* 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.
#include "qemu-common.h"
#include "sysemu.h"
+#include "gdbstub.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
int flags;
} KVMSlot;
+typedef struct kvm_dirty_log KVMDirtyLog;
+
int kvm_allowed = 0;
struct KVMState
KVMSlot slots[32];
int fd;
int vmfd;
+ int coalesced_mmio;
+#ifdef KVM_CAP_SET_GUEST_DEBUG
+ struct kvm_sw_breakpoint_head kvm_sw_breakpoints;
+#endif
};
static KVMState *kvm_state;
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;
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);
+
+ 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;
return -EINVAL;
s = qemu_mallocz(sizeof(KVMState));
- if (s == NULL)
- return -ENOMEM;
+#ifdef KVM_CAP_SET_GUEST_DEBUG
+ TAILQ_INIT(&s->kvm_sw_breakpoints);
+#endif
for (i = 0; i < ARRAY_SIZE(s->slots); i++)
s->slots[i].slot = i;
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;
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;
do {
kvm_arch_pre_run(env, run);
- if ((env->interrupt_request & CPU_INTERRUPT_EXIT)) {
+ if (env->exit_request) {
dprintf("interrupt exit requested\n");
ret = 0;
break;
abort();
}
+ kvm_run_coalesced_mmio(env, run);
+
ret = 0; /* exit loop */
switch (run->exit_reason) {
case KVM_EXIT_IO:
break;
case KVM_EXIT_DEBUG:
dprintf("kvm_exit_debug\n");
+#ifdef KVM_CAP_SET_GUEST_DEBUG
+ if (kvm_arch_debug(&run->debug.arch)) {
+ gdb_set_stop_cpu(env);
+ vm_stop(EXCP_DEBUG);
+ env->exception_index = EXCP_DEBUG;
+ return 0;
+ }
+ /* re-enter, this exception was guest-internal */
+ ret = 1;
+#endif /* KVM_CAP_SET_GUEST_DEBUG */
break;
default:
dprintf("kvm_arch_handle_exit\n");
}
} while (ret > 0);
- if ((env->interrupt_request & CPU_INTERRUPT_EXIT)) {
- env->interrupt_request &= ~CPU_INTERRUPT_EXIT;
+ if (env->exit_request) {
+ env->exit_request = 0;
env->exception_index = EXCP_INTERRUPT;
}
return ret;
}
-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);
-}
-
void kvm_set_phys_mem(target_phys_addr_t start_addr,
ram_addr_t size,
ram_addr_t phys_offset)
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;
+}
+
+#ifdef KVM_CAP_SET_GUEST_DEBUG
+struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
+ target_ulong pc)
+{
+ struct kvm_sw_breakpoint *bp;
+
+ TAILQ_FOREACH(bp, &env->kvm_state->kvm_sw_breakpoints, entry) {
+ if (bp->pc == pc)
+ return bp;
+ }
+ return NULL;
+}
+
+int kvm_sw_breakpoints_active(CPUState *env)
+{
+ return !TAILQ_EMPTY(&env->kvm_state->kvm_sw_breakpoints);
+}
+
+int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
+{
+ struct kvm_guest_debug dbg;
+
+ dbg.control = 0;
+ if (env->singlestep_enabled)
+ dbg.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
+
+ kvm_arch_update_guest_debug(env, &dbg);
+ dbg.control |= reinject_trap;
+
+ return kvm_vcpu_ioctl(env, KVM_SET_GUEST_DEBUG, &dbg);
+}
+
+int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
+ target_ulong len, int type)
+{
+ struct kvm_sw_breakpoint *bp;
+ CPUState *env;
+ int err;
+
+ if (type == GDB_BREAKPOINT_SW) {
+ bp = kvm_find_sw_breakpoint(current_env, addr);
+ if (bp) {
+ bp->use_count++;
+ return 0;
+ }
+
+ bp = qemu_malloc(sizeof(struct kvm_sw_breakpoint));
+ if (!bp)
+ return -ENOMEM;
+
+ bp->pc = addr;
+ bp->use_count = 1;
+ err = kvm_arch_insert_sw_breakpoint(current_env, bp);
+ if (err) {
+ free(bp);
+ return err;
+ }
+
+ TAILQ_INSERT_HEAD(¤t_env->kvm_state->kvm_sw_breakpoints,
+ bp, entry);
+ } else {
+ err = kvm_arch_insert_hw_breakpoint(addr, len, type);
+ if (err)
+ return err;
+ }
+
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ err = kvm_update_guest_debug(env, 0);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
+ target_ulong len, int type)
+{
+ struct kvm_sw_breakpoint *bp;
+ CPUState *env;
+ int err;
+
+ if (type == GDB_BREAKPOINT_SW) {
+ bp = kvm_find_sw_breakpoint(current_env, addr);
+ if (!bp)
+ return -ENOENT;
+
+ if (bp->use_count > 1) {
+ bp->use_count--;
+ return 0;
+ }
+
+ err = kvm_arch_remove_sw_breakpoint(current_env, bp);
+ if (err)
+ return err;
+
+ TAILQ_REMOVE(¤t_env->kvm_state->kvm_sw_breakpoints, bp, entry);
+ qemu_free(bp);
+ } else {
+ err = kvm_arch_remove_hw_breakpoint(addr, len, type);
+ if (err)
+ return err;
+ }
+
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ err = kvm_update_guest_debug(env, 0);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+void kvm_remove_all_breakpoints(CPUState *current_env)
+{
+ struct kvm_sw_breakpoint *bp, *next;
+ KVMState *s = current_env->kvm_state;
+ CPUState *env;
+
+ TAILQ_FOREACH_SAFE(bp, &s->kvm_sw_breakpoints, entry, next) {
+ if (kvm_arch_remove_sw_breakpoint(current_env, bp) != 0) {
+ /* Try harder to find a CPU that currently sees the breakpoint. */
+ for (env = first_cpu; env != NULL; env = env->next_cpu) {
+ if (kvm_arch_remove_sw_breakpoint(env, bp) == 0)
+ break;
+ }
+ }
+ }
+ kvm_arch_remove_all_hw_breakpoints();
+
+ for (env = first_cpu; env != NULL; env = env->next_cpu)
+ kvm_update_guest_debug(env, 0);
+}
+
+#else /* !KVM_CAP_SET_GUEST_DEBUG */
+
+int kvm_update_guest_debug(CPUState *env, unsigned long reinject_trap)
+{
+ return -EINVAL;
+}
+
+int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr,
+ target_ulong len, int type)
+{
+ return -EINVAL;
+}
+
+int kvm_remove_breakpoint(CPUState *current_env, target_ulong addr,
+ target_ulong len, int type)
+{
+ return -EINVAL;
+}
+
+void kvm_remove_all_breakpoints(CPUState *current_env)
+{
+}
+#endif /* !KVM_CAP_SET_GUEST_DEBUG */
projects / qemu / blobdiff