#endif
#include "exec/cpu-all.h"
#include "qemu/rcu_queue.h"
-#include "exec/cputlb.h"
+#include "qemu/main-loop.h"
#include "translate-all.h"
#include "exec/memory-internal.h"
*/
#define RAM_RESIZEABLE (1 << 2)
+/* An extra page is mapped on top of this RAM.
+ */
+#define RAM_EXTRA (1 << 3)
#endif
struct CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus);
/* current CPU in the current thread. It is only valid inside
cpu_exec() */
-DEFINE_TLS(CPUState *, current_cpu);
+__thread CPUState *current_cpu;
/* 0 = Do not count executed instructions.
1 = Precise instruction counting.
2 = Adaptive rate instruction counting. */
*xlat = addr + section->offset_within_region;
mr = section->mr;
+
+ /* MMIO registers can be expected to perform full-width accesses based only
+ * on their address, without considering adjacent registers that could
+ * decode to completely different MemoryRegions. When such registers
+ * exist (e.g. I/O ports 0xcf8 and 0xcf9 on most PC chipsets), MMIO
+ * regions overlap wildly. For this reason we cannot clamp the accesses
+ * here.
+ *
+ * If the length is small (as is the case for address_space_ldl/stl),
+ * everything works fine. If the incoming length is large, however,
+ * the caller really has to do the clamping through memory_access_size.
+ */
if (memory_region_is_ram(mr)) {
diff = int128_sub(section->size, int128_make64(addr));
*plen = int128_get64(int128_min(diff, int128_make64(*plen)));
}
};
+static bool cpu_common_crash_occurred_needed(void *opaque)
+{
+ CPUState *cpu = opaque;
+
+ return cpu->crash_occurred;
+}
+
+static const VMStateDescription vmstate_cpu_common_crash_occurred = {
+ .name = "cpu_common/crash_occurred",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = cpu_common_crash_occurred_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_BOOL(crash_occurred, CPUState),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
const VMStateDescription vmstate_cpu_common = {
.name = "cpu_common",
.version_id = 1,
},
.subsections = (const VMStateDescription*[]) {
&vmstate_cpu_common_exception_index,
+ &vmstate_cpu_common_crash_occurred,
NULL
}
};
}
#endif
-void cpu_exec_init(CPUArchState *env)
+#ifndef CONFIG_USER_ONLY
+static DECLARE_BITMAP(cpu_index_map, MAX_CPUMASK_BITS);
+
+static int cpu_get_free_index(Error **errp)
+{
+ int cpu = find_first_zero_bit(cpu_index_map, MAX_CPUMASK_BITS);
+
+ if (cpu >= MAX_CPUMASK_BITS) {
+ error_setg(errp, "Trying to use more CPUs than max of %d",
+ MAX_CPUMASK_BITS);
+ return -1;
+ }
+
+ bitmap_set(cpu_index_map, cpu, 1);
+ return cpu;
+}
+
+void cpu_exec_exit(CPUState *cpu)
+{
+ if (cpu->cpu_index == -1) {
+ /* cpu_index was never allocated by this @cpu or was already freed. */
+ return;
+ }
+
+ bitmap_clear(cpu_index_map, cpu->cpu_index, 1);
+ cpu->cpu_index = -1;
+}
+#else
+
+static int cpu_get_free_index(Error **errp)
{
- CPUState *cpu = ENV_GET_CPU(env);
- CPUClass *cc = CPU_GET_CLASS(cpu);
CPUState *some_cpu;
- int cpu_index;
+ int cpu_index = 0;
-#if defined(CONFIG_USER_ONLY)
- cpu_list_lock();
-#endif
- cpu_index = 0;
CPU_FOREACH(some_cpu) {
cpu_index++;
}
- cpu->cpu_index = cpu_index;
- cpu->numa_node = 0;
- QTAILQ_INIT(&cpu->breakpoints);
- QTAILQ_INIT(&cpu->watchpoints);
+ return cpu_index;
+}
+
+void cpu_exec_exit(CPUState *cpu)
+{
+}
+#endif
+
+void cpu_exec_init(CPUState *cpu, Error **errp)
+{
+ CPUClass *cc = CPU_GET_CLASS(cpu);
+ int cpu_index;
+ Error *local_err = NULL;
+
#ifndef CONFIG_USER_ONLY
cpu->as = &address_space_memory;
cpu->thread_id = qemu_get_thread_id();
cpu_reload_memory_map(cpu);
#endif
+
+#if defined(CONFIG_USER_ONLY)
+ cpu_list_lock();
+#endif
+ cpu_index = cpu->cpu_index = cpu_get_free_index(&local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+#if defined(CONFIG_USER_ONLY)
+ cpu_list_unlock();
+#endif
+ return;
+ }
QTAILQ_INSERT_TAIL(&cpus, cpu, node);
#if defined(CONFIG_USER_ONLY)
cpu_list_unlock();
}
#if defined(CPU_SAVE_VERSION) && !defined(CONFIG_USER_ONLY)
register_savevm(NULL, "cpu", cpu_index, CPU_SAVE_VERSION,
- cpu_save, cpu_load, env);
+ cpu_save, cpu_load, cpu->env_ptr);
assert(cc->vmsd == NULL);
assert(qdev_get_vmsd(DEVICE(cpu)) == NULL);
#endif
} else {
/* must flush all the translated code to avoid inconsistencies */
/* XXX: only flush what is necessary */
- CPUArchState *env = cpu->env_ptr;
- tb_flush(env);
+ tb_flush(cpu);
}
}
}
static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length)
{
+ CPUState *cpu;
ram_addr_t start1;
RAMBlock *block;
ram_addr_t end;
block = qemu_get_ram_block(start);
assert(block == qemu_get_ram_block(end - 1));
start1 = (uintptr_t)ramblock_ptr(block, start - block->offset);
- cpu_tlb_reset_dirty_all(start1, length);
+ CPU_FOREACH(cpu) {
+ tlb_reset_dirty(cpu, start1, length);
+ }
rcu_read_unlock();
}
iotlb |= PHYS_SECTION_ROM;
}
} else {
- iotlb = section - section->address_space->dispatch->map.sections;
+ AddressSpaceDispatch *d;
+
+ d = atomic_rcu_read(§ion->address_space->dispatch);
+ iotlb = section - d->map.sections;
iotlb += xlat;
}
char *filename;
char *sanitized_name;
char *c;
+ void *ptr;
void *area = NULL;
int fd;
uint64_t hpagesize;
+ uint64_t total;
Error *local_err = NULL;
+ size_t offset;
hpagesize = gethugepagesize(path, &local_err);
if (local_err) {
unlink(filename);
g_free(filename);
- memory = (memory+hpagesize-1) & ~(hpagesize-1);
+ memory = ROUND_UP(memory, hpagesize);
+ total = memory + hpagesize;
/*
* ftruncate is not supported by hugetlbfs in older
perror("ftruncate");
}
- area = mmap(0, memory, PROT_READ | PROT_WRITE,
- (block->flags & RAM_SHARED ? MAP_SHARED : MAP_PRIVATE),
+ ptr = mmap(0, total, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS,
+ -1, 0);
+ if (ptr == MAP_FAILED) {
+ error_setg_errno(errp, errno,
+ "unable to allocate memory range for hugepages");
+ close(fd);
+ goto error;
+ }
+
+ offset = QEMU_ALIGN_UP((uintptr_t)ptr, hpagesize) - (uintptr_t)ptr;
+
+ area = mmap(ptr + offset, memory, PROT_READ | PROT_WRITE,
+ (block->flags & RAM_SHARED ? MAP_SHARED : MAP_PRIVATE) |
+ MAP_FIXED,
fd, 0);
if (area == MAP_FAILED) {
error_setg_errno(errp, errno,
"unable to map backing store for hugepages");
+ munmap(ptr, total);
close(fd);
goto error;
}
+ if (offset > 0) {
+ munmap(ptr, offset);
+ }
+ ptr += offset;
+ total -= offset;
+
+ if (total > memory + getpagesize()) {
+ munmap(ptr + memory + getpagesize(),
+ total - memory - getpagesize());
+ }
+
if (mem_prealloc) {
os_mem_prealloc(fd, area, memory);
}
}
}
+ new_ram_size = MAX(old_ram_size,
+ (new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS);
+ if (new_ram_size > old_ram_size) {
+ migration_bitmap_extend(old_ram_size, new_ram_size);
+ }
/* Keep the list sorted from biggest to smallest block. Unlike QTAILQ,
* QLIST (which has an RCU-friendly variant) does not have insertion at
* tail, so save the last element in last_block.
new_block->used_length = size;
new_block->max_length = size;
new_block->flags = share ? RAM_SHARED : 0;
+ new_block->flags |= RAM_EXTRA;
new_block->host = file_ram_alloc(new_block, size,
mem_path, errp);
if (!new_block->host) {
xen_invalidate_map_cache_entry(block->host);
#ifndef _WIN32
} else if (block->fd >= 0) {
- munmap(block->host, block->max_length);
+ if (block->flags & RAM_EXTRA) {
+ munmap(block->host, block->max_length + getpagesize());
+ } else {
+ munmap(block->host, block->max_length);
+ }
close(block->fd);
#endif
} else {
/* we remove the notdirty callback only if the code has been
flushed */
if (!cpu_physical_memory_is_clean(ram_addr)) {
- CPUArchState *env = current_cpu->env_ptr;
- tlb_set_dirty(env, current_cpu->mem_io_vaddr);
+ tlb_set_dirty(current_cpu, current_cpu->mem_io_vaddr);
}
}
if (l > access_size_max) {
l = access_size_max;
}
- if (l & (l - 1)) {
- l = 1 << (qemu_fls(l) - 1);
- }
+ l = pow2floor(l);
return l;
}
+static bool prepare_mmio_access(MemoryRegion *mr)
+{
+ bool unlocked = !qemu_mutex_iothread_locked();
+ bool release_lock = false;
+
+ if (unlocked && mr->global_locking) {
+ qemu_mutex_lock_iothread();
+ unlocked = false;
+ release_lock = true;
+ }
+ if (mr->flush_coalesced_mmio) {
+ if (unlocked) {
+ qemu_mutex_lock_iothread();
+ }
+ qemu_flush_coalesced_mmio_buffer();
+ if (unlocked) {
+ qemu_mutex_unlock_iothread();
+ }
+ }
+
+ return release_lock;
+}
+
MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
uint8_t *buf, int len, bool is_write)
{
hwaddr addr1;
MemoryRegion *mr;
MemTxResult result = MEMTX_OK;
+ bool release_lock = false;
rcu_read_lock();
while (len > 0) {
if (is_write) {
if (!memory_access_is_direct(mr, is_write)) {
+ release_lock |= prepare_mmio_access(mr);
l = memory_access_size(mr, l, addr1);
/* XXX: could force current_cpu to NULL to avoid
potential bugs */
} else {
if (!memory_access_is_direct(mr, is_write)) {
/* I/O case */
+ release_lock |= prepare_mmio_access(mr);
l = memory_access_size(mr, l, addr1);
switch (l) {
case 8:
memcpy(buf, ptr, l);
}
}
+
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ release_lock = false;
+ }
+
len -= l;
buf += l;
addr += l;
if (!(memory_region_is_ram(mr) ||
memory_region_is_romd(mr))) {
- /* do nothing */
+ l = memory_access_size(mr, l, addr1);
} else {
addr1 += memory_region_get_ram_addr(mr);
/* ROM/RAM case */
hwaddr l = 4;
hwaddr addr1;
MemTxResult r;
+ bool release_lock = false;
rcu_read_lock();
mr = address_space_translate(as, addr, &addr1, &l, false);
if (l < 4 || !memory_access_is_direct(mr, false)) {
+ release_lock |= prepare_mmio_access(mr);
+
/* I/O case */
r = memory_region_dispatch_read(mr, addr1, &val, 4, attrs);
#if defined(TARGET_WORDS_BIGENDIAN)
if (result) {
*result = r;
}
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ }
rcu_read_unlock();
return val;
}
hwaddr l = 8;
hwaddr addr1;
MemTxResult r;
+ bool release_lock = false;
rcu_read_lock();
mr = address_space_translate(as, addr, &addr1, &l,
false);
if (l < 8 || !memory_access_is_direct(mr, false)) {
+ release_lock |= prepare_mmio_access(mr);
+
/* I/O case */
r = memory_region_dispatch_read(mr, addr1, &val, 8, attrs);
#if defined(TARGET_WORDS_BIGENDIAN)
if (result) {
*result = r;
}
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ }
rcu_read_unlock();
return val;
}
hwaddr l = 2;
hwaddr addr1;
MemTxResult r;
+ bool release_lock = false;
rcu_read_lock();
mr = address_space_translate(as, addr, &addr1, &l,
false);
if (l < 2 || !memory_access_is_direct(mr, false)) {
+ release_lock |= prepare_mmio_access(mr);
+
/* I/O case */
r = memory_region_dispatch_read(mr, addr1, &val, 2, attrs);
#if defined(TARGET_WORDS_BIGENDIAN)
if (result) {
*result = r;
}
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ }
rcu_read_unlock();
return val;
}
hwaddr addr1;
MemTxResult r;
uint8_t dirty_log_mask;
+ bool release_lock = false;
rcu_read_lock();
mr = address_space_translate(as, addr, &addr1, &l,
true);
if (l < 4 || !memory_access_is_direct(mr, true)) {
+ release_lock |= prepare_mmio_access(mr);
+
r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
} else {
addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
if (result) {
*result = r;
}
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ }
rcu_read_unlock();
}
hwaddr l = 4;
hwaddr addr1;
MemTxResult r;
+ bool release_lock = false;
rcu_read_lock();
mr = address_space_translate(as, addr, &addr1, &l,
true);
if (l < 4 || !memory_access_is_direct(mr, true)) {
+ release_lock |= prepare_mmio_access(mr);
+
#if defined(TARGET_WORDS_BIGENDIAN)
if (endian == DEVICE_LITTLE_ENDIAN) {
val = bswap32(val);
if (result) {
*result = r;
}
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ }
rcu_read_unlock();
}
hwaddr l = 2;
hwaddr addr1;
MemTxResult r;
+ bool release_lock = false;
rcu_read_lock();
mr = address_space_translate(as, addr, &addr1, &l, true);
if (l < 2 || !memory_access_is_direct(mr, true)) {
+ release_lock |= prepare_mmio_access(mr);
+
#if defined(TARGET_WORDS_BIGENDIAN)
if (endian == DEVICE_LITTLE_ENDIAN) {
val = bswap16(val);
if (result) {
*result = r;
}
+ if (release_lock) {
+ qemu_mutex_unlock_iothread();
+ }
rcu_read_unlock();
}