#include "gdbstub.h"
#include "kvm.h"
#include "bswap.h"
+#include "memory.h"
+#include "exec-memory.h"
/* This check must be after config-host.h is included */
#ifdef CONFIG_EVENTFD
{
target_phys_addr_t start_addr;
ram_addr_t memory_size;
- ram_addr_t phys_offset;
+ void *ram;
int slot;
int flags;
} KVMSlot;
int vmfd;
int coalesced_mmio;
struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
+ bool coalesced_flush_in_progress;
int broken_set_mem_region;
int migration_log;
int vcpu_events;
int pit_in_kernel;
int xsave, xcrs;
int many_ioeventfds;
+ int irqchip_inject_ioctl;
+#ifdef KVM_CAP_IRQ_ROUTING
+ struct kvm_irq_routing *irq_routes;
+ int nr_allocated_irq_routes;
+ uint32_t *used_gsi_bitmap;
+ unsigned int max_gsi;
+#endif
};
-static KVMState *kvm_state;
+KVMState *kvm_state;
static const KVMCapabilityInfo kvm_required_capabilites[] = {
KVM_CAP_INFO(USER_MEMORY),
return found;
}
-int kvm_physical_memory_addr_from_ram(KVMState *s, ram_addr_t ram_addr,
- target_phys_addr_t *phys_addr)
+int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
+ target_phys_addr_t *phys_addr)
{
int i;
for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
KVMSlot *mem = &s->slots[i];
- if (ram_addr >= mem->phys_offset &&
- ram_addr < mem->phys_offset + mem->memory_size) {
- *phys_addr = mem->start_addr + (ram_addr - mem->phys_offset);
+ if (ram >= mem->ram && ram < mem->ram + mem->memory_size) {
+ *phys_addr = mem->start_addr + (ram - mem->ram);
return 1;
}
}
mem.slot = slot->slot;
mem.guest_phys_addr = slot->start_addr;
mem.memory_size = slot->memory_size;
- mem.userspace_addr = (unsigned long)qemu_safe_ram_ptr(slot->phys_offset);
+ mem.userspace_addr = (unsigned long)slot->ram;
mem.flags = slot->flags;
if (s->migration_log) {
mem.flags |= KVM_MEM_LOG_DIRTY_PAGES;
env->kvm_fd = ret;
env->kvm_state = s;
+ env->kvm_vcpu_dirty = 1;
mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
if (mmap_size < 0) {
/*
* dirty pages logging control
*/
-static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
- ram_addr_t size, int flags, int mask)
+
+static int kvm_mem_flags(KVMState *s, bool log_dirty)
+{
+ return log_dirty ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+}
+
+static int kvm_slot_dirty_pages_log_change(KVMSlot *mem, bool log_dirty)
{
KVMState *s = kvm_state;
- KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
+ int flags, mask = KVM_MEM_LOG_DIRTY_PAGES;
int old_flags;
- if (mem == NULL) {
- fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
- TARGET_FMT_plx "\n", __func__, phys_addr,
- (target_phys_addr_t)(phys_addr + size - 1));
- return -EINVAL;
- }
-
old_flags = mem->flags;
- flags = (mem->flags & ~mask) | flags;
+ flags = (mem->flags & ~mask) | kvm_mem_flags(s, log_dirty);
mem->flags = flags;
/* If nothing changed effectively, no need to issue ioctl */
if (s->migration_log) {
flags |= KVM_MEM_LOG_DIRTY_PAGES;
}
+
if (flags == old_flags) {
- return 0;
+ return 0;
}
return kvm_set_user_memory_region(s, mem);
}
-int kvm_log_start(target_phys_addr_t phys_addr, ram_addr_t size)
+static int kvm_dirty_pages_log_change(target_phys_addr_t phys_addr,
+ ram_addr_t size, bool log_dirty)
+{
+ KVMState *s = kvm_state;
+ KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
+
+ if (mem == NULL) {
+ fprintf(stderr, "BUG: %s: invalid parameters " TARGET_FMT_plx "-"
+ TARGET_FMT_plx "\n", __func__, phys_addr,
+ (target_phys_addr_t)(phys_addr + size - 1));
+ return -EINVAL;
+ }
+ return kvm_slot_dirty_pages_log_change(mem, log_dirty);
+}
+
+static void kvm_log_start(MemoryListener *listener,
+ MemoryRegionSection *section)
{
- return kvm_dirty_pages_log_change(phys_addr, size, KVM_MEM_LOG_DIRTY_PAGES,
- KVM_MEM_LOG_DIRTY_PAGES);
+ int r;
+
+ r = kvm_dirty_pages_log_change(section->offset_within_address_space,
+ section->size, true);
+ if (r < 0) {
+ abort();
+ }
}
-int kvm_log_stop(target_phys_addr_t phys_addr, ram_addr_t size)
+static void kvm_log_stop(MemoryListener *listener,
+ MemoryRegionSection *section)
{
- return kvm_dirty_pages_log_change(phys_addr, size, 0,
- KVM_MEM_LOG_DIRTY_PAGES);
+ int r;
+
+ r = kvm_dirty_pages_log_change(section->offset_within_address_space,
+ section->size, false);
+ if (r < 0) {
+ abort();
+ }
}
static int kvm_set_migration_log(int enable)
}
/* 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)
+static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section,
+ unsigned long *bitmap)
{
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;
+ unsigned long page_number, c;
+ target_phys_addr_t addr, addr1;
+ unsigned int len = ((section->size / TARGET_PAGE_SIZE) + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
/*
* bitmap-traveling is faster than memory-traveling (for addr...)
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);
+ addr = section->offset_within_region + addr1;
+ memory_region_set_dirty(section->mr, addr, TARGET_PAGE_SIZE);
} while (c != 0);
}
}
/**
* 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.
+ * This function updates qemu's dirty bitmap using
+ * memory_region_set_dirty(). This means all bits are set
+ * to dirty.
*
* @start_add: start of logged region.
* @end_addr: end of logged region.
*/
-static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
- target_phys_addr_t end_addr)
+static int kvm_physical_sync_dirty_bitmap(MemoryRegionSection *section)
{
KVMState *s = kvm_state;
unsigned long size, allocated_size = 0;
KVMDirtyLog d;
KVMSlot *mem;
int ret = 0;
+ target_phys_addr_t start_addr = section->offset_within_address_space;
+ target_phys_addr_t end_addr = start_addr + section->size;
d.dirty_bitmap = NULL;
while (start_addr < end_addr) {
break;
}
- size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS), HOST_LONG_BITS) / 8;
+ /* XXX bad kernel interface alert
+ * For dirty bitmap, kernel allocates array of size aligned to
+ * bits-per-long. But for case when the kernel is 64bits and
+ * the userspace is 32bits, userspace can't align to the same
+ * bits-per-long, since sizeof(long) is different between kernel
+ * and user space. This way, userspace will provide buffer which
+ * may be 4 bytes less than the kernel will use, resulting in
+ * userspace memory corruption (which is not detectable by valgrind
+ * too, in most cases).
+ * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
+ * a hope that sizeof(long) wont become >8 any time soon.
+ */
+ size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
+ /*HOST_LONG_BITS*/ 64) / 8;
if (!d.dirty_bitmap) {
- d.dirty_bitmap = qemu_malloc(size);
+ d.dirty_bitmap = g_malloc(size);
} else if (size > allocated_size) {
- d.dirty_bitmap = qemu_realloc(d.dirty_bitmap, size);
+ d.dirty_bitmap = g_realloc(d.dirty_bitmap, size);
}
allocated_size = size;
memset(d.dirty_bitmap, 0, allocated_size);
break;
}
- kvm_get_dirty_pages_log_range(mem->start_addr, d.dirty_bitmap,
- mem->start_addr, mem->memory_size);
+ kvm_get_dirty_pages_log_range(section, d.dirty_bitmap);
start_addr = mem->start_addr + mem->memory_size;
}
- qemu_free(d.dirty_bitmap);
+ g_free(d.dirty_bitmap);
return ret;
}
* Older kernels have a 6 device limit on the KVM io bus. Find out so we
* can avoid creating too many ioeventfds.
*/
-#if defined(CONFIG_EVENTFD) && defined(CONFIG_IOTHREAD)
+#if defined(CONFIG_EVENTFD)
int ioeventfds[7];
int i, ret = 0;
for (i = 0; i < ARRAY_SIZE(ioeventfds); i++) {
return NULL;
}
-static void kvm_set_phys_mem(target_phys_addr_t start_addr, ram_addr_t size,
- ram_addr_t phys_offset)
+static void kvm_set_phys_mem(MemoryRegionSection *section, bool add)
{
KVMState *s = kvm_state;
- ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
KVMSlot *mem, old;
int err;
+ MemoryRegion *mr = section->mr;
+ bool log_dirty = memory_region_is_logging(mr);
+ target_phys_addr_t start_addr = section->offset_within_address_space;
+ ram_addr_t size = section->size;
+ void *ram = NULL;
/* kvm works in page size chunks, but the function may be called
with sub-page size and unaligned start address. */
size = TARGET_PAGE_ALIGN(size);
start_addr = TARGET_PAGE_ALIGN(start_addr);
- /* KVM does not support read-only slots */
- phys_offset &= ~IO_MEM_ROM;
+ if (!memory_region_is_ram(mr)) {
+ return;
+ }
+
+ ram = memory_region_get_ram_ptr(mr) + section->offset_within_region;
while (1) {
mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
break;
}
- if (flags < IO_MEM_UNASSIGNED && start_addr >= mem->start_addr &&
+ if (add && start_addr >= mem->start_addr &&
(start_addr + size <= mem->start_addr + mem->memory_size) &&
- (phys_offset - start_addr == mem->phys_offset - mem->start_addr)) {
+ (ram - start_addr == mem->ram - mem->start_addr)) {
/* The new slot fits into the existing one and comes with
- * identical parameters - nothing to be done. */
+ * identical parameters - update flags and done. */
+ kvm_slot_dirty_pages_log_change(mem, log_dirty);
return;
}
old = *mem;
+ if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+ kvm_physical_sync_dirty_bitmap(section);
+ }
+
/* unregister the overlapping slot */
mem->memory_size = 0;
err = kvm_set_user_memory_region(s, mem);
* slot comes around later, we will fail (not seen in practice so far)
* - and actually require a recent KVM version. */
if (s->broken_set_mem_region &&
- old.start_addr == start_addr && old.memory_size < size &&
- flags < IO_MEM_UNASSIGNED) {
+ old.start_addr == start_addr && old.memory_size < size && add) {
mem = kvm_alloc_slot(s);
mem->memory_size = old.memory_size;
mem->start_addr = old.start_addr;
- mem->phys_offset = old.phys_offset;
- mem->flags = 0;
+ mem->ram = old.ram;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
}
start_addr += old.memory_size;
- phys_offset += old.memory_size;
+ ram += old.memory_size;
size -= old.memory_size;
continue;
}
mem = kvm_alloc_slot(s);
mem->memory_size = start_addr - old.start_addr;
mem->start_addr = old.start_addr;
- mem->phys_offset = old.phys_offset;
- mem->flags = 0;
+ mem->ram = old.ram;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
fprintf(stderr, "%s: error registering prefix slot: %s\n",
__func__, strerror(-err));
+#ifdef TARGET_PPC
+ fprintf(stderr, "%s: This is probably because your kernel's " \
+ "PAGE_SIZE is too big. Please try to use 4k " \
+ "PAGE_SIZE!\n", __func__);
+#endif
abort();
}
}
mem->start_addr = start_addr + size;
size_delta = mem->start_addr - old.start_addr;
mem->memory_size = old.memory_size - size_delta;
- mem->phys_offset = old.phys_offset + size_delta;
- mem->flags = 0;
+ mem->ram = old.ram + size_delta;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
if (!size) {
return;
}
- /* KVM does not need to know about this memory */
- if (flags >= IO_MEM_UNASSIGNED) {
+ if (!add) {
return;
}
mem = kvm_alloc_slot(s);
mem->memory_size = size;
mem->start_addr = start_addr;
- mem->phys_offset = phys_offset;
- mem->flags = 0;
+ mem->ram = ram;
+ mem->flags = kvm_mem_flags(s, log_dirty);
err = kvm_set_user_memory_region(s, mem);
if (err) {
}
}
-static void kvm_client_set_memory(struct CPUPhysMemoryClient *client,
- target_phys_addr_t start_addr,
- ram_addr_t size, ram_addr_t phys_offset)
+static void kvm_region_add(MemoryListener *listener,
+ MemoryRegionSection *section)
{
- kvm_set_phys_mem(start_addr, size, phys_offset);
+ kvm_set_phys_mem(section, true);
}
-static int kvm_client_sync_dirty_bitmap(struct CPUPhysMemoryClient *client,
- target_phys_addr_t start_addr,
- target_phys_addr_t end_addr)
+static void kvm_region_del(MemoryListener *listener,
+ MemoryRegionSection *section)
{
- return kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
+ kvm_set_phys_mem(section, false);
}
-static int kvm_client_migration_log(struct CPUPhysMemoryClient *client,
- int enable)
+static void kvm_log_sync(MemoryListener *listener,
+ MemoryRegionSection *section)
{
- return kvm_set_migration_log(enable);
+ int r;
+
+ r = kvm_physical_sync_dirty_bitmap(section);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_log_global_start(struct MemoryListener *listener)
+{
+ int r;
+
+ r = kvm_set_migration_log(1);
+ assert(r >= 0);
}
-static CPUPhysMemoryClient kvm_cpu_phys_memory_client = {
- .set_memory = kvm_client_set_memory,
- .sync_dirty_bitmap = kvm_client_sync_dirty_bitmap,
- .migration_log = kvm_client_migration_log,
+static void kvm_log_global_stop(struct MemoryListener *listener)
+{
+ int r;
+
+ r = kvm_set_migration_log(0);
+ assert(r >= 0);
+}
+
+static void kvm_mem_ioeventfd_add(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ int r;
+
+ assert(match_data && section->size == 4);
+
+ r = kvm_set_ioeventfd_mmio_long(fd, section->offset_within_address_space,
+ data, true);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_mem_ioeventfd_del(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ int r;
+
+ r = kvm_set_ioeventfd_mmio_long(fd, section->offset_within_address_space,
+ data, false);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_io_ioeventfd_add(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ int r;
+
+ assert(match_data && section->size == 2);
+
+ r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
+ data, true);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_io_ioeventfd_del(MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+
+{
+ int r;
+
+ r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
+ data, false);
+ if (r < 0) {
+ abort();
+ }
+}
+
+static void kvm_eventfd_add(MemoryListener *listener,
+ MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ if (section->address_space == get_system_memory()) {
+ kvm_mem_ioeventfd_add(section, match_data, data, fd);
+ } else {
+ kvm_io_ioeventfd_add(section, match_data, data, fd);
+ }
+}
+
+static void kvm_eventfd_del(MemoryListener *listener,
+ MemoryRegionSection *section,
+ bool match_data, uint64_t data, int fd)
+{
+ if (section->address_space == get_system_memory()) {
+ kvm_mem_ioeventfd_del(section, match_data, data, fd);
+ } else {
+ kvm_io_ioeventfd_del(section, match_data, data, fd);
+ }
+}
+
+static MemoryListener kvm_memory_listener = {
+ .region_add = kvm_region_add,
+ .region_del = kvm_region_del,
+ .log_start = kvm_log_start,
+ .log_stop = kvm_log_stop,
+ .log_sync = kvm_log_sync,
+ .log_global_start = kvm_log_global_start,
+ .log_global_stop = kvm_log_global_stop,
+ .eventfd_add = kvm_eventfd_add,
+ .eventfd_del = kvm_eventfd_del,
+ .priority = 10,
};
+static void kvm_handle_interrupt(CPUState *env, int mask)
+{
+ env->interrupt_request |= mask;
+
+ if (!qemu_cpu_is_self(env)) {
+ qemu_cpu_kick(env);
+ }
+}
+
+int kvm_irqchip_set_irq(KVMState *s, int irq, int level)
+{
+ struct kvm_irq_level event;
+ int ret;
+
+ assert(s->irqchip_in_kernel);
+
+ event.level = level;
+ event.irq = irq;
+ ret = kvm_vm_ioctl(s, s->irqchip_inject_ioctl, &event);
+ if (ret < 0) {
+ perror("kvm_set_irqchip_line");
+ abort();
+ }
+
+ return (s->irqchip_inject_ioctl == KVM_IRQ_LINE) ? 1 : event.status;
+}
+
+#ifdef KVM_CAP_IRQ_ROUTING
+static void set_gsi(KVMState *s, unsigned int gsi)
+{
+ assert(gsi < s->max_gsi);
+
+ s->used_gsi_bitmap[gsi / 32] |= 1U << (gsi % 32);
+}
+
+static void kvm_init_irq_routing(KVMState *s)
+{
+ int gsi_count;
+
+ gsi_count = kvm_check_extension(s, KVM_CAP_IRQ_ROUTING);
+ if (gsi_count > 0) {
+ unsigned int gsi_bits, i;
+
+ /* Round up so we can search ints using ffs */
+ gsi_bits = (gsi_count + 31) / 32;
+ s->used_gsi_bitmap = g_malloc0(gsi_bits / 8);
+ s->max_gsi = gsi_bits;
+
+ /* Mark any over-allocated bits as already in use */
+ for (i = gsi_count; i < gsi_bits; i++) {
+ set_gsi(s, i);
+ }
+ }
+
+ s->irq_routes = g_malloc0(sizeof(*s->irq_routes));
+ s->nr_allocated_irq_routes = 0;
+
+ kvm_arch_init_irq_routing(s);
+}
+
+static void kvm_add_routing_entry(KVMState *s,
+ struct kvm_irq_routing_entry *entry)
+{
+ struct kvm_irq_routing_entry *new;
+ int n, size;
+
+ if (s->irq_routes->nr == s->nr_allocated_irq_routes) {
+ n = s->nr_allocated_irq_routes * 2;
+ if (n < 64) {
+ n = 64;
+ }
+ size = sizeof(struct kvm_irq_routing);
+ size += n * sizeof(*new);
+ s->irq_routes = g_realloc(s->irq_routes, size);
+ s->nr_allocated_irq_routes = n;
+ }
+ n = s->irq_routes->nr++;
+ new = &s->irq_routes->entries[n];
+ memset(new, 0, sizeof(*new));
+ new->gsi = entry->gsi;
+ new->type = entry->type;
+ new->flags = entry->flags;
+ new->u = entry->u;
+
+ set_gsi(s, entry->gsi);
+}
+
+void kvm_irqchip_add_route(KVMState *s, int irq, int irqchip, int pin)
+{
+ struct kvm_irq_routing_entry e;
+
+ e.gsi = irq;
+ e.type = KVM_IRQ_ROUTING_IRQCHIP;
+ e.flags = 0;
+ e.u.irqchip.irqchip = irqchip;
+ e.u.irqchip.pin = pin;
+ kvm_add_routing_entry(s, &e);
+}
+
+int kvm_irqchip_commit_routes(KVMState *s)
+{
+ s->irq_routes->flags = 0;
+ return kvm_vm_ioctl(s, KVM_SET_GSI_ROUTING, s->irq_routes);
+}
+
+#else /* !KVM_CAP_IRQ_ROUTING */
+
+static void kvm_init_irq_routing(KVMState *s)
+{
+}
+#endif /* !KVM_CAP_IRQ_ROUTING */
+
+static int kvm_irqchip_create(KVMState *s)
+{
+ QemuOptsList *list = qemu_find_opts("machine");
+ int ret;
+
+ if (QTAILQ_EMPTY(&list->head) ||
+ !qemu_opt_get_bool(QTAILQ_FIRST(&list->head),
+ "kernel_irqchip", false) ||
+ !kvm_check_extension(s, KVM_CAP_IRQCHIP)) {
+ return 0;
+ }
+
+ ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP);
+ if (ret < 0) {
+ fprintf(stderr, "Create kernel irqchip failed\n");
+ return ret;
+ }
+
+ s->irqchip_inject_ioctl = KVM_IRQ_LINE;
+ if (kvm_check_extension(s, KVM_CAP_IRQ_INJECT_STATUS)) {
+ s->irqchip_inject_ioctl = KVM_IRQ_LINE_STATUS;
+ }
+ s->irqchip_in_kernel = 1;
+
+ kvm_init_irq_routing(s);
+
+ return 0;
+}
+
int kvm_init(void)
{
static const char upgrade_note[] =
int ret;
int i;
- s = qemu_mallocz(sizeof(KVMState));
+ s = g_malloc0(sizeof(KVMState));
#ifdef KVM_CAP_SET_GUEST_DEBUG
QTAILQ_INIT(&s->kvm_sw_breakpoints);
fprintf(stderr, "Please add the 'switch_amode' kernel parameter to "
"your host kernel command line\n");
#endif
+ ret = s->vmfd;
goto err;
}
s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
s->broken_set_mem_region = 1;
-#ifdef KVM_CAP_JOIN_MEMORY_REGIONS_WORKS
ret = kvm_check_extension(s, KVM_CAP_JOIN_MEMORY_REGIONS_WORKS);
if (ret > 0) {
s->broken_set_mem_region = 0;
}
-#endif
- s->vcpu_events = 0;
#ifdef KVM_CAP_VCPU_EVENTS
s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS);
#endif
- s->robust_singlestep = 0;
-#ifdef KVM_CAP_X86_ROBUST_SINGLESTEP
s->robust_singlestep =
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
- s->xsave = 0;
#ifdef KVM_CAP_XSAVE
s->xsave = kvm_check_extension(s, KVM_CAP_XSAVE);
#endif
- s->xcrs = 0;
#ifdef KVM_CAP_XCRS
s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
#endif
goto err;
}
+ ret = kvm_irqchip_create(s);
+ if (ret < 0) {
+ goto err;
+ }
+
kvm_state = s;
- cpu_register_phys_memory_client(&kvm_cpu_phys_memory_client);
+ memory_listener_register(&kvm_memory_listener);
s->many_ioeventfds = kvm_check_many_ioeventfds();
+ cpu_interrupt_handler = kvm_handle_interrupt;
+
return 0;
err:
if (s) {
- if (s->vmfd != -1) {
+ if (s->vmfd >= 0) {
close(s->vmfd);
}
if (s->fd != -1) {
close(s->fd);
}
}
- qemu_free(s);
+ g_free(s);
return ret;
}
}
}
-#ifdef KVM_CAP_INTERNAL_ERROR_DATA
static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
{
fprintf(stderr, "KVM internal error.");
fprintf(stderr, "emulation failure\n");
if (!kvm_arch_stop_on_emulation_error(env)) {
cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
- return 0;
+ return EXCP_INTERRUPT;
}
}
/* FIXME: Should trigger a qmp message to let management know
*/
return -1;
}
-#endif
void kvm_flush_coalesced_mmio_buffer(void)
{
KVMState *s = kvm_state;
+
+ if (s->coalesced_flush_in_progress) {
+ return;
+ }
+
+ s->coalesced_flush_in_progress = true;
+
if (s->coalesced_mmio_ring) {
struct kvm_coalesced_mmio_ring *ring = s->coalesced_mmio_ring;
while (ring->first != ring->last) {
ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
}
}
+
+ s->coalesced_flush_in_progress = false;
}
static void do_kvm_cpu_synchronize_state(void *_env)
int kvm_cpu_exec(CPUState *env)
{
struct kvm_run *run = env->kvm_run;
- int ret;
+ int ret, run_ret;
DPRINTF("kvm_cpu_exec()\n");
- if (kvm_arch_process_irqchip_events(env)) {
+ if (kvm_arch_process_async_events(env)) {
env->exit_request = 0;
return EXCP_HLT;
}
cpu_single_env = NULL;
qemu_mutex_unlock_iothread();
- ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
+ run_ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
qemu_mutex_lock_iothread();
cpu_single_env = env;
kvm_flush_coalesced_mmio_buffer();
- if (ret == -EINTR || ret == -EAGAIN) {
- DPRINTF("io window exit\n");
- ret = 0;
- break;
- }
-
- if (ret < 0) {
- DPRINTF("kvm run failed %s\n", strerror(-ret));
+ if (run_ret < 0) {
+ if (run_ret == -EINTR || run_ret == -EAGAIN) {
+ DPRINTF("io window exit\n");
+ ret = EXCP_INTERRUPT;
+ break;
+ }
+ fprintf(stderr, "error: kvm run failed %s\n",
+ strerror(-run_ret));
abort();
}
- ret = 0; /* exit loop */
switch (run->exit_reason) {
case KVM_EXIT_IO:
DPRINTF("handle_io\n");
run->io.direction,
run->io.size,
run->io.count);
- ret = 1;
+ ret = 0;
break;
case KVM_EXIT_MMIO:
DPRINTF("handle_mmio\n");
run->mmio.data,
run->mmio.len,
run->mmio.is_write);
- ret = 1;
+ ret = 0;
break;
case KVM_EXIT_IRQ_WINDOW_OPEN:
DPRINTF("irq_window_open\n");
+ ret = EXCP_INTERRUPT;
break;
case KVM_EXIT_SHUTDOWN:
DPRINTF("shutdown\n");
qemu_system_reset_request();
+ ret = EXCP_INTERRUPT;
break;
case KVM_EXIT_UNKNOWN:
fprintf(stderr, "KVM: unknown exit, hardware reason %" PRIx64 "\n",
(uint64_t)run->hw.hardware_exit_reason);
ret = -1;
break;
-#ifdef KVM_CAP_INTERNAL_ERROR_DATA
case KVM_EXIT_INTERNAL_ERROR:
ret = kvm_handle_internal_error(env, run);
break;
-#endif
- case KVM_EXIT_DEBUG:
- DPRINTF("kvm_exit_debug\n");
-#ifdef KVM_CAP_SET_GUEST_DEBUG
- if (kvm_arch_debug(&run->debug.arch)) {
- ret = EXCP_DEBUG;
- goto out;
- }
- /* re-enter, this exception was guest-internal */
- ret = 1;
-#endif /* KVM_CAP_SET_GUEST_DEBUG */
- break;
default:
DPRINTF("kvm_arch_handle_exit\n");
ret = kvm_arch_handle_exit(env, run);
break;
}
- } while (ret > 0);
+ } while (ret == 0);
if (ret < 0) {
cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
- vm_stop(VMSTOP_PANIC);
+ vm_stop(RUN_STATE_INTERNAL_ERROR);
}
- ret = EXCP_INTERRUPT;
-out:
env->exit_request = 0;
cpu_single_env = NULL;
return ret;
return kvm_state->many_ioeventfds;
}
+int kvm_has_gsi_routing(void)
+{
+#ifdef KVM_CAP_IRQ_ROUTING
+ return kvm_check_extension(kvm_state, KVM_CAP_IRQ_ROUTING);
+#else
+ return false;
+#endif
+}
+
+int kvm_allows_irq0_override(void)
+{
+ return !kvm_enabled() || !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
+}
+
void kvm_setup_guest_memory(void *start, size_t size)
{
if (!kvm_has_sync_mmu()) {
return 0;
}
- bp = qemu_malloc(sizeof(struct kvm_sw_breakpoint));
+ bp = g_malloc(sizeof(struct kvm_sw_breakpoint));
if (!bp) {
return -ENOMEM;
}
bp->use_count = 1;
err = kvm_arch_insert_sw_breakpoint(current_env, bp);
if (err) {
- free(bp);
+ g_free(bp);
return err;
}
}
QTAILQ_REMOVE(¤t_env->kvm_state->kvm_sw_breakpoints, bp, entry);
- qemu_free(bp);
+ g_free(bp);
} else {
err = kvm_arch_remove_hw_breakpoint(addr, len, type);
if (err) {
return kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, NULL);
}
- sigmask = qemu_malloc(sizeof(*sigmask) + sizeof(*sigset));
+ sigmask = g_malloc(sizeof(*sigmask) + sizeof(*sigset));
sigmask->len = 8;
memcpy(sigmask->sigset, sigset, sizeof(*sigset));
r = kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, sigmask);
- free(sigmask);
+ g_free(sigmask);
return r;
}
int kvm_set_ioeventfd_mmio_long(int fd, uint32_t addr, uint32_t val, bool assign)
{
-#ifdef KVM_IOEVENTFD
int ret;
struct kvm_ioeventfd iofd;
}
return 0;
-#else
- return -ENOSYS;
-#endif
}
int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
{
-#ifdef KVM_IOEVENTFD
struct kvm_ioeventfd kick = {
.datamatch = val,
.addr = addr,
return r;
}
return 0;
-#else
- return -ENOSYS;
-#endif
}
int kvm_on_sigbus_vcpu(CPUState *env, int code, void *addr)
projects / qemu.git / blobdiff