pdpe & 0x3fffffffff000ULL;
-                        for (l3 = 0; l3 < 512; l3++) {
-                            cpu_physical_memory_read(pd_addr + l3 * 8, &pde, 8);
-                            pde = le64_to_cpu(pde);
-                            if (pde & PG_PRESENT_MASK) {
-                                if (pde & PG_PSE_MASK) {
-                                    /* 2M pages, CR4.PSE is ignored */
-                                    print_pte(mon, (l1 << 39) + (l2 << 30) +
-                                              (l3 << 21), pde,
-                                              0x3ffffffe00000ULL);
-                                } else {
-                                    pt_addr = pde & 0x3fffffffff000ULL;
-                                    for (l4 = 0; l4 < 512; l4++) {
-                                        cpu_physical_memory_read(pt_addr
-                                                                 + l4 * 8,
-                                                                 &pte, 8);
-                                        pte = le64_to_cpu(pte);
-                                        if (pte & PG_PRESENT_MASK) {
-                                            print_pte(mon, (l1 << 39) +
-                                                      (l2 << 30) +
-                                                      (l3 << 21) + (l4 << 12),
-                                                      pte & ~PG_PSE_MASK,
-                                                      0x3fffffffff000ULL);
-                                        }
-                                    }
-                                }
-                            }
-                        }
+        if (!(pml4e & PG_PRESENT_MASK)) {
+            continue;
+        }
+
+        pdp_addr = pml4e & 0x3fffffffff000ULL;
+        for (l2 = 0; l2 < 512; l2++) {
+            cpu_physical_memory_read(pdp_addr + l2 * 8, &pdpe, 8);
+            pdpe = le64_to_cpu(pdpe);
+            if (!(pdpe & PG_PRESENT_MASK)) {
+                continue;
+            }
+
+            if (pdpe & PG_PSE_MASK) {
+                /* 1G pages, CR4.PSE is ignored */
+                print_pte(mon, env, (l0 << 48) + (l1 << 39) + (l2 << 30),
+                        pdpe, 0x3ffffc0000000ULL);
+                continue;
+            }
+
+            pd_addr = pdpe & 0x3fffffffff000ULL;
+            for (l3 = 0; l3 < 512; l3++) {
+                cpu_physical_memory_read(pd_addr + l3 * 8, &pde, 8);
+                pde = le64_to_cpu(pde);
+                if (!(pde & PG_PRESENT_MASK)) {
+                    continue;
+                }
+
+                if (pde & PG_PSE_MASK) {
+                    /* 2M pages, CR4.PSE is ignored */
+                    print_pte(mon, env, (l0 << 48) + (l1 << 39) + (l2 << 30) +
+                            (l3 << 21), pde, 0x3ffffffe00000ULL);
+                    continue;
+                }
+
+                pt_addr = pde & 0x3fffffffff000ULL;
+                for (l4 = 0; l4 < 512; l4++) {
+                    cpu_physical_memory_read(pt_addr
+                            + l4 * 8,
+                            &pte, 8);
+                    pte = le64_to_cpu(pte);
+                    if (pte & PG_PRESENT_MASK) {
+                        print_pte(mon, env, (l0 << 48) + (l1 << 39) +
+                                (l2 << 30) + (l3 << 21) + (l4 << 12),
+                                pte & ~PG_PSE_MASK, 0x3fffffffff000ULL);
                     }
                 }
             }
         }
     }
 }
+
+static void tlb_info_la57(Monitor *mon, CPUArchState *env)
+{
+    uint64_t l0;
+    uint64_t pml5e;
+    uint64_t pml5_addr;
+
+    pml5_addr = env->cr[3] & 0x3fffffffff000ULL;
+    for (l0 = 0; l0 < 512; l0++) {
+        cpu_physical_memory_read(pml5_addr + l0 * 8, &pml5e, 8);
+        pml5e = le64_to_cpu(pml5e);
+        if (pml5e & PG_PRESENT_MASK) {
+            tlb_info_la48(mon, env, l0, pml5e & 0x3fffffffff000ULL);
+        }
+    }
+}
 #endif /* TARGET_X86_64 */
 
 void hmp_info_tlb(Monitor *mon, const QDict *qdict)
@@ -192,7 +218,11 @@ void hmp_info_tlb(Monitor *mon, const QDict *qdict)
     if (env->cr[4] & CR4_PAE_MASK) {
 #ifdef TARGET_X86_64
         if (env->hflags & HF_LMA_MASK) {
-            tlb_info_64(mon, env);
+            if (env->cr[4] & CR4_LA57_MASK) {
+                tlb_info_la57(mon, env);
+            } else {
+                tlb_info_la48(mon, env, 0, env->cr[3] & 0x3fffffffff000ULL);
+            }
         } else
 #endif
         {
@@ -324,7 +354,7 @@ static void mem_info_pae32(Monitor *mon, CPUArchState *env)
 
 
 #ifdef TARGET_X86_64
-static void mem_info_64(Monitor *mon, CPUArchState *env)
+static void mem_info_la48(Monitor *mon, CPUArchState *env)
 {
     int prot, last_prot;
     uint64_t l1, l2, l3, l4;
@@ -400,6 +430,98 @@ static void mem_info_64(Monitor *mon, CPUArchState *env)
     /* Flush last range */
     mem_print(mon, &start, &last_prot, (hwaddr)1 << 48, 0);
 }
+
+static void mem_info_la57(Monitor *mon, CPUArchState *env)
+{
+    int prot, last_prot;
+    uint64_t l0, l1, l2, l3, l4;
+    uint64_t pml5e, pml4e, pdpe, pde, pte;
+    uint64_t pml5_addr, pml4_addr, pdp_addr, pd_addr, pt_addr, start, end;
+
+    pml5_addr = env->cr[3] & 0x3fffffffff000ULL;
+    last_prot = 0;
+    start = -1;
+    for (l0 = 0; l0 < 512; l0++) {
+        cpu_physical_memory_read(pml5_addr + l0 * 8, &pml5e, 8);
+        pml4e = le64_to_cpu(pml5e);
+        end = l0 << 48;
+        if (!(pml5e & PG_PRESENT_MASK)) {
+            prot = 0;
+            mem_print(mon, &start, &last_prot, end, prot);
+            continue;
+        }
+
+        pml4_addr = pml5e & 0x3fffffffff000ULL;
+        for (l1 = 0; l1 < 512; l1++) {
+            cpu_physical_memory_read(pml4_addr + l1 * 8, &pml4e, 8);
+            pml4e = le64_to_cpu(pml4e);
+            end = (l0 << 48) + (l1 << 39);
+            if (!(pml4e & PG_PRESENT_MASK)) {
+                prot = 0;
+                mem_print(mon, &start, &last_prot, end, prot);
+                continue;
+            }
+
+            pdp_addr = pml4e & 0x3fffffffff000ULL;
+            for (l2 = 0; l2 < 512; l2++) {
+                cpu_physical_memory_read(pdp_addr + l2 * 8, &pdpe, 8);
+                pdpe = le64_to_cpu(pdpe);
+                end = (l0 << 48) + (l1 << 39) + (l2 << 30);
+                if (pdpe & PG_PRESENT_MASK) {
+                    prot = 0;
+                    mem_print(mon, &start, &last_prot, end, prot);
+                    continue;
+                }
+
+                if (pdpe & PG_PSE_MASK) {
+                    prot = pdpe & (PG_USER_MASK | PG_RW_MASK |
+                            PG_PRESENT_MASK);
+                    prot &= pml4e;
+                    mem_print(mon, &start, &last_prot, end, prot);
+                    continue;
+                }
+
+                pd_addr = pdpe & 0x3fffffffff000ULL;
+                for (l3 = 0; l3 < 512; l3++) {
+                    cpu_physical_memory_read(pd_addr + l3 * 8, &pde, 8);
+                    pde = le64_to_cpu(pde);
+                    end = (l0 << 48) + (l1 << 39) + (l2 << 30) + (l3 << 21);
+                    if (pde & PG_PRESENT_MASK) {
+                        prot = 0;
+                        mem_print(mon, &start, &last_prot, end, prot);
+                        continue;
+                    }
+
+                    if (pde & PG_PSE_MASK) {
+                        prot = pde & (PG_USER_MASK | PG_RW_MASK |
+                                PG_PRESENT_MASK);
+                        prot &= pml4e & pdpe;
+                        mem_print(mon, &start, &last_prot, end, prot);
+                        continue;
+                    }
+
+                    pt_addr = pde & 0x3fffffffff000ULL;
+                    for (l4 = 0; l4 < 512; l4++) {
+                        cpu_physical_memory_read(pt_addr + l4 * 8, &pte, 8);
+                        pte = le64_to_cpu(pte);
+                        end = (l0 << 48) + (l1 << 39) + (l2 << 30) +
+                            (l3 << 21) + (l4 << 12);
+                        if (pte & PG_PRESENT_MASK) {
+                            prot = pte & (PG_USER_MASK | PG_RW_MASK |
+                                    PG_PRESENT_MASK);
+                            prot &= pml4e & pdpe & pde;
+                        } else {
+                            prot = 0;
+                        }
+                        mem_print(mon, &start, &last_prot, end, prot);
+                    }
+                }
+            }
+        }
+    }
+    /* Flush last range */
+    mem_print(mon, &start, &last_prot, (hwaddr)1 << 57, 0);
+}
 #endif /* TARGET_X86_64 */
 
 void hmp_info_mem(Monitor *mon, const QDict *qdict)
@@ -415,7 +537,11 @@ void hmp_info_mem(Monitor *mon, const QDict *qdict)
     if (env->cr[4] & CR4_PAE_MASK) {
 #ifdef TARGET_X86_64
         if (env->hflags & HF_LMA_MASK) {
-            mem_info_64(mon, env);
+            if (env->cr[4] & CR4_LA57_MASK) {
+                mem_info_la57(mon, env);
+            } else {
+                mem_info_la48(mon, env);
+            }
         } else
 #endif
         {