#include "exec/memory-internal.h"
+#include "qemu/range.h"
+
//#define DEBUG_SUBPAGE
#if !defined(CONFIG_USER_ONLY)
#endif
-CPUState *first_cpu;
+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);
typedef struct PhysPageEntry PhysPageEntry;
struct PhysPageEntry {
- uint16_t is_leaf : 1;
- /* index into phys_sections (is_leaf) or phys_map_nodes (!is_leaf) */
- uint16_t ptr : 15;
+ /* How many bits skip to next level (in units of L2_SIZE). 0 for a leaf. */
+ uint32_t skip : 6;
+ /* index into phys_sections (!skip) or phys_map_nodes (skip) */
+ uint32_t ptr : 26;
};
-typedef PhysPageEntry Node[L2_SIZE];
+#define PHYS_MAP_NODE_NIL (((uint32_t)~0) >> 6)
+
+/* Size of the L2 (and L3, etc) page tables. */
+#define ADDR_SPACE_BITS 64
+
+#define P_L2_BITS 9
+#define P_L2_SIZE (1 << P_L2_BITS)
+
+#define P_L2_LEVELS (((ADDR_SPACE_BITS - TARGET_PAGE_BITS - 1) / P_L2_BITS) + 1)
+
+typedef PhysPageEntry Node[P_L2_SIZE];
+
+typedef struct PhysPageMap {
+ unsigned sections_nb;
+ unsigned sections_nb_alloc;
+ unsigned nodes_nb;
+ unsigned nodes_nb_alloc;
+ Node *nodes;
+ MemoryRegionSection *sections;
+} PhysPageMap;
struct AddressSpaceDispatch {
/* This is a multi-level map on the physical address space.
* The bottom level has pointers to MemoryRegionSections.
*/
PhysPageEntry phys_map;
- Node *nodes;
- MemoryRegionSection *sections;
+ PhysPageMap map;
AddressSpace *as;
};
#define PHYS_SECTION_ROM 2
#define PHYS_SECTION_WATCH 3
-typedef struct PhysPageMap {
- unsigned sections_nb;
- unsigned sections_nb_alloc;
- unsigned nodes_nb;
- unsigned nodes_nb_alloc;
- Node *nodes;
- MemoryRegionSection *sections;
-} PhysPageMap;
-
-static PhysPageMap *prev_map;
-static PhysPageMap next_map;
-
-#define PHYS_MAP_NODE_NIL (((uint16_t)~0) >> 1)
-
static void io_mem_init(void);
static void memory_map_init(void);
-static void *qemu_safe_ram_ptr(ram_addr_t addr);
static MemoryRegion io_mem_watch;
#endif
#if !defined(CONFIG_USER_ONLY)
-static void phys_map_node_reserve(unsigned nodes)
+static void phys_map_node_reserve(PhysPageMap *map, unsigned nodes)
{
- if (next_map.nodes_nb + nodes > next_map.nodes_nb_alloc) {
- next_map.nodes_nb_alloc = MAX(next_map.nodes_nb_alloc * 2,
- 16);
- next_map.nodes_nb_alloc = MAX(next_map.nodes_nb_alloc,
- next_map.nodes_nb + nodes);
- next_map.nodes = g_renew(Node, next_map.nodes,
- next_map.nodes_nb_alloc);
+ if (map->nodes_nb + nodes > map->nodes_nb_alloc) {
+ map->nodes_nb_alloc = MAX(map->nodes_nb_alloc * 2, 16);
+ map->nodes_nb_alloc = MAX(map->nodes_nb_alloc, map->nodes_nb + nodes);
+ map->nodes = g_renew(Node, map->nodes, map->nodes_nb_alloc);
}
}
-static uint16_t phys_map_node_alloc(void)
+static uint32_t phys_map_node_alloc(PhysPageMap *map)
{
unsigned i;
- uint16_t ret;
+ uint32_t ret;
- ret = next_map.nodes_nb++;
+ ret = map->nodes_nb++;
assert(ret != PHYS_MAP_NODE_NIL);
- assert(ret != next_map.nodes_nb_alloc);
- for (i = 0; i < L2_SIZE; ++i) {
- next_map.nodes[ret][i].is_leaf = 0;
- next_map.nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;
+ assert(ret != map->nodes_nb_alloc);
+ for (i = 0; i < P_L2_SIZE; ++i) {
+ map->nodes[ret][i].skip = 1;
+ map->nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;
}
return ret;
}
-static void phys_page_set_level(PhysPageEntry *lp, hwaddr *index,
- hwaddr *nb, uint16_t leaf,
+static void phys_page_set_level(PhysPageMap *map, PhysPageEntry *lp,
+ hwaddr *index, hwaddr *nb, uint16_t leaf,
int level)
{
PhysPageEntry *p;
int i;
- hwaddr step = (hwaddr)1 << (level * L2_BITS);
+ hwaddr step = (hwaddr)1 << (level * P_L2_BITS);
- if (!lp->is_leaf && lp->ptr == PHYS_MAP_NODE_NIL) {
- lp->ptr = phys_map_node_alloc();
- p = next_map.nodes[lp->ptr];
+ if (lp->skip && lp->ptr == PHYS_MAP_NODE_NIL) {
+ lp->ptr = phys_map_node_alloc(map);
+ p = map->nodes[lp->ptr];
if (level == 0) {
- for (i = 0; i < L2_SIZE; i++) {
- p[i].is_leaf = 1;
+ for (i = 0; i < P_L2_SIZE; i++) {
+ p[i].skip = 0;
p[i].ptr = PHYS_SECTION_UNASSIGNED;
}
}
} else {
- p = next_map.nodes[lp->ptr];
+ p = map->nodes[lp->ptr];
}
- lp = &p[(*index >> (level * L2_BITS)) & (L2_SIZE - 1)];
+ lp = &p[(*index >> (level * P_L2_BITS)) & (P_L2_SIZE - 1)];
- while (*nb && lp < &p[L2_SIZE]) {
+ while (*nb && lp < &p[P_L2_SIZE]) {
if ((*index & (step - 1)) == 0 && *nb >= step) {
- lp->is_leaf = true;
+ lp->skip = 0;
lp->ptr = leaf;
*index += step;
*nb -= step;
} else {
- phys_page_set_level(lp, index, nb, leaf, level - 1);
+ phys_page_set_level(map, lp, index, nb, leaf, level - 1);
}
++lp;
}
uint16_t leaf)
{
/* Wildly overreserve - it doesn't matter much. */
- phys_map_node_reserve(3 * P_L2_LEVELS);
+ phys_map_node_reserve(&d->map, 3 * P_L2_LEVELS);
- phys_page_set_level(&d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
+ phys_page_set_level(&d->map, &d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
}
-static MemoryRegionSection *phys_page_find(PhysPageEntry lp, hwaddr index,
+/* Compact a non leaf page entry. Simply detect that the entry has a single child,
+ * and update our entry so we can skip it and go directly to the destination.
+ */
+static void phys_page_compact(PhysPageEntry *lp, Node *nodes, unsigned long *compacted)
+{
+ unsigned valid_ptr = P_L2_SIZE;
+ int valid = 0;
+ PhysPageEntry *p;
+ int i;
+
+ if (lp->ptr == PHYS_MAP_NODE_NIL) {
+ return;
+ }
+
+ p = nodes[lp->ptr];
+ for (i = 0; i < P_L2_SIZE; i++) {
+ if (p[i].ptr == PHYS_MAP_NODE_NIL) {
+ continue;
+ }
+
+ valid_ptr = i;
+ valid++;
+ if (p[i].skip) {
+ phys_page_compact(&p[i], nodes, compacted);
+ }
+ }
+
+ /* We can only compress if there's only one child. */
+ if (valid != 1) {
+ return;
+ }
+
+ assert(valid_ptr < P_L2_SIZE);
+
+ /* Don't compress if it won't fit in the # of bits we have. */
+ if (lp->skip + p[valid_ptr].skip >= (1 << 3)) {
+ return;
+ }
+
+ lp->ptr = p[valid_ptr].ptr;
+ if (!p[valid_ptr].skip) {
+ /* If our only child is a leaf, make this a leaf. */
+ /* By design, we should have made this node a leaf to begin with so we
+ * should never reach here.
+ * But since it's so simple to handle this, let's do it just in case we
+ * change this rule.
+ */
+ lp->skip = 0;
+ } else {
+ lp->skip += p[valid_ptr].skip;
+ }
+}
+
+static void phys_page_compact_all(AddressSpaceDispatch *d, int nodes_nb)
+{
+ DECLARE_BITMAP(compacted, nodes_nb);
+
+ if (d->phys_map.skip) {
+ phys_page_compact(&d->phys_map, d->map.nodes, compacted);
+ }
+}
+
+static MemoryRegionSection *phys_page_find(PhysPageEntry lp, hwaddr addr,
Node *nodes, MemoryRegionSection *sections)
{
PhysPageEntry *p;
+ hwaddr index = addr >> TARGET_PAGE_BITS;
int i;
- for (i = P_L2_LEVELS - 1; i >= 0 && !lp.is_leaf; i--) {
+ for (i = P_L2_LEVELS; lp.skip && (i -= lp.skip) >= 0;) {
if (lp.ptr == PHYS_MAP_NODE_NIL) {
return §ions[PHYS_SECTION_UNASSIGNED];
}
p = nodes[lp.ptr];
- lp = p[(index >> (i * L2_BITS)) & (L2_SIZE - 1)];
+ lp = p[(index >> (i * P_L2_BITS)) & (P_L2_SIZE - 1)];
+ }
+
+ if (sections[lp.ptr].size.hi ||
+ range_covers_byte(sections[lp.ptr].offset_within_address_space,
+ sections[lp.ptr].size.lo, addr)) {
+ return §ions[lp.ptr];
+ } else {
+ return §ions[PHYS_SECTION_UNASSIGNED];
}
- return §ions[lp.ptr];
}
bool memory_region_is_unassigned(MemoryRegion *mr)
MemoryRegionSection *section;
subpage_t *subpage;
- section = phys_page_find(d->phys_map, addr >> TARGET_PAGE_BITS,
- d->nodes, d->sections);
+ section = phys_page_find(d->phys_map, addr, d->map.nodes, d->map.sections);
if (resolve_subpage && section->mr->subpage) {
subpage = container_of(section->mr, subpage_t, iomem);
- section = &d->sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
+ section = &d->map.sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
}
return section;
}
CPUState *qemu_get_cpu(int index)
{
- CPUState *cpu = first_cpu;
+ CPUState *cpu;
- while (cpu) {
+ CPU_FOREACH(cpu) {
if (cpu->cpu_index == index) {
- break;
+ return cpu;
}
- cpu = cpu->next_cpu;
}
- return cpu;
-}
-
-void qemu_for_each_cpu(void (*func)(CPUState *cpu, void *data), void *data)
-{
- CPUState *cpu;
-
- cpu = first_cpu;
- while (cpu) {
- func(cpu, data);
- cpu = cpu->next_cpu;
- }
+ return NULL;
}
void cpu_exec_init(CPUArchState *env)
{
CPUState *cpu = ENV_GET_CPU(env);
CPUClass *cc = CPU_GET_CLASS(cpu);
- CPUState **pcpu;
+ CPUState *some_cpu;
int cpu_index;
#if defined(CONFIG_USER_ONLY)
cpu_list_lock();
#endif
- cpu->next_cpu = NULL;
- pcpu = &first_cpu;
cpu_index = 0;
- while (*pcpu != NULL) {
- pcpu = &(*pcpu)->next_cpu;
+ CPU_FOREACH(some_cpu) {
cpu_index++;
}
cpu->cpu_index = cpu_index;
#ifndef CONFIG_USER_ONLY
cpu->thread_id = qemu_get_thread_id();
#endif
- *pcpu = cpu;
+ QTAILQ_INSERT_TAIL(&cpus, cpu, node);
#if defined(CONFIG_USER_ONLY)
cpu_list_unlock();
#endif
- vmstate_register(NULL, cpu_index, &vmstate_cpu_common, cpu);
+ if (qdev_get_vmsd(DEVICE(cpu)) == NULL) {
+ vmstate_register(NULL, cpu_index, &vmstate_cpu_common, cpu);
+ }
#if defined(CPU_SAVE_VERSION) && !defined(CONFIG_USER_ONLY)
register_savevm(NULL, "cpu", cpu_index, CPU_SAVE_VERSION,
cpu_save, cpu_load, env);
assert(cc->vmsd == NULL);
+ assert(qdev_get_vmsd(DEVICE(cpu)) == NULL);
#endif
if (cc->vmsd != NULL) {
vmstate_register(NULL, cpu_index, cc->vmsd, cpu);
#else
static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
{
- tb_invalidate_phys_addr(cpu_get_phys_page_debug(cpu, pc) |
- (pc & ~TARGET_PAGE_MASK));
+ hwaddr phys = cpu_get_phys_page_debug(cpu, pc);
+ if (phys != -1) {
+ tb_invalidate_phys_addr(phys | (pc & ~TARGET_PAGE_MASK));
+ }
}
#endif
#endif /* TARGET_HAS_ICE */
void cpu_single_step(CPUState *cpu, int enabled)
{
#if defined(TARGET_HAS_ICE)
- CPUArchState *env = cpu->env_ptr;
-
if (cpu->singlestep_enabled != enabled) {
cpu->singlestep_enabled = enabled;
if (kvm_enabled()) {
- kvm_update_guest_debug(env, 0);
+ kvm_update_guest_debug(cpu, 0);
} else {
/* must flush all the translated code to avoid inconsistencies */
/* XXX: only flush what is necessary */
+ CPUArchState *env = cpu->env_ptr;
tb_flush(env);
}
}
abort();
}
-CPUArchState *cpu_copy(CPUArchState *env)
+#if !defined(CONFIG_USER_ONLY)
+static RAMBlock *qemu_get_ram_block(ram_addr_t addr)
{
- CPUArchState *new_env = cpu_init(env->cpu_model_str);
-#if defined(TARGET_HAS_ICE)
- CPUBreakpoint *bp;
- CPUWatchpoint *wp;
-#endif
-
- /* Reset non arch specific state */
- cpu_reset(ENV_GET_CPU(new_env));
-
- /* Copy arch specific state into the new CPU */
- memcpy(new_env, env, sizeof(CPUArchState));
+ RAMBlock *block;
- /* Clone all break/watchpoints.
- Note: Once we support ptrace with hw-debug register access, make sure
- BP_CPU break/watchpoints are handled correctly on clone. */
- QTAILQ_INIT(&env->breakpoints);
- QTAILQ_INIT(&env->watchpoints);
-#if defined(TARGET_HAS_ICE)
- QTAILQ_FOREACH(bp, &env->breakpoints, entry) {
- cpu_breakpoint_insert(new_env, bp->pc, bp->flags, NULL);
+ /* The list is protected by the iothread lock here. */
+ block = ram_list.mru_block;
+ if (block && addr - block->offset < block->length) {
+ goto found;
}
- QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
- cpu_watchpoint_insert(new_env, wp->vaddr, (~wp->len_mask) + 1,
- wp->flags, NULL);
+ QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+ if (addr - block->offset < block->length) {
+ goto found;
+ }
}
-#endif
- return new_env;
+ fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
+ abort();
+
+found:
+ ram_list.mru_block = block;
+ return block;
}
-#if !defined(CONFIG_USER_ONLY)
static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t end,
uintptr_t length)
{
- uintptr_t start1;
+ RAMBlock *block;
+ ram_addr_t start1;
- /* we modify the TLB cache so that the dirty bit will be set again
- when accessing the range */
- start1 = (uintptr_t)qemu_safe_ram_ptr(start);
- /* Check that we don't span multiple blocks - this breaks the
- address comparisons below. */
- if ((uintptr_t)qemu_safe_ram_ptr(end - 1) - start1
- != (end - 1) - start) {
- abort();
- }
+ block = qemu_get_ram_block(start);
+ assert(block == qemu_get_ram_block(end - 1));
+ start1 = (uintptr_t)block->host + (start - block->offset);
cpu_tlb_reset_dirty_all(start1, length);
-
}
/* Note: start and end must be within the same ram block. */
iotlb |= PHYS_SECTION_ROM;
}
} else {
- iotlb = section - address_space_memory.dispatch->sections;
+ iotlb = section - address_space_memory.dispatch->map.sections;
iotlb += xlat;
}
uint16_t section);
static subpage_t *subpage_init(AddressSpace *as, hwaddr base);
-static uint16_t phys_section_add(MemoryRegionSection *section)
+static void *(*phys_mem_alloc)(size_t size) = qemu_anon_ram_alloc;
+
+/*
+ * Set a custom physical guest memory alloator.
+ * Accelerators with unusual needs may need this. Hopefully, we can
+ * get rid of it eventually.
+ */
+void phys_mem_set_alloc(void *(*alloc)(size_t))
+{
+ phys_mem_alloc = alloc;
+}
+
+static uint16_t phys_section_add(PhysPageMap *map,
+ MemoryRegionSection *section)
{
/* The physical section number is ORed with a page-aligned
* pointer to produce the iotlb entries. Thus it should
* never overflow into the page-aligned value.
*/
- assert(next_map.sections_nb < TARGET_PAGE_SIZE);
+ assert(map->sections_nb < TARGET_PAGE_SIZE);
- if (next_map.sections_nb == next_map.sections_nb_alloc) {
- next_map.sections_nb_alloc = MAX(next_map.sections_nb_alloc * 2,
- 16);
- next_map.sections = g_renew(MemoryRegionSection, next_map.sections,
- next_map.sections_nb_alloc);
+ if (map->sections_nb == map->sections_nb_alloc) {
+ map->sections_nb_alloc = MAX(map->sections_nb_alloc * 2, 16);
+ map->sections = g_renew(MemoryRegionSection, map->sections,
+ map->sections_nb_alloc);
}
- next_map.sections[next_map.sections_nb] = *section;
+ map->sections[map->sections_nb] = *section;
memory_region_ref(section->mr);
- return next_map.sections_nb++;
+ return map->sections_nb++;
}
static void phys_section_destroy(MemoryRegion *mr)
}
g_free(map->sections);
g_free(map->nodes);
- g_free(map);
}
static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *section)
subpage_t *subpage;
hwaddr base = section->offset_within_address_space
& TARGET_PAGE_MASK;
- MemoryRegionSection *existing = phys_page_find(d->phys_map, base >> TARGET_PAGE_BITS,
- next_map.nodes, next_map.sections);
+ MemoryRegionSection *existing = phys_page_find(d->phys_map, base,
+ d->map.nodes, d->map.sections);
MemoryRegionSection subsection = {
.offset_within_address_space = base,
.size = int128_make64(TARGET_PAGE_SIZE),
subpage = subpage_init(d->as, base);
subsection.mr = &subpage->iomem;
phys_page_set(d, base >> TARGET_PAGE_BITS, 1,
- phys_section_add(&subsection));
+ phys_section_add(&d->map, &subsection));
} else {
subpage = container_of(existing->mr, subpage_t, iomem);
}
start = section->offset_within_address_space & ~TARGET_PAGE_MASK;
end = start + int128_get64(section->size) - 1;
- subpage_register(subpage, start, end, phys_section_add(section));
+ subpage_register(subpage, start, end,
+ phys_section_add(&d->map, section));
}
MemoryRegionSection *section)
{
hwaddr start_addr = section->offset_within_address_space;
- uint16_t section_index = phys_section_add(section);
+ uint16_t section_index = phys_section_add(&d->map, section);
uint64_t num_pages = int128_get64(int128_rshift(section->size,
TARGET_PAGE_BITS));
now = remain;
if (int128_lt(remain.size, page_size)) {
register_subpage(d, &now);
- } else if (remain.offset_within_region & ~TARGET_PAGE_MASK) {
+ } else if (remain.offset_within_address_space & ~TARGET_PAGE_MASK) {
now.size = page_size;
register_subpage(d, &now);
} else {
qemu_mutex_unlock(&ram_list.mutex);
}
-#if defined(__linux__) && !defined(TARGET_S390X)
+#ifdef __linux__
#include <sys/vfs.h>
return fs.f_bsize;
}
+static sigjmp_buf sigjump;
+
+static void sigbus_handler(int signal)
+{
+ siglongjmp(sigjump, 1);
+}
+
static void *file_ram_alloc(RAMBlock *block,
ram_addr_t memory,
const char *path)
char *c;
void *area;
int fd;
-#ifdef MAP_POPULATE
- int flags;
-#endif
unsigned long hpagesize;
hpagesize = gethugepagesize(path);
if (ftruncate(fd, memory))
perror("ftruncate");
-#ifdef MAP_POPULATE
- /* NB: MAP_POPULATE won't exhaustively alloc all phys pages in the case
- * MAP_PRIVATE is requested. For mem_prealloc we mmap as MAP_SHARED
- * to sidestep this quirk.
- */
- flags = mem_prealloc ? MAP_POPULATE | MAP_SHARED : MAP_PRIVATE;
- area = mmap(0, memory, PROT_READ | PROT_WRITE, flags, fd, 0);
-#else
area = mmap(0, memory, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
-#endif
if (area == MAP_FAILED) {
perror("file_ram_alloc: can't mmap RAM pages");
close(fd);
return (NULL);
}
+
+ if (mem_prealloc) {
+ int ret, i;
+ struct sigaction act, oldact;
+ sigset_t set, oldset;
+
+ memset(&act, 0, sizeof(act));
+ act.sa_handler = &sigbus_handler;
+ act.sa_flags = 0;
+
+ ret = sigaction(SIGBUS, &act, &oldact);
+ if (ret) {
+ perror("file_ram_alloc: failed to install signal handler");
+ exit(1);
+ }
+
+ /* unblock SIGBUS */
+ sigemptyset(&set);
+ sigaddset(&set, SIGBUS);
+ pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
+
+ if (sigsetjmp(sigjump, 1)) {
+ fprintf(stderr, "file_ram_alloc: failed to preallocate pages\n");
+ exit(1);
+ }
+
+ /* MAP_POPULATE silently ignores failures */
+ for (i = 0; i < (memory/hpagesize)-1; i++) {
+ memset(area + (hpagesize*i), 0, 1);
+ }
+
+ ret = sigaction(SIGBUS, &oldact, NULL);
+ if (ret) {
+ perror("file_ram_alloc: failed to reinstall signal handler");
+ exit(1);
+ }
+
+ pthread_sigmask(SIG_SETMASK, &oldset, NULL);
+ }
+
block->fd = fd;
return area;
}
+#else
+static void *file_ram_alloc(RAMBlock *block,
+ ram_addr_t memory,
+ const char *path)
+{
+ fprintf(stderr, "-mem-path not supported on this host\n");
+ exit(1);
+}
#endif
static ram_addr_t find_ram_offset(ram_addr_t size)
size = TARGET_PAGE_ALIGN(size);
new_block = g_malloc0(sizeof(*new_block));
+ new_block->fd = -1;
/* This assumes the iothread lock is taken here too. */
qemu_mutex_lock_ramlist();
if (host) {
new_block->host = host;
new_block->flags |= RAM_PREALLOC_MASK;
+ } else if (xen_enabled()) {
+ if (mem_path) {
+ fprintf(stderr, "-mem-path not supported with Xen\n");
+ exit(1);
+ }
+ xen_ram_alloc(new_block->offset, size, mr);
} else {
if (mem_path) {
-#if defined (__linux__) && !defined(TARGET_S390X)
+ if (phys_mem_alloc != qemu_anon_ram_alloc) {
+ /*
+ * file_ram_alloc() needs to allocate just like
+ * phys_mem_alloc, but we haven't bothered to provide
+ * a hook there.
+ */
+ fprintf(stderr,
+ "-mem-path not supported with this accelerator\n");
+ exit(1);
+ }
new_block->host = file_ram_alloc(new_block, size, mem_path);
+ }
+ if (!new_block->host) {
+ new_block->host = phys_mem_alloc(size);
if (!new_block->host) {
- new_block->host = qemu_anon_ram_alloc(size);
- memory_try_enable_merging(new_block->host, size);
- }
-#else
- fprintf(stderr, "-mem-path option unsupported\n");
- exit(1);
-#endif
- } else {
- if (xen_enabled()) {
- xen_ram_alloc(new_block->offset, size, mr);
- } else if (kvm_enabled()) {
- /* some s390/kvm configurations have special constraints */
- new_block->host = kvm_ram_alloc(size);
- } else {
- new_block->host = qemu_anon_ram_alloc(size);
+ fprintf(stderr, "Cannot set up guest memory '%s': %s\n",
+ new_block->mr->name, strerror(errno));
+ exit(1);
}
memory_try_enable_merging(new_block->host, size);
}
qemu_ram_setup_dump(new_block->host, size);
qemu_madvise(new_block->host, size, QEMU_MADV_HUGEPAGE);
+ qemu_madvise(new_block->host, size, QEMU_MADV_DONTFORK);
if (kvm_enabled())
kvm_setup_guest_memory(new_block->host, size);
ram_list.version++;
if (block->flags & RAM_PREALLOC_MASK) {
;
- } else if (mem_path) {
-#if defined (__linux__) && !defined(TARGET_S390X)
- if (block->fd) {
- munmap(block->host, block->length);
- close(block->fd);
- } else {
- qemu_anon_ram_free(block->host, block->length);
- }
-#else
- abort();
+ } else if (xen_enabled()) {
+ xen_invalidate_map_cache_entry(block->host);
+#ifndef _WIN32
+ } else if (block->fd >= 0) {
+ munmap(block->host, block->length);
+ close(block->fd);
#endif
} else {
- if (xen_enabled()) {
- xen_invalidate_map_cache_entry(block->host);
- } else {
- qemu_anon_ram_free(block->host, block->length);
- }
+ qemu_anon_ram_free(block->host, block->length);
}
g_free(block);
break;
vaddr = block->host + offset;
if (block->flags & RAM_PREALLOC_MASK) {
;
+ } else if (xen_enabled()) {
+ abort();
} else {
flags = MAP_FIXED;
munmap(vaddr, length);
- if (mem_path) {
-#if defined(__linux__) && !defined(TARGET_S390X)
- if (block->fd) {
+ if (block->fd >= 0) {
#ifdef MAP_POPULATE
- flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :
- MAP_PRIVATE;
-#else
- flags |= MAP_PRIVATE;
-#endif
- area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
- flags, block->fd, offset);
- } else {
- flags |= MAP_PRIVATE | MAP_ANONYMOUS;
- area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
- flags, -1, 0);
- }
+ flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :
+ MAP_PRIVATE;
#else
- abort();
+ flags |= MAP_PRIVATE;
#endif
+ area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+ flags, block->fd, offset);
} else {
-#if defined(TARGET_S390X) && defined(CONFIG_KVM)
- flags |= MAP_SHARED | MAP_ANONYMOUS;
- area = mmap(vaddr, length, PROT_EXEC|PROT_READ|PROT_WRITE,
- flags, -1, 0);
-#else
+ /*
+ * Remap needs to match alloc. Accelerators that
+ * set phys_mem_alloc never remap. If they did,
+ * we'd need a remap hook here.
+ */
+ assert(phys_mem_alloc == qemu_anon_ram_alloc);
+
flags |= MAP_PRIVATE | MAP_ANONYMOUS;
area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
flags, -1, 0);
-#endif
}
if (area != vaddr) {
fprintf(stderr, "Could not remap addr: "
}
#endif /* !_WIN32 */
-static RAMBlock *qemu_get_ram_block(ram_addr_t addr)
-{
- RAMBlock *block;
-
- /* The list is protected by the iothread lock here. */
- block = ram_list.mru_block;
- if (block && addr - block->offset < block->length) {
- goto found;
- }
- QTAILQ_FOREACH(block, &ram_list.blocks, next) {
- if (addr - block->offset < block->length) {
- goto found;
- }
- }
-
- fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
- abort();
-
-found:
- ram_list.mru_block = block;
- return block;
-}
-
/* Return a host pointer to ram allocated with qemu_ram_alloc.
With the exception of the softmmu code in this file, this should
only be used for local memory (e.g. video ram) that the device owns,
return block->host + (addr - block->offset);
}
-/* Return a host pointer to ram allocated with qemu_ram_alloc. Same as
- * qemu_get_ram_ptr but do not touch ram_list.mru_block.
- *
- * ??? Is this still necessary?
- */
-static void *qemu_safe_ram_ptr(ram_addr_t addr)
-{
- RAMBlock *block;
-
- /* The list is protected by the iothread lock here. */
- QTAILQ_FOREACH(block, &ram_list.blocks, next) {
- if (addr - block->offset < block->length) {
- if (xen_enabled()) {
- /* We need to check if the requested address is in the RAM
- * because we don't want to map the entire memory in QEMU.
- * In that case just map until the end of the page.
- */
- if (block->offset == 0) {
- return xen_map_cache(addr, 0, 0);
- } else if (block->host == NULL) {
- block->host =
- xen_map_cache(block->offset, block->length, 1);
- }
- }
- return block->host + (addr - block->offset);
- }
- }
-
- fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
- abort();
-
- return NULL;
-}
-
/* Return a host pointer to guest's ram. Similar to qemu_get_ram_ptr
* but takes a size argument */
static void *qemu_ram_ptr_length(ram_addr_t addr, hwaddr *size)
uint8_t buf[4];
#if defined(DEBUG_SUBPAGE)
- printf("%s: subpage %p len %d addr " TARGET_FMT_plx "\n", __func__,
+ printf("%s: subpage %p len %u addr " TARGET_FMT_plx "\n", __func__,
subpage, len, addr);
#endif
address_space_read(subpage->as, addr + subpage->base, buf, len);
uint8_t buf[4];
#if defined(DEBUG_SUBPAGE)
- printf("%s: subpage %p len %d addr " TARGET_FMT_plx
+ printf("%s: subpage %p len %u addr " TARGET_FMT_plx
" value %"PRIx64"\n",
__func__, subpage, len, addr, value);
#endif
}
static bool subpage_accepts(void *opaque, hwaddr addr,
- unsigned size, bool is_write)
+ unsigned len, bool is_write)
{
subpage_t *subpage = opaque;
#if defined(DEBUG_SUBPAGE)
- printf("%s: subpage %p %c len %d addr " TARGET_FMT_plx "\n",
+ printf("%s: subpage %p %c len %u addr " TARGET_FMT_plx "\n",
__func__, subpage, is_write ? 'w' : 'r', len, addr);
#endif
return address_space_access_valid(subpage->as, addr + subpage->base,
- size, is_write);
+ len, is_write);
}
static const MemoryRegionOps subpage_ops = {
idx = SUBPAGE_IDX(start);
eidx = SUBPAGE_IDX(end);
#if defined(DEBUG_SUBPAGE)
- printf("%s: %p start %08x end %08x idx %08x eidx %08x mem %ld\n", __func__,
- mmio, start, end, idx, eidx, memory);
+ printf("%s: %p start %08x end %08x idx %08x eidx %08x section %d\n",
+ __func__, mmio, start, end, idx, eidx, section);
#endif
for (; idx <= eidx; idx++) {
mmio->sub_section[idx] = section;
"subpage", TARGET_PAGE_SIZE);
mmio->iomem.subpage = true;
#if defined(DEBUG_SUBPAGE)
- printf("%s: %p base " TARGET_FMT_plx " len %08x %d\n", __func__,
- mmio, base, TARGET_PAGE_SIZE, subpage_memory);
+ printf("%s: %p base " TARGET_FMT_plx " len %08x\n", __func__,
+ mmio, base, TARGET_PAGE_SIZE);
#endif
subpage_register(mmio, 0, TARGET_PAGE_SIZE-1, PHYS_SECTION_UNASSIGNED);
return mmio;
}
-static uint16_t dummy_section(MemoryRegion *mr)
+static uint16_t dummy_section(PhysPageMap *map, MemoryRegion *mr)
{
MemoryRegionSection section = {
.mr = mr,
.size = int128_2_64(),
};
- return phys_section_add(§ion);
+ return phys_section_add(map, §ion);
}
MemoryRegion *iotlb_to_region(hwaddr index)
{
- return address_space_memory.dispatch->sections[index & ~TARGET_PAGE_MASK].mr;
+ return address_space_memory.dispatch->map.sections[
+ index & ~TARGET_PAGE_MASK].mr;
}
static void io_mem_init(void)
static void mem_begin(MemoryListener *listener)
{
AddressSpace *as = container_of(listener, AddressSpace, dispatch_listener);
- AddressSpaceDispatch *d = g_new(AddressSpaceDispatch, 1);
+ AddressSpaceDispatch *d = g_new0(AddressSpaceDispatch, 1);
+ uint16_t n;
- d->phys_map = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .is_leaf = 0 };
+ n = dummy_section(&d->map, &io_mem_unassigned);
+ assert(n == PHYS_SECTION_UNASSIGNED);
+ n = dummy_section(&d->map, &io_mem_notdirty);
+ assert(n == PHYS_SECTION_NOTDIRTY);
+ n = dummy_section(&d->map, &io_mem_rom);
+ assert(n == PHYS_SECTION_ROM);
+ n = dummy_section(&d->map, &io_mem_watch);
+ assert(n == PHYS_SECTION_WATCH);
+
+ d->phys_map = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .skip = 1 };
d->as = as;
as->next_dispatch = d;
}
AddressSpaceDispatch *cur = as->dispatch;
AddressSpaceDispatch *next = as->next_dispatch;
- next->nodes = next_map.nodes;
- next->sections = next_map.sections;
+ phys_page_compact_all(next, next->map.nodes_nb);
as->dispatch = next;
- g_free(cur);
-}
-
-static void core_begin(MemoryListener *listener)
-{
- uint16_t n;
-
- prev_map = g_new(PhysPageMap, 1);
- *prev_map = next_map;
-
- memset(&next_map, 0, sizeof(next_map));
- n = dummy_section(&io_mem_unassigned);
- assert(n == PHYS_SECTION_UNASSIGNED);
- n = dummy_section(&io_mem_notdirty);
- assert(n == PHYS_SECTION_NOTDIRTY);
- n = dummy_section(&io_mem_rom);
- assert(n == PHYS_SECTION_ROM);
- n = dummy_section(&io_mem_watch);
- assert(n == PHYS_SECTION_WATCH);
-}
-/* This listener's commit run after the other AddressSpaceDispatch listeners'.
- * All AddressSpaceDispatch instances have switched to the next map.
- */
-static void core_commit(MemoryListener *listener)
-{
- phys_sections_free(prev_map);
+ if (cur) {
+ phys_sections_free(&cur->map);
+ g_free(cur);
+ }
}
static void tcg_commit(MemoryListener *listener)
/* since each CPU stores ram addresses in its TLB cache, we must
reset the modified entries */
/* XXX: slow ! */
- for (cpu = first_cpu; cpu != NULL; cpu = cpu->next_cpu) {
+ CPU_FOREACH(cpu) {
CPUArchState *env = cpu->env_ptr;
tlb_flush(env, 1);
}
static MemoryListener core_memory_listener = {
- .begin = core_begin,
- .commit = core_commit,
.log_global_start = core_log_global_start,
.log_global_stop = core_log_global_stop,
.priority = 1,
static void memory_map_init(void)
{
system_memory = g_malloc(sizeof(*system_memory));
- memory_region_init(system_memory, NULL, "system", INT64_MAX);
+
+ memory_region_init(system_memory, NULL, "system", UINT64_MAX);
address_space_init(&address_space_memory, system_memory, "memory");
system_io = g_malloc(sizeof(*system_io));
- memory_region_init(system_io, NULL, "io", 65536);
+ memory_region_init_io(system_io, NULL, &unassigned_io_ops, NULL, "io",
+ 65536);
address_space_init(&address_space_io, system_io, "I/O");
memory_listener_register(&core_memory_listener, &address_space_memory);
- memory_listener_register(&tcg_memory_listener, &address_space_memory);
+ if (tcg_enabled()) {
+ memory_listener_register(&tcg_memory_listener, &address_space_memory);
+ }
}
MemoryRegion *get_system_memory(void)
if (l > access_size_max) {
l = access_size_max;
}
+ if (l & (l - 1)) {
+ l = 1 << (qemu_fls(l) - 1);
+ }
return l;
}
if (bounce.buffer) {
return NULL;
}
- bounce.buffer = qemu_memalign(TARGET_PAGE_SIZE, TARGET_PAGE_SIZE);
+ /* Avoid unbounded allocations */
+ l = MIN(l, TARGET_PAGE_SIZE);
+ bounce.buffer = qemu_memalign(TARGET_PAGE_SIZE, l);
bounce.addr = addr;
bounce.len = l;