#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.h"
+#include "trace-root.h"
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+#include <fcntl.h>
+#include <linux/falloc.h>
+#endif
+
#endif
#include "exec/cpu-all.h"
#include "qemu/rcu_queue.h"
/* 0x01 was CPU_INTERRUPT_EXIT. This line can be removed when the
version_id is increased. */
cpu->interrupt_request &= ~0x01;
- tlb_flush(cpu, 1);
+ tlb_flush(cpu);
return 0;
}
qemu_mutex_unlock(&ram_list.mutex);
}
+#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)
{
}
if (mem_prealloc) {
- os_mem_prealloc(fd, area, memory, errp);
+ os_mem_prealloc(fd, area, memory, smp_cpus, errp);
if (errp && *errp) {
goto error;
}
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)
{
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;
+
+ QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+ 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)) {
qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_HUGEPAGE);
/* MADV_DONTFORK is also needed by KVM in absence of synchronous MMU */
qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_DONTFORK);
+ ram_block_notify_add(new_block->host, new_block->max_length);
}
}
return;
}
+ if (block->host) {
+ ram_block_notify_remove(block->host, block->max_length);
+ }
+
qemu_mutex_lock_ramlist();
QLIST_REMOVE_RCU(block, next);
ram_list.mru_block = NULL;
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);
memory_region_init_io(&io_mem_rom, NULL, &unassigned_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);
}
*/
d = atomic_rcu_read(&cpuas->as->dispatch);
atomic_rcu_set(&cpuas->memory_dispatch, d);
- tlb_flush(cpuas->cpu, 1);
+ tlb_flush(cpuas->cpu);
}
void address_space_init_dispatch(AddressSpace *as)
break;
case 4:
/* 32 bit write access */
- val = ldl_p(buf);
+ val = (uint32_t)ldl_p(buf);
result |= memory_region_dispatch_write(mr, addr1, val, 4,
attrs);
break;
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)) {
+ rcu_read_unlock();
return false;
}
}
xen_invalidate_map_cache_entry(cache->ptr);
}
memory_region_unref(cache->mr);
+ cache->mr = NULL;
}
/* Called from RCU critical section. This function has the same
hwaddr phys_addr;
target_ulong page;
+ cpu_synchronize_state(cpu);
while (len > 0) {
int asidx;
MemTxAttrs attrs;
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
projects / mirror_qemu.git / blobdiff