Merge remote branch 'qemu-kvm/uq/master' into HEAD

bswap.h

@@ -205,8 +205,10 @@ static inline void cpu_to_be32wu(uint32_t *p, uint32_t v)
 
 #ifdef HOST_WORDS_BIGENDIAN
 #define cpu_to_32wu cpu_to_be32wu
+#define leul_to_cpu(v) le ## HOST_LONG_BITS ## _to_cpu(v)
 #else
 #define cpu_to_32wu cpu_to_le32wu
+#define leul_to_cpu(v) (v)
 #endif
 
 #undef le_bswap

cpus.c

@@ -401,6 +401,7 @@ static void *kvm_cpu_thread_fn(void *arg)
 {
     CPUState *env = arg;
 
+    qemu_mutex_lock(&qemu_global_mutex);
     qemu_thread_self(env->thread);
     if (kvm_enabled())
         kvm_init_vcpu(env);
@@ -408,7 +409,6 @@ static void *kvm_cpu_thread_fn(void *arg)
     kvm_block_io_signals(env);
 
     /* signal CPU creation */
-    qemu_mutex_lock(&qemu_global_mutex);
     env->created = 1;
     qemu_cond_signal(&qemu_cpu_cond);
 

hw/vga.c

@@ -1618,8 +1618,8 @@ void vga_dirty_log_stop(VGACommonState *s)
 	kvm_log_stop(s->map_addr, s->map_end - s->map_addr);
 
     if (kvm_enabled() && s->lfb_vram_mapped) {
-	kvm_log_stop(isa_mem_base + 0xa0000, 0x80000);
+	kvm_log_stop(isa_mem_base + 0xa0000, 0x8000);
-	kvm_log_stop(isa_mem_base + 0xa8000, 0x80000);
+	kvm_log_stop(isa_mem_base + 0xa8000, 0x8000);
     }
 
 #ifdef CONFIG_BOCHS_VBE

kvm-all.c

@@ -26,6 +26,7 @@
 #include "hw/hw.h"
 #include "gdbstub.h"
 #include "kvm.h"
+#include "bswap.h"
 
 /* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
 #define PAGE_SIZE TARGET_PAGE_SIZE
@@ -64,6 +65,7 @@ struct KVMState
     int migration_log;
     int vcpu_events;
     int robust_singlestep;
+    int debugregs;
 #ifdef KVM_CAP_SET_GUEST_DEBUG
     struct kvm_sw_breakpoint_head kvm_sw_breakpoints;
 #endif
@@ -282,11 +284,41 @@ static int kvm_set_migration_log(int enable)
     return 0;
 }
 
-static int test_le_bit(unsigned long nr, unsigned char *addr)
+/* get kvm's dirty pages bitmap and update qemu's */
+static int kvm_get_dirty_pages_log_range(unsigned long start_addr,
+                                         unsigned long *bitmap,
+                                         unsigned long offset,
+                                         unsigned long mem_size)
 {
-    return (addr[nr >> 3] >> (nr & 7)) & 1;
+    unsigned int i, j;
+    unsigned long page_number, addr, addr1, c;
+    ram_addr_t ram_addr;
+    unsigned int len = ((mem_size / TARGET_PAGE_SIZE) + HOST_LONG_BITS - 1) /
+        HOST_LONG_BITS;
+
+    /*
+     * bitmap-traveling is faster than memory-traveling (for addr...)
+     * especially when most of the memory is not dirty.
+     */
+    for (i = 0; i < len; i++) {
+        if (bitmap[i] != 0) {
+            c = leul_to_cpu(bitmap[i]);
+            do {
+                j = ffsl(c) - 1;
+                c &= ~(1ul << j);
+                page_number = i * HOST_LONG_BITS + j;
+                addr1 = page_number * TARGET_PAGE_SIZE;
+                addr = offset + addr1;
+                ram_addr = cpu_get_physical_page_desc(addr);
+                cpu_physical_memory_set_dirty(ram_addr);
+            } while (c != 0);
+        }
+    }
+    return 0;
 }
 
+#define ALIGN(x, y)  (((x)+(y)-1) & ~((y)-1))
+
 /**
  * kvm_physical_sync_dirty_bitmap - Grab dirty bitmap from kernel space
  * This function updates qemu's dirty bitmap using cpu_physical_memory_set_dirty().
@@ -300,8 +332,6 @@ static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
 {
     KVMState *s = kvm_state;
     unsigned long size, allocated_size = 0;
-    target_phys_addr_t phys_addr;
-    ram_addr_t addr;
     KVMDirtyLog d;
     KVMSlot *mem;
     int ret = 0;
@@ -313,7 +343,7 @@ static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
             break;
         }
 
-        size = ((mem->memory_size >> TARGET_PAGE_BITS) + 7) / 8;
+        size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS), HOST_LONG_BITS) / 8;
         if (!d.dirty_bitmap) {
             d.dirty_bitmap = qemu_malloc(size);
         } else if (size > allocated_size) {
@@ -330,17 +360,9 @@ static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
             break;
         }
 
-        for (phys_addr = mem->start_addr, addr = mem->phys_offset;
+        kvm_get_dirty_pages_log_range(mem->start_addr, d.dirty_bitmap,
-             phys_addr < mem->start_addr + mem->memory_size;
+                                      mem->start_addr, mem->memory_size);
-             phys_addr += TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
+        start_addr = mem->start_addr + mem->memory_size;
-            unsigned char *bitmap = (unsigned char *)d.dirty_bitmap;
-            unsigned nr = (phys_addr - mem->start_addr) >> TARGET_PAGE_BITS;
-
-            if (test_le_bit(nr, bitmap)) {
-                cpu_physical_memory_set_dirty(addr);
-            }
-        }
-        start_addr = phys_addr;
     }
     qemu_free(d.dirty_bitmap);
 
@@ -664,6 +686,11 @@ int kvm_init(int smp_cpus)
         kvm_check_extension(s, KVM_CAP_X86_ROBUST_SINGLESTEP);
 #endif
 
+    s->debugregs = 0;
+#ifdef KVM_CAP_DEBUGREGS
+    s->debugregs = kvm_check_extension(s, KVM_CAP_DEBUGREGS);
+#endif
+
     ret = kvm_arch_init(s, smp_cpus);
     if (ret < 0)
         goto err;
@@ -724,6 +751,32 @@ static int kvm_handle_io(uint16_t port, void *data, int direction, int size,
     return 1;
 }
 
+#ifdef KVM_CAP_INTERNAL_ERROR_DATA
+static void kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
+{
+
+    if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
+        int i;
+
+        fprintf(stderr, "KVM internal error. Suberror: %d\n",
+                run->internal.suberror);
+
+        for (i = 0; i < run->internal.ndata; ++i) {
+            fprintf(stderr, "extra data[%d]: %"PRIx64"\n",
+                    i, (uint64_t)run->internal.data[i]);
+        }
+    }
+    cpu_dump_state(env, stderr, fprintf, 0);
+    if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
+        fprintf(stderr, "emulation failure\n");
+    }
+    /* FIXME: Should trigger a qmp message to let management know
+     * something went wrong.
+     */
+    vm_stop(0);
+}
+#endif
+
 void kvm_flush_coalesced_mmio_buffer(void)
 {
 #ifdef KVM_CAP_COALESCED_MMIO
@@ -839,6 +892,11 @@ int kvm_cpu_exec(CPUState *env)
         case KVM_EXIT_EXCEPTION:
             DPRINTF("kvm_exit_exception\n");
             break;
+#ifdef KVM_CAP_INTERNAL_ERROR_DATA
+        case KVM_EXIT_INTERNAL_ERROR:
+            kvm_handle_internal_error(env, run);
+            break;
+#endif
         case KVM_EXIT_DEBUG:
             DPRINTF("kvm_exit_debug\n");
 #ifdef KVM_CAP_SET_GUEST_DEBUG
@@ -939,6 +997,11 @@ int kvm_has_robust_singlestep(void)
     return kvm_state->robust_singlestep;
 }
 
+int kvm_has_debugregs(void)
+{
+    return kvm_state->debugregs;
+}
+
 void kvm_setup_guest_memory(void *start, size_t size)
 {
     if (!kvm_has_sync_mmu()) {

kvm.h

@@ -40,6 +40,7 @@ int kvm_init(int smp_cpus);
 int kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
 int kvm_has_robust_singlestep(void);
+int kvm_has_debugregs(void);
 
 #ifdef NEED_CPU_H
 int kvm_init_vcpu(CPUState *env);

target-i386/helper.c

@@ -356,6 +356,7 @@ void cpu_dump_state(CPUState *env, FILE *f,
                         cc_op_name);
         }
     }
+    cpu_fprintf(f, "EFER=%016" PRIx64 "\n", env->efer);
     if (flags & X86_DUMP_FPU) {
         int fptag;
         fptag = 0;

target-i386/kvm.c

@@ -326,6 +326,25 @@ static int kvm_has_msr_star(CPUState *env)
     return 0;
 }
 
+static int kvm_init_identity_map_page(KVMState *s)
+{
+#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
+    int ret;
+    uint64_t addr = 0xfffbc000;
+
+    if (!kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
+        return 0;
+    }
+
+    ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &addr);
+    if (ret < 0) {
+        fprintf(stderr, "kvm_set_identity_map_addr: %s\n", strerror(ret));
+        return ret;
+    }
+#endif
+    return 0;
+}
+
 int kvm_arch_init(KVMState *s, int smp_cpus)
 {
     int ret;
@@ -353,7 +372,12 @@ int kvm_arch_init(KVMState *s, int smp_cpus)
         perror("e820_add_entry() table is full");
         exit(1);
     }
-    return kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, 0xfffbd000);
+    ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, 0xfffbd000);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return kvm_init_identity_map_page(s);
 }
                     
 static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
@@ -874,6 +898,53 @@ static int kvm_guest_debug_workarounds(CPUState *env)
     return ret;
 }
 
+static int kvm_put_debugregs(CPUState *env)
+{
+#ifdef KVM_CAP_DEBUGREGS
+    struct kvm_debugregs dbgregs;
+    int i;
+
+    if (!kvm_has_debugregs()) {
+        return 0;
+    }
+
+    for (i = 0; i < 4; i++) {
+        dbgregs.db[i] = env->dr[i];
+    }
+    dbgregs.dr6 = env->dr[6];
+    dbgregs.dr7 = env->dr[7];
+    dbgregs.flags = 0;
+
+    return kvm_vcpu_ioctl(env, KVM_SET_DEBUGREGS, &dbgregs);
+#else
+    return 0;
+#endif
+}
+
+static int kvm_get_debugregs(CPUState *env)
+{
+#ifdef KVM_CAP_DEBUGREGS
+    struct kvm_debugregs dbgregs;
+    int i, ret;
+
+    if (!kvm_has_debugregs()) {
+        return 0;
+    }
+
+    ret = kvm_vcpu_ioctl(env, KVM_GET_DEBUGREGS, &dbgregs);
+    if (ret < 0) {
+       return ret;
+    }
+    for (i = 0; i < 4; i++) {
+        env->dr[i] = dbgregs.db[i];
+    }
+    env->dr[4] = env->dr[6] = dbgregs.dr6;
+    env->dr[5] = env->dr[7] = dbgregs.dr7;
+#endif
+
+    return 0;
+}
+
 int kvm_arch_put_registers(CPUState *env, int level)
 {
     int ret;
@@ -909,6 +980,10 @@ int kvm_arch_put_registers(CPUState *env, int level)
     if (ret < 0)
         return ret;
 
+    ret = kvm_put_debugregs(env);
+    if (ret < 0)
+        return ret;
+
     return 0;
 }
 
@@ -940,6 +1015,10 @@ int kvm_arch_get_registers(CPUState *env)
     if (ret < 0)
         return ret;
 
+    ret = kvm_get_debugregs(env);
+    if (ret < 0)
+        return ret;
+
     return 0;
 }