return false;
}
+ if (getpagesize() != ram_pagesize_summary()) {
+ bool have_hp = false;
+ /* We've got a huge page */
+#ifdef UFFD_FEATURE_MISSING_HUGETLBFS
+ have_hp = api_struct.features & UFFD_FEATURE_MISSING_HUGETLBFS;
+#endif
+ if (!have_hp) {
+ error_report("Userfault on this host does not support huge pages");
+ return false;
+ }
+ }
return true;
}
-/*
- * Check for things that postcopy won't support; returns 0 if the block
- * is fine.
+/* Callback from postcopy_ram_supported_by_host block iterator.
*/
-static int check_range(const char *block_name, void *host_addr,
- ram_addr_t offset, ram_addr_t length, void *opaque)
+static int test_range_shared(const char *block_name, void *host_addr,
+ ram_addr_t offset, ram_addr_t length, void *opaque)
{
- RAMBlock *rb = qemu_ram_block_by_name(block_name);
-
- if (qemu_ram_pagesize(rb) > getpagesize()) {
- error_report("Postcopy doesn't support large page sizes yet (%s)",
+ if (qemu_ram_is_shared(qemu_ram_block_by_name(block_name))) {
+ error_report("Postcopy on shared RAM (%s) is not yet supported",
block_name);
- return -E2BIG;
+ return 1;
}
-
return 0;
}
goto out;
}
- /* Check for anything about the RAMBlocks we don't support */
- if (qemu_ram_foreach_block(check_range, NULL)) {
- /* check_range will have printed its own error */
- goto out;
- }
-
ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
if (ufd == -1) {
error_report("%s: userfaultfd not available: %s", __func__,
goto out;
}
+ /* We don't support postcopy with shared RAM yet */
+ if (qemu_ram_foreach_block(test_range_shared, NULL)) {
+ goto out;
+ }
+
/*
* userfault and mlock don't go together; we'll put it back later if
* it was enabled.
migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0);
if (mis->postcopy_tmp_page) {
- munmap(mis->postcopy_tmp_page, getpagesize());
+ munmap(mis->postcopy_tmp_page, mis->largest_page_size);
mis->postcopy_tmp_page = NULL;
}
+ if (mis->postcopy_tmp_zero_page) {
+ munmap(mis->postcopy_tmp_zero_page, mis->largest_page_size);
+ mis->postcopy_tmp_zero_page = NULL;
+ }
trace_postcopy_ram_incoming_cleanup_exit();
return 0;
}
error_report("%s userfault register: %s", __func__, strerror(errno));
return -1;
}
+ if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) {
+ error_report("%s userfault: Region doesn't support COPY", __func__);
+ return -1;
+ }
return 0;
}
MigrationIncomingState *mis = opaque;
struct uffd_msg msg;
int ret;
- size_t hostpagesize = getpagesize();
RAMBlock *rb = NULL;
RAMBlock *last_rb = NULL; /* last RAMBlock we sent part of */
break;
}
- rb_offset &= ~(hostpagesize - 1);
+ rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
qemu_ram_get_idstr(rb),
rb_offset);
if (rb != last_rb) {
last_rb = rb;
migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
- rb_offset, hostpagesize);
+ rb_offset, qemu_ram_pagesize(rb));
} else {
/* Save some space */
migrate_send_rp_req_pages(mis, NULL,
- rb_offset, hostpagesize);
+ rb_offset, qemu_ram_pagesize(rb));
}
}
trace_postcopy_ram_fault_thread_exit();
* Place a host page (from) at (host) atomically
* returns 0 on success
*/
-int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from)
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
+ size_t pagesize)
{
struct uffdio_copy copy_struct;
copy_struct.dst = (uint64_t)(uintptr_t)host;
copy_struct.src = (uint64_t)(uintptr_t)from;
- copy_struct.len = getpagesize();
+ copy_struct.len = pagesize;
copy_struct.mode = 0;
/* copy also acks to the kernel waking the stalled thread up
*/
if (ioctl(mis->userfault_fd, UFFDIO_COPY, ©_struct)) {
int e = errno;
- error_report("%s: %s copy host: %p from: %p",
- __func__, strerror(e), host, from);
+ error_report("%s: %s copy host: %p from: %p (size: %zd)",
+ __func__, strerror(e), host, from, pagesize);
return -e;
}
* Place a zero page at (host) atomically
* returns 0 on success
*/
-int postcopy_place_page_zero(MigrationIncomingState *mis, void *host)
+int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
+ size_t pagesize)
{
- struct uffdio_zeropage zero_struct;
+ trace_postcopy_place_page_zero(host);
- zero_struct.range.start = (uint64_t)(uintptr_t)host;
- zero_struct.range.len = getpagesize();
- zero_struct.mode = 0;
+ if (pagesize == getpagesize()) {
+ struct uffdio_zeropage zero_struct;
+ zero_struct.range.start = (uint64_t)(uintptr_t)host;
+ zero_struct.range.len = getpagesize();
+ zero_struct.mode = 0;
- if (ioctl(mis->userfault_fd, UFFDIO_ZEROPAGE, &zero_struct)) {
- int e = errno;
- error_report("%s: %s zero host: %p",
- __func__, strerror(e), host);
+ if (ioctl(mis->userfault_fd, UFFDIO_ZEROPAGE, &zero_struct)) {
+ int e = errno;
+ error_report("%s: %s zero host: %p",
+ __func__, strerror(e), host);
- return -e;
+ return -e;
+ }
+ } else {
+ /* The kernel can't use UFFDIO_ZEROPAGE for hugepages */
+ if (!mis->postcopy_tmp_zero_page) {
+ mis->postcopy_tmp_zero_page = mmap(NULL, mis->largest_page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS,
+ -1, 0);
+ if (mis->postcopy_tmp_zero_page == MAP_FAILED) {
+ int e = errno;
+ mis->postcopy_tmp_zero_page = NULL;
+ error_report("%s: %s mapping large zero page",
+ __func__, strerror(e));
+ return -e;
+ }
+ memset(mis->postcopy_tmp_zero_page, '\0', mis->largest_page_size);
+ }
+ return postcopy_place_page(mis, host, mis->postcopy_tmp_zero_page,
+ pagesize);
}
- trace_postcopy_place_page_zero(host);
return 0;
}
void *postcopy_get_tmp_page(MigrationIncomingState *mis)
{
if (!mis->postcopy_tmp_page) {
- mis->postcopy_tmp_page = mmap(NULL, getpagesize(),
+ mis->postcopy_tmp_page = mmap(NULL, mis->largest_page_size,
PROT_READ | PROT_WRITE, MAP_PRIVATE |
MAP_ANONYMOUS, -1, 0);
if (mis->postcopy_tmp_page == MAP_FAILED) {
return -1;
}
-int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from)
+int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
+ size_t pagesize)
{
assert(0);
return -1;
}
-int postcopy_place_page_zero(MigrationIncomingState *mis, void *host)
+int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
+ size_t pagesize)
{
assert(0);
return -1;