*/
#include "qemu/osdep.h"
#include "qapi/error.h"
-#ifndef _WIN32
-#endif
#include "qemu/cutils.h"
#include "cpu.h"
#include "exec/exec-all.h"
+#include "exec/target_page.h"
#include "tcg.h"
#include "hw/qdev-core.h"
+#include "hw/qdev-properties.h"
#if !defined(CONFIG_USER_ONLY)
#include "hw/boards.h"
#include "hw/xen/xen.h"
#include "exec/memory.h"
#include "exec/ioport.h"
#include "sysemu/dma.h"
+#include "sysemu/numa.h"
+#include "sysemu/hw_accel.h"
#include "exec/address-spaces.h"
#include "sysemu/xen-mapcache.h"
#include "trace-root.h"
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+#include <linux/falloc.h>
+#endif
+
#endif
-#include "exec/cpu-all.h"
#include "qemu/rcu_queue.h"
#include "qemu/main-loop.h"
#include "translate-all.h"
#include "qemu/mmap-alloc.h"
#endif
+#include "monitor/monitor.h"
+
//#define DEBUG_SUBPAGE
#if !defined(CONFIG_USER_ONLY)
2 = Adaptive rate instruction counting. */
int use_icount;
+uintptr_t qemu_host_page_size;
+intptr_t qemu_host_page_mask;
+
bool set_preferred_target_page_bits(int bits)
{
/* The target page size is the lowest common denominator for all
} PhysPageMap;
struct AddressSpaceDispatch {
- struct rcu_head rcu;
-
MemoryRegionSection *mru_section;
/* This is a multi-level map on the physical address space.
* The bottom level has pointers to MemoryRegionSections.
*/
PhysPageEntry phys_map;
PhysPageMap map;
- AddressSpace *as;
};
#define SUBPAGE_IDX(addr) ((addr) & ~TARGET_PAGE_MASK)
typedef struct subpage_t {
MemoryRegion iomem;
- AddressSpace *as;
+ FlatView *fv;
hwaddr base;
uint16_t sub_section[];
} subpage_t;
MemoryListener tcg_as_listener;
};
+struct DirtyBitmapSnapshot {
+ ram_addr_t start;
+ ram_addr_t end;
+ unsigned long dirty[];
+};
+
#endif
#if !defined(CONFIG_USER_ONLY)
}
}
-static void phys_page_compact_all(AddressSpaceDispatch *d, int nodes_nb)
+void address_space_dispatch_compact(AddressSpaceDispatch *d)
{
if (d->phys_map.skip) {
phys_page_compact(&d->phys_map, d->map.nodes);
int128_getlo(section->size), addr);
}
-static MemoryRegionSection *phys_page_find(PhysPageEntry lp, hwaddr addr,
- Node *nodes, MemoryRegionSection *sections)
+static MemoryRegionSection *phys_page_find(AddressSpaceDispatch *d, hwaddr addr)
{
- PhysPageEntry *p;
+ PhysPageEntry lp = d->phys_map, *p;
+ Node *nodes = d->map.nodes;
+ MemoryRegionSection *sections = d->map.sections;
hwaddr index = addr >> TARGET_PAGE_BITS;
int i;
{
MemoryRegionSection *section = atomic_read(&d->mru_section);
subpage_t *subpage;
- bool update;
- if (section && section != &d->map.sections[PHYS_SECTION_UNASSIGNED] &&
- section_covers_addr(section, addr)) {
- update = false;
- } else {
- section = phys_page_find(d->phys_map, addr, d->map.nodes,
- d->map.sections);
- update = true;
+ if (!section || section == &d->map.sections[PHYS_SECTION_UNASSIGNED] ||
+ !section_covers_addr(section, addr)) {
+ section = phys_page_find(d, addr);
+ atomic_set(&d->mru_section, section);
}
if (resolve_subpage && section->mr->subpage) {
subpage = container_of(section->mr, subpage_t, iomem);
section = &d->map.sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
}
- if (update) {
- atomic_set(&d->mru_section, section);
- }
return section;
}
return section;
}
-/* Called from RCU critical section */
-IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr,
- bool is_write)
+/**
+ * flatview_do_translate - translate an address in FlatView
+ *
+ * @fv: the flat view that we want to translate on
+ * @addr: the address to be translated in above address space
+ * @xlat: the translated address offset within memory region. It
+ * cannot be @NULL.
+ * @plen_out: valid read/write length of the translated address. It
+ * can be @NULL when we don't care about it.
+ * @page_mask_out: page mask for the translated address. This
+ * should only be meaningful for IOMMU translated
+ * addresses, since there may be huge pages that this bit
+ * would tell. It can be @NULL if we don't care about it.
+ * @is_write: whether the translation operation is for write
+ * @is_mmio: whether this can be MMIO, set true if it can
+ *
+ * This function is called from RCU critical section
+ */
+static MemoryRegionSection flatview_do_translate(FlatView *fv,
+ hwaddr addr,
+ hwaddr *xlat,
+ hwaddr *plen_out,
+ hwaddr *page_mask_out,
+ bool is_write,
+ bool is_mmio,
+ AddressSpace **target_as)
{
- IOMMUTLBEntry iotlb = {0};
+ IOMMUTLBEntry iotlb;
MemoryRegionSection *section;
- MemoryRegion *mr;
+ IOMMUMemoryRegion *iommu_mr;
+ IOMMUMemoryRegionClass *imrc;
+ hwaddr page_mask = (hwaddr)(-1);
+ hwaddr plen = (hwaddr)(-1);
+
+ if (plen_out) {
+ plen = *plen_out;
+ }
for (;;) {
- AddressSpaceDispatch *d = atomic_rcu_read(&as->dispatch);
- section = address_space_lookup_region(d, addr, false);
- addr = addr - section->offset_within_address_space
- + section->offset_within_region;
- mr = section->mr;
+ section = address_space_translate_internal(
+ flatview_to_dispatch(fv), addr, &addr,
+ &plen, is_mmio);
- if (!mr->iommu_ops) {
+ iommu_mr = memory_region_get_iommu(section->mr);
+ if (!iommu_mr) {
break;
}
+ imrc = memory_region_get_iommu_class_nocheck(iommu_mr);
- iotlb = mr->iommu_ops->translate(mr, addr, is_write);
+ iotlb = imrc->translate(iommu_mr, addr, is_write ?
+ IOMMU_WO : IOMMU_RO);
+ addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
+ | (addr & iotlb.addr_mask));
+ page_mask &= iotlb.addr_mask;
+ plen = MIN(plen, (addr | iotlb.addr_mask) - addr + 1);
if (!(iotlb.perm & (1 << is_write))) {
- iotlb.target_as = NULL;
- break;
+ goto translate_fail;
}
- addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
- | (addr & iotlb.addr_mask));
- as = iotlb.target_as;
+ fv = address_space_to_flatview(iotlb.target_as);
+ *target_as = iotlb.target_as;
}
- return iotlb;
+ *xlat = addr;
+
+ if (page_mask == (hwaddr)(-1)) {
+ /* Not behind an IOMMU, use default page size. */
+ page_mask = ~TARGET_PAGE_MASK;
+ }
+
+ if (page_mask_out) {
+ *page_mask_out = page_mask;
+ }
+
+ if (plen_out) {
+ *plen_out = plen;
+ }
+
+ return *section;
+
+translate_fail:
+ return (MemoryRegionSection) { .mr = &io_mem_unassigned };
}
/* Called from RCU critical section */
-MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,
- hwaddr *xlat, hwaddr *plen,
- bool is_write)
+IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr,
+ bool is_write)
{
- IOMMUTLBEntry iotlb;
- MemoryRegionSection *section;
- MemoryRegion *mr;
+ MemoryRegionSection section;
+ hwaddr xlat, page_mask;
- for (;;) {
- AddressSpaceDispatch *d = atomic_rcu_read(&as->dispatch);
- section = address_space_translate_internal(d, addr, &addr, plen, true);
- mr = section->mr;
+ /*
+ * This can never be MMIO, and we don't really care about plen,
+ * but page mask.
+ */
+ section = flatview_do_translate(address_space_to_flatview(as), addr, &xlat,
+ NULL, &page_mask, is_write, false, &as);
- if (!mr->iommu_ops) {
- break;
- }
+ /* Illegal translation */
+ if (section.mr == &io_mem_unassigned) {
+ goto iotlb_fail;
+ }
- iotlb = mr->iommu_ops->translate(mr, addr, is_write);
- addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
- | (addr & iotlb.addr_mask));
- *plen = MIN(*plen, (addr | iotlb.addr_mask) - addr + 1);
- if (!(iotlb.perm & (1 << is_write))) {
- mr = &io_mem_unassigned;
- break;
- }
+ /* Convert memory region offset into address space offset */
+ xlat += section.offset_within_address_space -
+ section.offset_within_region;
- as = iotlb.target_as;
- }
+ return (IOMMUTLBEntry) {
+ .target_as = as,
+ .iova = addr & ~page_mask,
+ .translated_addr = xlat & ~page_mask,
+ .addr_mask = page_mask,
+ /* IOTLBs are for DMAs, and DMA only allows on RAMs. */
+ .perm = IOMMU_RW,
+ };
+
+iotlb_fail:
+ return (IOMMUTLBEntry) {0};
+}
+
+/* Called from RCU critical section */
+MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat,
+ hwaddr *plen, bool is_write)
+{
+ MemoryRegion *mr;
+ MemoryRegionSection section;
+ AddressSpace *as = NULL;
+
+ /* This can be MMIO, so setup MMIO bit. */
+ section = flatview_do_translate(fv, addr, xlat, plen, NULL,
+ is_write, true, &as);
+ mr = section.mr;
if (xen_enabled() && memory_access_is_direct(mr, is_write)) {
hwaddr page = ((addr & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE) - addr;
*plen = MIN(page, *plen);
}
- *xlat = addr;
return mr;
}
section = address_space_translate_internal(d, addr, xlat, plen, false);
- assert(!section->mr->iommu_ops);
+ assert(!memory_region_is_iommu(section->mr));
return section;
}
#endif
}
#if !defined(CONFIG_USER_ONLY)
-void cpu_address_space_init(CPUState *cpu, AddressSpace *as, int asidx)
+void cpu_address_space_init(CPUState *cpu, int asidx,
+ const char *prefix, MemoryRegion *mr)
{
CPUAddressSpace *newas;
+ AddressSpace *as = g_new0(AddressSpace, 1);
+ char *as_name;
+
+ assert(mr);
+ as_name = g_strdup_printf("%s-%d", prefix, cpu->cpu_index);
+ address_space_init(as, mr, as_name);
+ g_free(as_name);
/* Target code should have set num_ases before calling us */
assert(asidx < cpu->num_ases);
}
}
+Property cpu_common_props[] = {
+#ifndef CONFIG_USER_ONLY
+ /* Create a memory property for softmmu CPU object,
+ * so users can wire up its memory. (This can't go in qom/cpu.c
+ * because that file is compiled only once for both user-mode
+ * and system builds.) The default if no link is set up is to use
+ * the system address space.
+ */
+ DEFINE_PROP_LINK("memory", CPUState, memory, TYPE_MEMORY_REGION,
+ MemoryRegion *),
+#endif
+ DEFINE_PROP_END_OF_LIST(),
+};
+
void cpu_exec_initfn(CPUState *cpu)
{
cpu->as = NULL;
#ifndef CONFIG_USER_ONLY
cpu->thread_id = qemu_get_thread_id();
-
- /* This is a softmmu CPU object, so create a property for it
- * so users can wire up its memory. (This can't go in qom/cpu.c
- * because that file is compiled only once for both user-mode
- * and system builds.) The default if no link is set up is to use
- * the system address space.
- */
- object_property_add_link(OBJECT(cpu), "memory", TYPE_MEMORY_REGION,
- (Object **)&cpu->memory,
- qdev_prop_allow_set_link_before_realize,
- OBJ_PROP_LINK_UNREF_ON_RELEASE,
- &error_abort);
cpu->memory = system_memory;
object_ref(OBJECT(cpu->memory));
#endif
void cpu_exec_realizefn(CPUState *cpu, Error **errp)
{
- CPUClass *cc ATTRIBUTE_UNUSED = CPU_GET_CLASS(cpu);
+ CPUClass *cc = CPU_GET_CLASS(cpu);
+ static bool tcg_target_initialized;
cpu_list_add(cpu);
+ if (tcg_enabled() && !tcg_target_initialized) {
+ tcg_target_initialized = true;
+ cc->tcg_initialize();
+ }
+
#ifndef CONFIG_USER_ONLY
if (qdev_get_vmsd(DEVICE(cpu)) == NULL) {
vmstate_register(NULL, cpu->cpu_index, &vmstate_cpu_common, cpu);
#endif
}
+#if defined(CONFIG_USER_ONLY)
static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
{
- /* Flush the whole TB as this will not have race conditions
- * even if we don't have proper locking yet.
- * Ideally we would just invalidate the TBs for the
- * specified PC.
- */
- tb_flush(cpu);
+ mmap_lock();
+ tb_lock();
+ tb_invalidate_phys_page_range(pc, pc + 1, 0);
+ tb_unlock();
+ mmap_unlock();
}
+#else
+static void breakpoint_invalidate(CPUState *cpu, target_ulong pc)
+{
+ MemTxAttrs attrs;
+ hwaddr phys = cpu_get_phys_page_attrs_debug(cpu, pc, &attrs);
+ int asidx = cpu_asidx_from_attrs(cpu, attrs);
+ if (phys != -1) {
+ /* Locks grabbed by tb_invalidate_phys_addr */
+ tb_invalidate_phys_addr(cpu->cpu_ases[asidx].as,
+ phys | (pc & ~TARGET_PAGE_MASK));
+ }
+}
+#endif
#if defined(CONFIG_USER_ONLY)
void cpu_watchpoint_remove_all(CPUState *cpu, int mask)
if (block && addr - block->offset < block->max_length) {
return block;
}
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
if (addr - block->offset < block->max_length) {
goto found;
}
return dirty;
}
+DirtyBitmapSnapshot *cpu_physical_memory_snapshot_and_clear_dirty
+ (ram_addr_t start, ram_addr_t length, unsigned client)
+{
+ DirtyMemoryBlocks *blocks;
+ unsigned long align = 1UL << (TARGET_PAGE_BITS + BITS_PER_LEVEL);
+ ram_addr_t first = QEMU_ALIGN_DOWN(start, align);
+ ram_addr_t last = QEMU_ALIGN_UP(start + length, align);
+ DirtyBitmapSnapshot *snap;
+ unsigned long page, end, dest;
+
+ snap = g_malloc0(sizeof(*snap) +
+ ((last - first) >> (TARGET_PAGE_BITS + 3)));
+ snap->start = first;
+ snap->end = last;
+
+ page = first >> TARGET_PAGE_BITS;
+ end = last >> TARGET_PAGE_BITS;
+ dest = 0;
+
+ rcu_read_lock();
+
+ blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);
+
+ while (page < end) {
+ unsigned long idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+ unsigned long offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+ unsigned long num = MIN(end - page, DIRTY_MEMORY_BLOCK_SIZE - offset);
+
+ assert(QEMU_IS_ALIGNED(offset, (1 << BITS_PER_LEVEL)));
+ assert(QEMU_IS_ALIGNED(num, (1 << BITS_PER_LEVEL)));
+ offset >>= BITS_PER_LEVEL;
+
+ bitmap_copy_and_clear_atomic(snap->dirty + dest,
+ blocks->blocks[idx] + offset,
+ num);
+ page += num;
+ dest += num >> BITS_PER_LEVEL;
+ }
+
+ rcu_read_unlock();
+
+ if (tcg_enabled()) {
+ tlb_reset_dirty_range_all(start, length);
+ }
+
+ return snap;
+}
+
+bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap,
+ ram_addr_t start,
+ ram_addr_t length)
+{
+ unsigned long page, end;
+
+ assert(start >= snap->start);
+ assert(start + length <= snap->end);
+
+ end = TARGET_PAGE_ALIGN(start + length - snap->start) >> TARGET_PAGE_BITS;
+ page = (start - snap->start) >> TARGET_PAGE_BITS;
+
+ while (page < end) {
+ if (test_bit(page, snap->dirty)) {
+ return true;
+ }
+ page++;
+ }
+ return false;
+}
+
/* Called from RCU critical section */
hwaddr memory_region_section_get_iotlb(CPUState *cpu,
MemoryRegionSection *section,
} else {
AddressSpaceDispatch *d;
- d = atomic_rcu_read(§ion->address_space->dispatch);
+ d = flatview_to_dispatch(section->fv);
iotlb = section - d->map.sections;
iotlb += xlat;
}
static int subpage_register (subpage_t *mmio, uint32_t start, uint32_t end,
uint16_t section);
-static subpage_t *subpage_init(AddressSpace *as, hwaddr base);
+static subpage_t *subpage_init(FlatView *fv, hwaddr base);
static void *(*phys_mem_alloc)(size_t size, uint64_t *align) =
qemu_anon_ram_alloc;
g_free(map->nodes);
}
-static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *section)
+static void register_subpage(FlatView *fv, MemoryRegionSection *section)
{
+ AddressSpaceDispatch *d = flatview_to_dispatch(fv);
subpage_t *subpage;
hwaddr base = section->offset_within_address_space
& TARGET_PAGE_MASK;
- MemoryRegionSection *existing = phys_page_find(d->phys_map, base,
- d->map.nodes, d->map.sections);
+ MemoryRegionSection *existing = phys_page_find(d, base);
MemoryRegionSection subsection = {
.offset_within_address_space = base,
.size = int128_make64(TARGET_PAGE_SIZE),
assert(existing->mr->subpage || existing->mr == &io_mem_unassigned);
if (!(existing->mr->subpage)) {
- subpage = subpage_init(d->as, base);
- subsection.address_space = d->as;
+ subpage = subpage_init(fv, base);
+ subsection.fv = fv;
subsection.mr = &subpage->iomem;
phys_page_set(d, base >> TARGET_PAGE_BITS, 1,
phys_section_add(&d->map, &subsection));
}
-static void register_multipage(AddressSpaceDispatch *d,
+static void register_multipage(FlatView *fv,
MemoryRegionSection *section)
{
+ AddressSpaceDispatch *d = flatview_to_dispatch(fv);
hwaddr start_addr = section->offset_within_address_space;
uint16_t section_index = phys_section_add(&d->map, section);
uint64_t num_pages = int128_get64(int128_rshift(section->size,
phys_page_set(d, start_addr >> TARGET_PAGE_BITS, num_pages, section_index);
}
-static void mem_add(MemoryListener *listener, MemoryRegionSection *section)
+void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section)
{
- AddressSpace *as = container_of(listener, AddressSpace, dispatch_listener);
- AddressSpaceDispatch *d = as->next_dispatch;
MemoryRegionSection now = *section, remain = *section;
Int128 page_size = int128_make64(TARGET_PAGE_SIZE);
- now.offset_within_address_space;
now.size = int128_min(int128_make64(left), now.size);
- register_subpage(d, &now);
+ register_subpage(fv, &now);
} else {
now.size = int128_zero();
}
remain.offset_within_region += int128_get64(now.size);
now = remain;
if (int128_lt(remain.size, page_size)) {
- register_subpage(d, &now);
+ register_subpage(fv, &now);
} else if (remain.offset_within_address_space & ~TARGET_PAGE_MASK) {
now.size = page_size;
- register_subpage(d, &now);
+ register_subpage(fv, &now);
} else {
now.size = int128_and(now.size, int128_neg(page_size));
- register_multipage(d, &now);
+ register_multipage(fv, &now);
}
}
}
qemu_mutex_unlock(&ram_list.mutex);
}
+void ram_block_dump(Monitor *mon)
+{
+ RAMBlock *block;
+ char *psize;
+
+ rcu_read_lock();
+ monitor_printf(mon, "%24s %8s %18s %18s %18s\n",
+ "Block Name", "PSize", "Offset", "Used", "Total");
+ RAMBLOCK_FOREACH(block) {
+ psize = size_to_str(block->page_size);
+ monitor_printf(mon, "%24s %8s 0x%016" PRIx64 " 0x%016" PRIx64
+ " 0x%016" PRIx64 "\n", block->idstr, psize,
+ (uint64_t)block->offset,
+ (uint64_t)block->used_length,
+ (uint64_t)block->max_length);
+ g_free(psize);
+ }
+ rcu_read_unlock();
+}
+
+#ifdef __linux__
+/*
+ * FIXME TOCTTOU: this iterates over memory backends' mem-path, which
+ * may or may not name the same files / on the same filesystem now as
+ * when we actually open and map them. Iterate over the file
+ * descriptors instead, and use qemu_fd_getpagesize().
+ */
+static int find_max_supported_pagesize(Object *obj, void *opaque)
+{
+ char *mem_path;
+ long *hpsize_min = opaque;
+
+ if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
+ mem_path = object_property_get_str(obj, "mem-path", NULL);
+ if (mem_path) {
+ long hpsize = qemu_mempath_getpagesize(mem_path);
+ if (hpsize < *hpsize_min) {
+ *hpsize_min = hpsize;
+ }
+ } else {
+ *hpsize_min = getpagesize();
+ }
+ }
+
+ return 0;
+}
+
+long qemu_getrampagesize(void)
+{
+ long hpsize = LONG_MAX;
+ long mainrampagesize;
+ Object *memdev_root;
+
+ if (mem_path) {
+ mainrampagesize = qemu_mempath_getpagesize(mem_path);
+ } else {
+ mainrampagesize = getpagesize();
+ }
+
+ /* it's possible we have memory-backend objects with
+ * hugepage-backed RAM. these may get mapped into system
+ * address space via -numa parameters or memory hotplug
+ * hooks. we want to take these into account, but we
+ * also want to make sure these supported hugepage
+ * sizes are applicable across the entire range of memory
+ * we may boot from, so we take the min across all
+ * backends, and assume normal pages in cases where a
+ * backend isn't backed by hugepages.
+ */
+ memdev_root = object_resolve_path("/objects", NULL);
+ if (memdev_root) {
+ object_child_foreach(memdev_root, find_max_supported_pagesize, &hpsize);
+ }
+ if (hpsize == LONG_MAX) {
+ /* No additional memory regions found ==> Report main RAM page size */
+ return mainrampagesize;
+ }
+
+ /* If NUMA is disabled or the NUMA nodes are not backed with a
+ * memory-backend, then there is at least one node using "normal" RAM,
+ * so if its page size is smaller we have got to report that size instead.
+ */
+ if (hpsize > mainrampagesize &&
+ (nb_numa_nodes == 0 || numa_info[0].node_memdev == NULL)) {
+ static bool warned;
+ if (!warned) {
+ error_report("Huge page support disabled (n/a for main memory).");
+ warned = true;
+ }
+ return mainrampagesize;
+ }
+
+ return hpsize;
+}
+#else
+long qemu_getrampagesize(void)
+{
+ return getpagesize();
+}
+#endif
+
#ifdef __linux__
static int64_t get_file_size(int fd)
{
return size;
}
-static void *file_ram_alloc(RAMBlock *block,
- ram_addr_t memory,
- const char *path,
- Error **errp)
+static int file_ram_open(const char *path,
+ const char *region_name,
+ bool *created,
+ Error **errp)
{
- bool unlink_on_error = false;
char *filename;
char *sanitized_name;
char *c;
- void *area = MAP_FAILED;
int fd = -1;
- int64_t file_size;
-
- if (kvm_enabled() && !kvm_has_sync_mmu()) {
- error_setg(errp,
- "host lacks kvm mmu notifiers, -mem-path unsupported");
- return NULL;
- }
+ *created = false;
for (;;) {
fd = open(path, O_RDWR);
if (fd >= 0) {
/* @path names a file that doesn't exist, create it */
fd = open(path, O_RDWR | O_CREAT | O_EXCL, 0644);
if (fd >= 0) {
- unlink_on_error = true;
+ *created = true;
break;
}
} else if (errno == EISDIR) {
/* @path names a directory, create a file there */
/* Make name safe to use with mkstemp by replacing '/' with '_'. */
- sanitized_name = g_strdup(memory_region_name(block->mr));
+ sanitized_name = g_strdup(region_name);
for (c = sanitized_name; *c != '\0'; c++) {
if (*c == '/') {
*c = '_';
error_setg_errno(errp, errno,
"can't open backing store %s for guest RAM",
path);
- goto error;
+ return -1;
}
/*
* Try again on EINTR and EEXIST. The latter happens when
*/
}
+ return fd;
+}
+
+static void *file_ram_alloc(RAMBlock *block,
+ ram_addr_t memory,
+ int fd,
+ bool truncate,
+ Error **errp)
+{
+ void *area;
+
block->page_size = qemu_fd_getpagesize(fd);
block->mr->align = block->page_size;
#if defined(__s390x__)
}
#endif
- file_size = get_file_size(fd);
-
if (memory < block->page_size) {
error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
"or larger than page size 0x%zx",
memory, block->page_size);
- goto error;
- }
-
- if (file_size > 0 && file_size < memory) {
- error_setg(errp, "backing store %s size 0x%" PRIx64
- " does not match 'size' option 0x" RAM_ADDR_FMT,
- path, file_size, memory);
- goto error;
+ return NULL;
}
memory = ROUND_UP(memory, block->page_size);
* those labels. Therefore, extending the non-empty backend file
* is disabled as well.
*/
- if (!file_size && ftruncate(fd, memory)) {
+ if (truncate && ftruncate(fd, memory)) {
perror("ftruncate");
}
if (area == MAP_FAILED) {
error_setg_errno(errp, errno,
"unable to map backing store for guest RAM");
- goto error;
+ return NULL;
}
if (mem_prealloc) {
- os_mem_prealloc(fd, area, memory, errp);
+ os_mem_prealloc(fd, area, memory, smp_cpus, errp);
if (errp && *errp) {
- goto error;
+ qemu_ram_munmap(area, memory);
+ return NULL;
}
}
block->fd = fd;
return area;
-
-error:
- if (area != MAP_FAILED) {
- qemu_ram_munmap(area, memory);
- }
- if (unlink_on_error) {
- unlink(path);
- }
- if (fd != -1) {
- close(fd);
- }
- return NULL;
}
#endif
return 0;
}
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
ram_addr_t end, next = RAM_ADDR_MAX;
end = block->offset + block->max_length;
- QLIST_FOREACH_RCU(next_block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(next_block) {
if (next_block->offset >= end) {
next = MIN(next, next_block->offset);
}
return offset;
}
-ram_addr_t last_ram_offset(void)
+unsigned long last_ram_page(void)
{
RAMBlock *block;
ram_addr_t last = 0;
rcu_read_lock();
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
last = MAX(last, block->offset + block->max_length);
}
rcu_read_unlock();
- return last;
+ return last >> TARGET_PAGE_BITS;
}
static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
return rb->idstr;
}
+bool qemu_ram_is_shared(RAMBlock *rb)
+{
+ return rb->flags & RAM_SHARED;
+}
+
/* Called with iothread lock held. */
void qemu_ram_set_idstr(RAMBlock *new_block, const char *name, DeviceState *dev)
{
pstrcat(new_block->idstr, sizeof(new_block->idstr), name);
rcu_read_lock();
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
if (block != new_block &&
!strcmp(block->idstr, new_block->idstr)) {
fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",
return rb->page_size;
}
+/* Returns the largest size of page in use */
+size_t qemu_ram_pagesize_largest(void)
+{
+ RAMBlock *block;
+ size_t largest = 0;
+
+ RAMBLOCK_FOREACH(block) {
+ largest = MAX(largest, qemu_ram_pagesize(block));
+ }
+
+ return largest;
+}
+
static int memory_try_enable_merging(void *addr, size_t len)
{
if (!machine_mem_merge(current_machine)) {
ram_addr_t old_ram_size, new_ram_size;
Error *err = NULL;
- old_ram_size = last_ram_offset() >> TARGET_PAGE_BITS;
+ old_ram_size = last_ram_page();
qemu_mutex_lock_ramlist();
new_block->offset = find_ram_offset(new_block->max_length);
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);
dirty_memory_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.
*/
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
last_block = block;
if (block->max_length < new_block->max_length) {
break;
}
#ifdef __linux__
-RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
- bool share, const char *mem_path,
- Error **errp)
+RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
+ bool share, int fd,
+ Error **errp)
{
RAMBlock *new_block;
Error *local_err = NULL;
+ int64_t file_size;
if (xen_enabled()) {
error_setg(errp, "-mem-path not supported with Xen");
return NULL;
}
+ if (kvm_enabled() && !kvm_has_sync_mmu()) {
+ error_setg(errp,
+ "host lacks kvm mmu notifiers, -mem-path unsupported");
+ return NULL;
+ }
+
if (phys_mem_alloc != qemu_anon_ram_alloc) {
/*
* file_ram_alloc() needs to allocate just like
}
size = HOST_PAGE_ALIGN(size);
+ file_size = get_file_size(fd);
+ if (file_size > 0 && file_size < size) {
+ error_setg(errp, "backing store %s size 0x%" PRIx64
+ " does not match 'size' option 0x" RAM_ADDR_FMT,
+ mem_path, file_size, size);
+ return NULL;
+ }
+
new_block = g_malloc0(sizeof(*new_block));
new_block->mr = mr;
new_block->used_length = size;
new_block->max_length = size;
new_block->flags = share ? RAM_SHARED : 0;
- new_block->host = file_ram_alloc(new_block, size,
- mem_path, errp);
+ new_block->host = file_ram_alloc(new_block, size, fd, !file_size, errp);
if (!new_block->host) {
g_free(new_block);
return NULL;
return NULL;
}
return new_block;
+
+}
+
+
+RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
+ bool share, const char *mem_path,
+ Error **errp)
+{
+ int fd;
+ bool created;
+ RAMBlock *block;
+
+ fd = file_ram_open(mem_path, memory_region_name(mr), &created, errp);
+ if (fd < 0) {
+ return NULL;
+ }
+
+ block = qemu_ram_alloc_from_fd(size, mr, share, fd, errp);
+ if (!block) {
+ if (created) {
+ unlink(mem_path);
+ }
+ close(fd);
+ return NULL;
+ }
+
+ return block;
}
#endif
int flags;
void *area, *vaddr;
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
offset = addr - block->offset;
if (offset < block->max_length) {
vaddr = ramblock_ptr(block, offset);
* In that case just map until the end of the page.
*/
if (block->offset == 0) {
- return xen_map_cache(addr, 0, 0);
+ return xen_map_cache(addr, 0, 0, false);
}
- block->host = xen_map_cache(block->offset, block->max_length, 1);
+ block->host = xen_map_cache(block->offset, block->max_length, 1, false);
}
return ramblock_ptr(block, addr);
}
* Called within RCU critical section.
*/
static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
- hwaddr *size)
+ hwaddr *size, bool lock)
{
RAMBlock *block = ram_block;
if (*size == 0) {
* In that case just map the requested area.
*/
if (block->offset == 0) {
- return xen_map_cache(addr, *size, 1);
+ return xen_map_cache(addr, *size, lock, lock);
}
- block->host = xen_map_cache(block->offset, block->max_length, 1);
+ block->host = xen_map_cache(block->offset, block->max_length, 1, lock);
}
return ramblock_ptr(block, addr);
goto found;
}
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
/* This case append when the block is not mapped. */
if (block->host == NULL) {
continue;
{
RAMBlock *block;
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
if (!strcmp(name, block->idstr)) {
return block;
}
return block->offset + offset;
}
-/* Called within RCU critical section. */
-static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
- uint64_t val, unsigned size)
+/* Called within RCU critical section. */
+void memory_notdirty_write_prepare(NotDirtyInfo *ndi,
+ CPUState *cpu,
+ vaddr mem_vaddr,
+ ram_addr_t ram_addr,
+ unsigned size)
{
- bool locked = false;
+ ndi->cpu = cpu;
+ ndi->ram_addr = ram_addr;
+ ndi->mem_vaddr = mem_vaddr;
+ ndi->size = size;
+ ndi->locked = false;
+ assert(tcg_enabled());
if (!cpu_physical_memory_get_dirty_flag(ram_addr, DIRTY_MEMORY_CODE)) {
- locked = true;
+ ndi->locked = true;
tb_lock();
tb_invalidate_phys_page_fast(ram_addr, size);
}
+}
+
+/* Called within RCU critical section. */
+void memory_notdirty_write_complete(NotDirtyInfo *ndi)
+{
+ if (ndi->locked) {
+ tb_unlock();
+ }
+
+ /* Set both VGA and migration bits for simplicity and to remove
+ * the notdirty callback faster.
+ */
+ cpu_physical_memory_set_dirty_range(ndi->ram_addr, ndi->size,
+ DIRTY_CLIENTS_NOCODE);
+ /* we remove the notdirty callback only if the code has been
+ flushed */
+ if (!cpu_physical_memory_is_clean(ndi->ram_addr)) {
+ tlb_set_dirty(ndi->cpu, ndi->mem_vaddr);
+ }
+}
+
+/* Called within RCU critical section. */
+static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
+ uint64_t val, unsigned size)
+{
+ NotDirtyInfo ndi;
+
+ memory_notdirty_write_prepare(&ndi, current_cpu, current_cpu->mem_io_vaddr,
+ ram_addr, size);
+
switch (size) {
case 1:
stb_p(qemu_map_ram_ptr(NULL, ram_addr), val);
case 4:
stl_p(qemu_map_ram_ptr(NULL, ram_addr), val);
break;
+ case 8:
+ stq_p(qemu_map_ram_ptr(NULL, ram_addr), val);
+ break;
default:
abort();
}
-
- if (locked) {
- tb_unlock();
- }
-
- /* Set both VGA and migration bits for simplicity and to remove
- * the notdirty callback faster.
- */
- cpu_physical_memory_set_dirty_range(ram_addr, size,
- DIRTY_CLIENTS_NOCODE);
- /* we remove the notdirty callback only if the code has been
- flushed */
- if (!cpu_physical_memory_is_clean(ram_addr)) {
- tlb_set_dirty(current_cpu, current_cpu->mem_io_vaddr);
- }
+ memory_notdirty_write_complete(&ndi);
}
static bool notdirty_mem_accepts(void *opaque, hwaddr addr,
.write = notdirty_mem_write,
.valid.accepts = notdirty_mem_accepts,
.endianness = DEVICE_NATIVE_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = false,
+ },
+ .impl = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = false,
+ },
};
/* Generate a debug exception if a watchpoint has been hit. */
{
CPUState *cpu = current_cpu;
CPUClass *cc = CPU_GET_CLASS(cpu);
- CPUArchState *env = cpu->env_ptr;
- target_ulong pc, cs_base;
target_ulong vaddr;
CPUWatchpoint *wp;
- uint32_t cpu_flags;
+ assert(tcg_enabled());
if (cpu->watchpoint_hit) {
/* We re-entered the check after replacing the TB. Now raise
* the debug interrupt so that is will trigger after the
return;
}
vaddr = (cpu->mem_io_vaddr & TARGET_PAGE_MASK) + offset;
+ vaddr = cc->adjust_watchpoint_address(cpu, vaddr, len);
QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
if (cpu_watchpoint_address_matches(wp, vaddr, len)
&& (wp->flags & flags)) {
}
cpu->watchpoint_hit = wp;
- /* The tb_lock will be reset when cpu_loop_exit or
- * cpu_loop_exit_noexc longjmp back into the cpu_exec
- * main loop.
+ /* Both tb_lock and iothread_mutex will be reset when
+ * cpu_loop_exit or cpu_loop_exit_noexc longjmp
+ * back into the cpu_exec main loop.
*/
tb_lock();
tb_check_watchpoint(cpu);
cpu->exception_index = EXCP_DEBUG;
cpu_loop_exit(cpu);
} else {
- cpu_get_tb_cpu_state(env, &pc, &cs_base, &cpu_flags);
- tb_gen_code(cpu, pc, cs_base, cpu_flags, 1);
+ /* Force execution of one insn next time. */
+ cpu->cflags_next_tb = 1 | curr_cflags();
cpu_loop_exit_noexc(cpu);
}
}
case 4:
data = address_space_ldl(as, addr, attrs, &res);
break;
+ case 8:
+ data = address_space_ldq(as, addr, attrs, &res);
+ break;
default: abort();
}
*pdata = data;
case 4:
address_space_stl(as, addr, val, attrs, &res);
break;
+ case 8:
+ address_space_stq(as, addr, val, attrs, &res);
+ break;
default: abort();
}
return res;
.read_with_attrs = watch_mem_read,
.write_with_attrs = watch_mem_write,
.endianness = DEVICE_NATIVE_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = false,
+ },
+ .impl = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = false,
+ },
};
+static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs,
+ const uint8_t *buf, int len);
+static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len,
+ bool is_write);
+
static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data,
unsigned len, MemTxAttrs attrs)
{
printf("%s: subpage %p len %u addr " TARGET_FMT_plx "\n", __func__,
subpage, len, addr);
#endif
- res = address_space_read(subpage->as, addr + subpage->base,
- attrs, buf, len);
+ res = flatview_read(subpage->fv, addr + subpage->base, attrs, buf, len);
if (res) {
return res;
}
default:
abort();
}
- return address_space_write(subpage->as, addr + subpage->base,
- attrs, buf, len);
+ return flatview_write(subpage->fv, addr + subpage->base, attrs, buf, len);
}
static bool subpage_accepts(void *opaque, hwaddr addr,
__func__, subpage, is_write ? 'w' : 'r', len, addr);
#endif
- return address_space_access_valid(subpage->as, addr + subpage->base,
- len, is_write);
+ return flatview_access_valid(subpage->fv, addr + subpage->base,
+ len, is_write);
}
static const MemoryRegionOps subpage_ops = {
return 0;
}
-static subpage_t *subpage_init(AddressSpace *as, hwaddr base)
+static subpage_t *subpage_init(FlatView *fv, hwaddr base)
{
subpage_t *mmio;
mmio = g_malloc0(sizeof(subpage_t) + TARGET_PAGE_SIZE * sizeof(uint16_t));
- mmio->as = as;
+ mmio->fv = fv;
mmio->base = base;
memory_region_init_io(&mmio->iomem, NULL, &subpage_ops, mmio,
NULL, TARGET_PAGE_SIZE);
return mmio;
}
-static uint16_t dummy_section(PhysPageMap *map, AddressSpace *as,
- MemoryRegion *mr)
+static uint16_t dummy_section(PhysPageMap *map, FlatView *fv, MemoryRegion *mr)
{
- assert(as);
+ assert(fv);
MemoryRegionSection section = {
- .address_space = as,
+ .fv = fv,
.mr = mr,
.offset_within_address_space = 0,
.offset_within_region = 0,
return phys_section_add(map, §ion);
}
+static void readonly_mem_write(void *opaque, hwaddr addr,
+ uint64_t val, unsigned size)
+{
+ /* Ignore any write to ROM. */
+}
+
+static bool readonly_mem_accepts(void *opaque, hwaddr addr,
+ unsigned size, bool is_write)
+{
+ return is_write;
+}
+
+/* This will only be used for writes, because reads are special cased
+ * to directly access the underlying host ram.
+ */
+static const MemoryRegionOps readonly_mem_ops = {
+ .write = readonly_mem_write,
+ .valid.accepts = readonly_mem_accepts,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = false,
+ },
+ .impl = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = false,
+ },
+};
+
MemoryRegion *iotlb_to_region(CPUState *cpu, hwaddr index, MemTxAttrs attrs)
{
int asidx = cpu_asidx_from_attrs(cpu, attrs);
static void io_mem_init(void)
{
- memory_region_init_io(&io_mem_rom, NULL, &unassigned_mem_ops, NULL, NULL, UINT64_MAX);
+ memory_region_init_io(&io_mem_rom, NULL, &readonly_mem_ops,
+ NULL, NULL, UINT64_MAX);
memory_region_init_io(&io_mem_unassigned, NULL, &unassigned_mem_ops, NULL,
NULL, UINT64_MAX);
+
+ /* io_mem_notdirty calls tb_invalidate_phys_page_fast,
+ * which can be called without the iothread mutex.
+ */
memory_region_init_io(&io_mem_notdirty, NULL, ¬dirty_mem_ops, NULL,
NULL, UINT64_MAX);
+ memory_region_clear_global_locking(&io_mem_notdirty);
+
memory_region_init_io(&io_mem_watch, NULL, &watch_mem_ops, NULL,
NULL, UINT64_MAX);
}
-static void mem_begin(MemoryListener *listener)
+AddressSpaceDispatch *address_space_dispatch_new(FlatView *fv)
{
- AddressSpace *as = container_of(listener, AddressSpace, dispatch_listener);
AddressSpaceDispatch *d = g_new0(AddressSpaceDispatch, 1);
uint16_t n;
- n = dummy_section(&d->map, as, &io_mem_unassigned);
+ n = dummy_section(&d->map, fv, &io_mem_unassigned);
assert(n == PHYS_SECTION_UNASSIGNED);
- n = dummy_section(&d->map, as, &io_mem_notdirty);
+ n = dummy_section(&d->map, fv, &io_mem_notdirty);
assert(n == PHYS_SECTION_NOTDIRTY);
- n = dummy_section(&d->map, as, &io_mem_rom);
+ n = dummy_section(&d->map, fv, &io_mem_rom);
assert(n == PHYS_SECTION_ROM);
- n = dummy_section(&d->map, as, &io_mem_watch);
+ n = dummy_section(&d->map, fv, &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;
+
+ return d;
}
-static void address_space_dispatch_free(AddressSpaceDispatch *d)
+void address_space_dispatch_free(AddressSpaceDispatch *d)
{
phys_sections_free(&d->map);
g_free(d);
}
-static void mem_commit(MemoryListener *listener)
-{
- AddressSpace *as = container_of(listener, AddressSpace, dispatch_listener);
- AddressSpaceDispatch *cur = as->dispatch;
- AddressSpaceDispatch *next = as->next_dispatch;
-
- phys_page_compact_all(next, next->map.nodes_nb);
-
- atomic_rcu_set(&as->dispatch, next);
- if (cur) {
- call_rcu(cur, address_space_dispatch_free, rcu);
- }
-}
-
static void tcg_commit(MemoryListener *listener)
{
CPUAddressSpace *cpuas;
* We reload the dispatch pointer now because cpu_reloading_memory_map()
* may have split the RCU critical section.
*/
- d = atomic_rcu_read(&cpuas->as->dispatch);
+ d = address_space_to_dispatch(cpuas->as);
atomic_rcu_set(&cpuas->memory_dispatch, d);
tlb_flush(cpuas->cpu);
}
-void address_space_init_dispatch(AddressSpace *as)
-{
- as->dispatch = NULL;
- as->dispatch_listener = (MemoryListener) {
- .begin = mem_begin,
- .commit = mem_commit,
- .region_add = mem_add,
- .region_nop = mem_add,
- .priority = 0,
- };
- memory_listener_register(&as->dispatch_listener, as);
-}
-
-void address_space_unregister(AddressSpace *as)
-{
- memory_listener_unregister(&as->dispatch_listener);
-}
-
-void address_space_destroy_dispatch(AddressSpace *as)
-{
- AddressSpaceDispatch *d = as->dispatch;
-
- atomic_rcu_set(&as->dispatch, NULL);
- if (d) {
- call_rcu(d, address_space_dispatch_free, rcu);
- }
-}
-
static void memory_map_init(void)
{
system_memory = g_malloc(sizeof(*system_memory));
cpu_physical_memory_range_includes_clean(addr, length, dirty_log_mask);
}
if (dirty_log_mask & (1 << DIRTY_MEMORY_CODE)) {
+ assert(tcg_enabled());
tb_lock();
tb_invalidate_phys_range(addr, addr + length);
tb_unlock();
}
/* Called within RCU critical section. */
-static MemTxResult address_space_write_continue(AddressSpace *as, hwaddr addr,
- MemTxAttrs attrs,
- const uint8_t *buf,
- int len, hwaddr addr1,
- hwaddr l, MemoryRegion *mr)
+static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr,
+ MemTxAttrs attrs,
+ const uint8_t *buf,
+ int len, hwaddr addr1,
+ hwaddr l, MemoryRegion *mr)
{
uint8_t *ptr;
uint64_t val;
}
} else {
/* RAM case */
- ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
+ ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false);
memcpy(ptr, buf, l);
invalidate_and_set_dirty(mr, addr1, l);
}
}
l = len;
- mr = address_space_translate(as, addr, &addr1, &l, true);
+ mr = flatview_translate(fv, addr, &addr1, &l, true);
}
return result;
}
-MemTxResult address_space_write(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
- const uint8_t *buf, int len)
+static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs,
+ const uint8_t *buf, int len)
{
hwaddr l;
hwaddr addr1;
if (len > 0) {
rcu_read_lock();
l = len;
- mr = address_space_translate(as, addr, &addr1, &l, true);
- result = address_space_write_continue(as, addr, attrs, buf, len,
- addr1, l, mr);
+ mr = flatview_translate(fv, addr, &addr1, &l, true);
+ result = flatview_write_continue(fv, addr, attrs, buf, len,
+ addr1, l, mr);
rcu_read_unlock();
}
return result;
}
+MemTxResult address_space_write(AddressSpace *as, hwaddr addr,
+ MemTxAttrs attrs,
+ const uint8_t *buf, int len)
+{
+ return flatview_write(address_space_to_flatview(as), addr, attrs, buf, len);
+}
+
/* Called within RCU critical section. */
-MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
- MemTxAttrs attrs, uint8_t *buf,
- int len, hwaddr addr1, hwaddr l,
- MemoryRegion *mr)
+MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr,
+ MemTxAttrs attrs, uint8_t *buf,
+ int len, hwaddr addr1, hwaddr l,
+ MemoryRegion *mr)
{
uint8_t *ptr;
uint64_t val;
}
} else {
/* RAM case */
- ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
+ ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false);
memcpy(buf, ptr, l);
}
}
l = len;
- mr = address_space_translate(as, addr, &addr1, &l, false);
+ mr = flatview_translate(fv, addr, &addr1, &l, false);
}
return result;
}
-MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
- MemTxAttrs attrs, uint8_t *buf, int len)
+MemTxResult flatview_read_full(FlatView *fv, hwaddr addr,
+ MemTxAttrs attrs, uint8_t *buf, int len)
{
hwaddr l;
hwaddr addr1;
if (len > 0) {
rcu_read_lock();
l = len;
- mr = address_space_translate(as, addr, &addr1, &l, false);
- result = address_space_read_continue(as, addr, attrs, buf, len,
- addr1, l, mr);
+ mr = flatview_translate(fv, addr, &addr1, &l, false);
+ result = flatview_read_continue(fv, addr, attrs, buf, len,
+ addr1, l, mr);
rcu_read_unlock();
}
return result;
}
-MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
- uint8_t *buf, int len, bool is_write)
+static MemTxResult flatview_rw(FlatView *fv, hwaddr addr, MemTxAttrs attrs,
+ uint8_t *buf, int len, bool is_write)
{
if (is_write) {
- return address_space_write(as, addr, attrs, (uint8_t *)buf, len);
+ return flatview_write(fv, addr, attrs, (uint8_t *)buf, len);
} else {
- return address_space_read(as, addr, attrs, (uint8_t *)buf, len);
+ return flatview_read(fv, addr, attrs, (uint8_t *)buf, len);
}
}
+MemTxResult address_space_rw(AddressSpace *as, hwaddr addr,
+ MemTxAttrs attrs, uint8_t *buf,
+ int len, bool is_write)
+{
+ return flatview_rw(address_space_to_flatview(as),
+ addr, attrs, buf, len, is_write);
+}
+
void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf,
int len, int is_write)
{
qemu_mutex_unlock(&map_client_list_lock);
}
-bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_write)
+static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len,
+ bool is_write)
{
MemoryRegion *mr;
hwaddr l, xlat;
rcu_read_lock();
while (len > 0) {
l = len;
- mr = address_space_translate(as, addr, &xlat, &l, is_write);
+ mr = flatview_translate(fv, addr, &xlat, &l, is_write);
if (!memory_access_is_direct(mr, is_write)) {
l = memory_access_size(mr, l, addr);
if (!memory_region_access_valid(mr, xlat, l, is_write)) {
return true;
}
+bool address_space_access_valid(AddressSpace *as, hwaddr addr,
+ int len, bool is_write)
+{
+ return flatview_access_valid(address_space_to_flatview(as),
+ addr, len, is_write);
+}
+
static hwaddr
-address_space_extend_translation(AddressSpace *as, hwaddr addr, hwaddr target_len,
+flatview_extend_translation(FlatView *fv, hwaddr addr,
+ hwaddr target_len,
MemoryRegion *mr, hwaddr base, hwaddr len,
bool is_write)
{
}
len = target_len;
- this_mr = address_space_translate(as, addr, &xlat, &len, is_write);
+ this_mr = flatview_translate(fv, addr, &xlat,
+ &len, is_write);
if (this_mr != mr || xlat != base + done) {
return done;
}
hwaddr l, xlat;
MemoryRegion *mr;
void *ptr;
+ FlatView *fv = address_space_to_flatview(as);
if (len == 0) {
return NULL;
l = len;
rcu_read_lock();
- mr = address_space_translate(as, addr, &xlat, &l, is_write);
+ mr = flatview_translate(fv, addr, &xlat, &l, is_write);
if (!memory_access_is_direct(mr, is_write)) {
if (atomic_xchg(&bounce.in_use, true)) {
memory_region_ref(mr);
bounce.mr = mr;
if (!is_write) {
- address_space_read(as, addr, MEMTXATTRS_UNSPECIFIED,
+ flatview_read(fv, addr, MEMTXATTRS_UNSPECIFIED,
bounce.buffer, l);
}
memory_region_ref(mr);
- *plen = address_space_extend_translation(as, addr, len, mr, xlat, l, is_write);
- ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen);
+ *plen = flatview_extend_translation(fv, addr, len, mr, xlat,
+ l, is_write);
+ ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen, true);
rcu_read_unlock();
return ptr;
hwaddr len,
bool is_write)
{
- hwaddr l, xlat;
- MemoryRegion *mr;
- void *ptr;
-
- assert(len > 0);
-
- l = len;
- mr = address_space_translate(as, addr, &xlat, &l, is_write);
- if (!memory_access_is_direct(mr, is_write)) {
- return -EINVAL;
- }
-
- l = address_space_extend_translation(as, addr, len, mr, xlat, l, is_write);
- ptr = qemu_ram_ptr_length(mr->ram_block, xlat, &l);
-
- cache->xlat = xlat;
- cache->is_write = is_write;
- cache->mr = mr;
- cache->ptr = ptr;
- cache->len = l;
- memory_region_ref(cache->mr);
-
- return l;
+ cache->len = len;
+ cache->as = as;
+ cache->xlat = addr;
+ return len;
}
void address_space_cache_invalidate(MemoryRegionCache *cache,
hwaddr addr,
hwaddr access_len)
{
- assert(cache->is_write);
- invalidate_and_set_dirty(cache->mr, addr + cache->xlat, access_len);
}
void address_space_cache_destroy(MemoryRegionCache *cache)
{
- if (!cache->mr) {
- return;
- }
-
- if (xen_enabled()) {
- xen_invalidate_map_cache_entry(cache->ptr);
- }
- memory_region_unref(cache->mr);
-}
-
-/* Called from RCU critical section. This function has the same
- * semantics as address_space_translate, but it only works on a
- * predefined range of a MemoryRegion that was mapped with
- * address_space_cache_init.
- */
-static inline MemoryRegion *address_space_translate_cached(
- MemoryRegionCache *cache, hwaddr addr, hwaddr *xlat,
- hwaddr *plen, bool is_write)
-{
- assert(addr < cache->len && *plen <= cache->len - addr);
- *xlat = addr + cache->xlat;
- return cache->mr;
+ cache->as = NULL;
}
#define ARG1_DECL MemoryRegionCache *cache
#define ARG1 cache
#define SUFFIX _cached
-#define TRANSLATE(...) address_space_translate_cached(cache, __VA_ARGS__)
+#define TRANSLATE(addr, ...) \
+ address_space_translate(cache->as, cache->xlat + (addr), __VA_ARGS__)
#define IS_DIRECT(mr, is_write) true
-#define MAP_RAM(mr, ofs) (cache->ptr + (ofs - cache->xlat))
-#define INVALIDATE(mr, ofs, len) ((void)0)
-#define RCU_READ_LOCK() ((void)0)
-#define RCU_READ_UNLOCK() ((void)0)
+#define MAP_RAM(mr, ofs) qemu_map_ram_ptr((mr)->ram_block, ofs)
+#define INVALIDATE(mr, ofs, len) invalidate_and_set_dirty(mr, ofs, len)
+#define RCU_READ_LOCK() rcu_read_lock()
+#define RCU_READ_UNLOCK() rcu_read_unlock()
#include "memory_ldst.inc.c"
/* virtual memory access for debug (includes writing to ROM) */
hwaddr phys_addr;
target_ulong page;
+ cpu_synchronize_state(cpu);
while (len > 0) {
int asidx;
MemTxAttrs attrs;
* Allows code that needs to deal with migration bitmaps etc to still be built
* target independent.
*/
-size_t qemu_target_page_bits(void)
+size_t qemu_target_page_size(void)
+{
+ return TARGET_PAGE_SIZE;
+}
+
+int qemu_target_page_bits(void)
{
return TARGET_PAGE_BITS;
}
+int qemu_target_page_bits_min(void)
+{
+ return TARGET_PAGE_BITS_MIN;
+}
#endif
/*
int ret = 0;
rcu_read_lock();
- QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ RAMBLOCK_FOREACH(block) {
ret = func(block->idstr, block->host, block->offset,
block->used_length, opaque);
if (ret) {
rcu_read_unlock();
return ret;
}
+
+/*
+ * Unmap pages of memory from start to start+length such that
+ * they a) read as 0, b) Trigger whatever fault mechanism
+ * the OS provides for postcopy.
+ * The pages must be unmapped by the end of the function.
+ * Returns: 0 on success, none-0 on failure
+ *
+ */
+int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
+{
+ int ret = -1;
+
+ uint8_t *host_startaddr = rb->host + start;
+
+ if ((uintptr_t)host_startaddr & (rb->page_size - 1)) {
+ error_report("ram_block_discard_range: Unaligned start address: %p",
+ host_startaddr);
+ goto err;
+ }
+
+ if ((start + length) <= rb->used_length) {
+ uint8_t *host_endaddr = host_startaddr + length;
+ if ((uintptr_t)host_endaddr & (rb->page_size - 1)) {
+ error_report("ram_block_discard_range: Unaligned end address: %p",
+ host_endaddr);
+ goto err;
+ }
+
+ errno = ENOTSUP; /* If we are missing MADVISE etc */
+
+ if (rb->page_size == qemu_host_page_size) {
+#if defined(CONFIG_MADVISE)
+ /* Note: We need the madvise MADV_DONTNEED behaviour of definitely
+ * freeing the page.
+ */
+ ret = madvise(host_startaddr, length, MADV_DONTNEED);
+#endif
+ } else {
+ /* Huge page case - unfortunately it can't do DONTNEED, but
+ * it can do the equivalent by FALLOC_FL_PUNCH_HOLE in the
+ * huge page file.
+ */
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+ ret = fallocate(rb->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+ start, length);
+#endif
+ }
+ if (ret) {
+ ret = -errno;
+ error_report("ram_block_discard_range: Failed to discard range "
+ "%s:%" PRIx64 " +%zx (%d)",
+ rb->idstr, start, length, ret);
+ }
+ } else {
+ error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
+ "/%zx/" RAM_ADDR_FMT")",
+ rb->idstr, start, length, rb->used_length);
+ }
+
+err:
+ return ret;
+}
+
+#endif
+
+void page_size_init(void)
+{
+ /* NOTE: we can always suppose that qemu_host_page_size >=
+ TARGET_PAGE_SIZE */
+ if (qemu_host_page_size == 0) {
+ qemu_host_page_size = qemu_real_host_page_size;
+ }
+ if (qemu_host_page_size < TARGET_PAGE_SIZE) {
+ qemu_host_page_size = TARGET_PAGE_SIZE;
+ }
+ qemu_host_page_mask = -(intptr_t)qemu_host_page_size;
+}
+
+#if !defined(CONFIG_USER_ONLY)
+
+static void mtree_print_phys_entries(fprintf_function mon, void *f,
+ int start, int end, int skip, int ptr)
+{
+ if (start == end - 1) {
+ mon(f, "\t%3d ", start);
+ } else {
+ mon(f, "\t%3d..%-3d ", start, end - 1);
+ }
+ mon(f, " skip=%d ", skip);
+ if (ptr == PHYS_MAP_NODE_NIL) {
+ mon(f, " ptr=NIL");
+ } else if (!skip) {
+ mon(f, " ptr=#%d", ptr);
+ } else {
+ mon(f, " ptr=[%d]", ptr);
+ }
+ mon(f, "\n");
+}
+
+#define MR_SIZE(size) (int128_nz(size) ? (hwaddr)int128_get64( \
+ int128_sub((size), int128_one())) : 0)
+
+void mtree_print_dispatch(fprintf_function mon, void *f,
+ AddressSpaceDispatch *d, MemoryRegion *root)
+{
+ int i;
+
+ mon(f, " Dispatch\n");
+ mon(f, " Physical sections\n");
+
+ for (i = 0; i < d->map.sections_nb; ++i) {
+ MemoryRegionSection *s = d->map.sections + i;
+ const char *names[] = { " [unassigned]", " [not dirty]",
+ " [ROM]", " [watch]" };
+
+ mon(f, " #%d @" TARGET_FMT_plx ".." TARGET_FMT_plx " %s%s%s%s%s",
+ i,
+ s->offset_within_address_space,
+ s->offset_within_address_space + MR_SIZE(s->mr->size),
+ s->mr->name ? s->mr->name : "(noname)",
+ i < ARRAY_SIZE(names) ? names[i] : "",
+ s->mr == root ? " [ROOT]" : "",
+ s == d->mru_section ? " [MRU]" : "",
+ s->mr->is_iommu ? " [iommu]" : "");
+
+ if (s->mr->alias) {
+ mon(f, " alias=%s", s->mr->alias->name ?
+ s->mr->alias->name : "noname");
+ }
+ mon(f, "\n");
+ }
+
+ mon(f, " Nodes (%d bits per level, %d levels) ptr=[%d] skip=%d\n",
+ P_L2_BITS, P_L2_LEVELS, d->phys_map.ptr, d->phys_map.skip);
+ for (i = 0; i < d->map.nodes_nb; ++i) {
+ int j, jprev;
+ PhysPageEntry prev;
+ Node *n = d->map.nodes + i;
+
+ mon(f, " [%d]\n", i);
+
+ for (j = 0, jprev = 0, prev = *n[0]; j < ARRAY_SIZE(*n); ++j) {
+ PhysPageEntry *pe = *n + j;
+
+ if (pe->ptr == prev.ptr && pe->skip == prev.skip) {
+ continue;
+ }
+
+ mtree_print_phys_entries(mon, f, jprev, j, prev.skip, prev.ptr);
+
+ jprev = j;
+ prev = *pe;
+ }
+
+ if (jprev != ARRAY_SIZE(*n)) {
+ mtree_print_phys_entries(mon, f, jprev, j, prev.skip, prev.ptr);
+ }
+ }
+}
+
#endif
projects / qemu.git / blobdiff