X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/a3d6841ff82223f4c2bb05dbf3e29335e15f31c2..ea026b2fc32bdddad6df22f7ab952761a29d9e6b:/kvm-all.c

diff --git a/kvm-all.c b/kvm-all.c
index 5cb2db24ab..9fb295ce63 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -2,9 +2,11 @@
  * QEMU KVM support
  *
  * Copyright IBM, Corp. 2008
+ *           Red Hat, Inc. 2008
  *
  * Authors:
  *  Anthony Liguori   <aliguori@us.ibm.com>
+ *  Glauber Costa     <gcosta@redhat.com>
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
@@ -22,6 +24,9 @@
 #include "sysemu.h"
 #include "kvm.h"
 
+/* KVM uses PAGE_SIZE in it's definition of COALESCED_MMIO_MAX */
+#define PAGE_SIZE TARGET_PAGE_SIZE
+
 //#define DEBUG_KVM
 
 #ifdef DEBUG_KVM
@@ -32,7 +37,16 @@
     do { } while (0)
 #endif
 
-typedef struct kvm_userspace_memory_region KVMSlot;
+typedef struct KVMSlot
+{
+    target_phys_addr_t start_addr;
+    ram_addr_t memory_size;
+    ram_addr_t phys_offset;
+    int slot;
+    int flags;
+} KVMSlot;
+
+typedef struct kvm_dirty_log KVMDirtyLog;
 
 int kvm_allowed = 0;
 
@@ -41,6 +55,7 @@ struct KVMState
     KVMSlot slots[32];
     int fd;
     int vmfd;
+    int coalesced_mmio;
 };
 
 static KVMState *kvm_state;
@@ -67,14 +82,28 @@ static KVMSlot *kvm_lookup_slot(KVMState *s, target_phys_addr_t start_addr)
     for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
         KVMSlot *mem = &s->slots[i];
 
-        if (start_addr >= mem->guest_phys_addr &&
-            start_addr < (mem->guest_phys_addr + mem->memory_size))
+        if (start_addr >= mem->start_addr &&
+            start_addr < (mem->start_addr + mem->memory_size))
             return mem;
     }
 
     return NULL;
 }
 
+static int kvm_set_user_memory_region(KVMState *s, KVMSlot *slot)
+{
+    struct kvm_userspace_memory_region mem;
+
+    mem.slot = slot->slot;
+    mem.guest_phys_addr = slot->start_addr;
+    mem.memory_size = slot->memory_size;
+    mem.userspace_addr = (unsigned long)phys_ram_base + slot->phys_offset;
+    mem.flags = slot->flags;
+
+    return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
+}
+
+
 int kvm_init_vcpu(CPUState *env)
 {
     KVMState *s = kvm_state;
@@ -112,6 +141,150 @@ err:
     return ret;
 }
 
+int kvm_sync_vcpus(void)
+{
+    CPUState *env;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        int ret;
+
+        ret = kvm_arch_put_registers(env);
+        if (ret)
+            return ret;
+    }
+
+    return 0;
+}
+
+/*
+ * dirty pages logging control
+ */
+static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr, target_phys_addr_t end_addr,
+                                      unsigned flags,
+                                      unsigned mask)
+{
+    KVMState *s = kvm_state;
+    KVMSlot *mem = kvm_lookup_slot(s, phys_addr);
+    if (mem == NULL)  {
+            dprintf("invalid parameters %llx-%llx\n", phys_addr, end_addr);
+            return -EINVAL;
+    }
+
+    flags = (mem->flags & ~mask) | flags;
+    /* Nothing changed, no need to issue ioctl */
+    if (flags == mem->flags)
+            return 0;
+
+    mem->flags = flags;
+
+    return kvm_set_user_memory_region(s, mem);
+}
+
+int kvm_log_start(target_phys_addr_t phys_addr, target_phys_addr_t end_addr)
+{
+        return kvm_dirty_pages_log_change(phys_addr, end_addr,
+                                          KVM_MEM_LOG_DIRTY_PAGES,
+                                          KVM_MEM_LOG_DIRTY_PAGES);
+}
+
+int kvm_log_stop(target_phys_addr_t phys_addr, target_phys_addr_t end_addr)
+{
+        return kvm_dirty_pages_log_change(phys_addr, end_addr,
+                                          0,
+                                          KVM_MEM_LOG_DIRTY_PAGES);
+}
+
+/**
+ * kvm_physical_sync_dirty_bitmap - Grab dirty bitmap from kernel space
+ * This function updates qemu's dirty bitmap using cpu_physical_memory_set_dirty().
+ * This means all bits are set to dirty.
+ *
+ * @start_add: start of logged region. This is what we use to search the memslot
+ * @end_addr: end of logged region.
+ */
+void kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr, target_phys_addr_t end_addr)
+{
+    KVMState *s = kvm_state;
+    KVMDirtyLog d;
+    KVMSlot *mem = kvm_lookup_slot(s, start_addr);
+    unsigned long alloc_size;
+    ram_addr_t addr;
+    target_phys_addr_t phys_addr = start_addr;
+
+    dprintf("sync addr: %llx into %lx\n", start_addr, mem->phys_offset);
+    if (mem == NULL) {
+            fprintf(stderr, "BUG: %s: invalid parameters\n", __func__);
+            return;
+    }
+
+    alloc_size = mem->memory_size >> TARGET_PAGE_BITS / sizeof(d.dirty_bitmap);
+    d.dirty_bitmap = qemu_mallocz(alloc_size);
+
+    if (d.dirty_bitmap == NULL) {
+        dprintf("Could not allocate dirty bitmap\n");
+        return;
+    }
+
+    d.slot = mem->slot;
+    dprintf("slot %d, phys_addr %llx, uaddr: %llx\n",
+            d.slot, mem->start_addr, mem->phys_offset);
+
+    if (kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
+        dprintf("ioctl failed %d\n", errno);
+        goto out;
+    }
+
+    phys_addr = start_addr;
+    for (addr = mem->phys_offset; phys_addr < end_addr; phys_addr+= TARGET_PAGE_SIZE, addr += TARGET_PAGE_SIZE) {
+        unsigned long *bitmap = (unsigned long *)d.dirty_bitmap;
+        unsigned nr = (phys_addr - start_addr) >> TARGET_PAGE_BITS;
+        unsigned word = nr / (sizeof(*bitmap) * 8);
+        unsigned bit = nr % (sizeof(*bitmap) * 8);
+        if ((bitmap[word] >> bit) & 1)
+            cpu_physical_memory_set_dirty(addr);
+    }
+out:
+    qemu_free(d.dirty_bitmap);
+}
+
+int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
+{
+    int ret = -ENOSYS;
+#ifdef KVM_CAP_COALESCED_MMIO
+    KVMState *s = kvm_state;
+
+    if (s->coalesced_mmio) {
+        struct kvm_coalesced_mmio_zone zone;
+
+        zone.addr = start;
+        zone.size = size;
+
+        ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
+    }
+#endif
+
+    return ret;
+}
+
+int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
+{
+    int ret = -ENOSYS;
+#ifdef KVM_CAP_COALESCED_MMIO
+    KVMState *s = kvm_state;
+
+    if (s->coalesced_mmio) {
+        struct kvm_coalesced_mmio_zone zone;
+
+        zone.addr = start;
+        zone.size = size;
+
+        ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
+    }
+#endif
+
+    return ret;
+}
+
 int kvm_init(int smp_cpus)
 {
     KVMState *s;
@@ -167,6 +340,28 @@ int kvm_init(int smp_cpus)
         goto err;
     }
 
+    /* There was a nasty bug in < kvm-80 that prevents memory slots from being
+     * destroyed properly.  Since we rely on this capability, refuse to work
+     * with any kernel without this capability. */
+    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION,
+                    KVM_CAP_DESTROY_MEMORY_REGION_WORKS);
+    if (ret <= 0) {
+        if (ret == 0)
+            ret = -EINVAL;
+
+        fprintf(stderr,
+                "KVM kernel module broken (DESTROY_MEMORY_REGION)\n"
+                "Please upgrade to at least kvm-81.\n");
+        goto err;
+    }
+
+    s->coalesced_mmio = 0;
+#ifdef KVM_CAP_COALESCED_MMIO
+    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
+    if (ret > 0)
+        s->coalesced_mmio = ret;
+#endif
+
     ret = kvm_arch_init(s, smp_cpus);
     if (ret < 0)
         goto err;
@@ -226,6 +421,27 @@ static int kvm_handle_io(CPUState *env, uint16_t port, void *data,
     return 1;
 }
 
+static void kvm_run_coalesced_mmio(CPUState *env, struct kvm_run *run)
+{
+#ifdef KVM_CAP_COALESCED_MMIO
+    KVMState *s = kvm_state;
+    if (s->coalesced_mmio) {
+        struct kvm_coalesced_mmio_ring *ring;
+
+        ring = (void *)run + (s->coalesced_mmio * TARGET_PAGE_SIZE);
+        while (ring->first != ring->last) {
+            struct kvm_coalesced_mmio *ent;
+
+            ent = &ring->coalesced_mmio[ring->first];
+
+            cpu_physical_memory_write(ent->phys_addr, ent->data, ent->len);
+            /* FIXME smp_wmb() */
+            ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
+        }
+    }
+#endif
+}
+
 int kvm_cpu_exec(CPUState *env)
 {
     struct kvm_run *run = env->kvm_run;
@@ -256,6 +472,8 @@ int kvm_cpu_exec(CPUState *env)
             abort();
         }
 
+        kvm_run_coalesced_mmio(env, run);
+
         ret = 0; /* exit loop */
         switch (run->exit_reason) {
         case KVM_EXIT_IO:
@@ -324,32 +542,32 @@ void kvm_set_phys_mem(target_phys_addr_t start_addr,
     if (mem) {
         if ((flags == IO_MEM_UNASSIGNED) || (flags >= TLB_MMIO)) {
             mem->memory_size = 0;
-            mem->guest_phys_addr = start_addr;
-            mem->userspace_addr = 0;
+            mem->start_addr = start_addr;
+            mem->phys_offset = 0;
             mem->flags = 0;
 
-            kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, mem);
-        } else if (start_addr >= mem->guest_phys_addr &&
-                   (start_addr + size) <= (mem->guest_phys_addr +
+            kvm_set_user_memory_region(s, mem);
+        } else if (start_addr >= mem->start_addr &&
+                   (start_addr + size) <= (mem->start_addr +
                                            mem->memory_size)) {
             KVMSlot slot;
             target_phys_addr_t mem_start;
             ram_addr_t mem_size, mem_offset;
 
             /* Not splitting */
-            if ((phys_offset - (start_addr - mem->guest_phys_addr)) == 
-                ((uint8_t *)mem->userspace_addr - phys_ram_base))
+            if ((phys_offset - (start_addr - mem->start_addr)) == 
+                mem->phys_offset)
                 return;
 
             /* unregister whole slot */
             memcpy(&slot, mem, sizeof(slot));
             mem->memory_size = 0;
-            kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, mem);
+            kvm_set_user_memory_region(s, mem);
 
             /* register prefix slot */
-            mem_start = slot.guest_phys_addr;
-            mem_size = start_addr - slot.guest_phys_addr;
-            mem_offset = (uint8_t *)slot.userspace_addr - phys_ram_base;
+            mem_start = slot.start_addr;
+            mem_size = start_addr - slot.start_addr;
+            mem_offset = slot.phys_offset;
             if (mem_size)
                 kvm_set_phys_mem(mem_start, mem_size, mem_offset);
 
@@ -375,11 +593,11 @@ void kvm_set_phys_mem(target_phys_addr_t start_addr,
 
     mem = kvm_alloc_slot(s);
     mem->memory_size = size;
-    mem->guest_phys_addr = start_addr;
-    mem->userspace_addr = (unsigned long)(phys_ram_base + phys_offset);
+    mem->start_addr = start_addr;
+    mem->phys_offset = phys_offset;
     mem->flags = 0;
 
-    kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, mem);
+    kvm_set_user_memory_region(s, mem);
     /* FIXME deal with errors */
 }
 
@@ -433,3 +651,15 @@ int kvm_vcpu_ioctl(CPUState *env, int type, ...)
 
     return ret;
 }
+
+int kvm_has_sync_mmu(void)
+{
+#ifdef KVM_CAP_SYNC_MMU
+    KVMState *s = kvm_state;
+
+    if (kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_SYNC_MMU) > 0)
+        return 1;
+#endif
+
+    return 0;
+}