+fail:
+ close(uffd);
+ return -1;
+}
+
+/**
+ * uffd_close_fd: close UFFD file descriptor
+ *
+ * @uffd: UFFD file descriptor
+ */
+static void uffd_close_fd(int uffd)
+{
+ assert(uffd >= 0);
+ close(uffd);
+}
+
+/**
+ * uffd_register_memory: register memory range with UFFD
+ *
+ * Returns 0 in case of success, negative value on error
+ *
+ * @uffd: UFFD file descriptor
+ * @start: starting virtual address of memory range
+ * @length: length of memory range
+ * @track_missing: generate events on missing-page faults
+ * @track_wp: generate events on write-protected-page faults
+ */
+static int uffd_register_memory(int uffd, hwaddr start, hwaddr length,
+ bool track_missing, bool track_wp)
+{
+ struct uffdio_register uffd_register;
+
+ uffd_register.range.start = start;
+ uffd_register.range.len = length;
+ uffd_register.mode = (track_missing ? UFFDIO_REGISTER_MODE_MISSING : 0) |
+ (track_wp ? UFFDIO_REGISTER_MODE_WP : 0);
+
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) {
+ error_report("uffd_register_memory() failed: "
+ "start=%0"PRIx64" len=%"PRIu64" mode=%llu errno=%i",
+ start, length, uffd_register.mode, errno);
+ return -1;
+ }
+
+ return 0;
+}
+
+/**
+ * uffd_protect_memory: protect/unprotect memory range for writes with UFFD
+ *
+ * Returns 0 on success or negative value in case of error
+ *
+ * @uffd: UFFD file descriptor
+ * @start: starting virtual address of memory range
+ * @length: length of memory range
+ * @wp: write-protect/unprotect
+ */
+static int uffd_protect_memory(int uffd, hwaddr start, hwaddr length, bool wp)
+{
+ struct uffdio_writeprotect uffd_writeprotect;
+ int res;
+
+ uffd_writeprotect.range.start = start;
+ uffd_writeprotect.range.len = length;
+ uffd_writeprotect.mode = (wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0);
+
+ do {
+ res = ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect);
+ } while (res < 0 && errno == EINTR);
+ if (res < 0) {
+ error_report("uffd_protect_memory() failed: "
+ "start=%0"PRIx64" len=%"PRIu64" mode=%llu errno=%i",
+ start, length, uffd_writeprotect.mode, errno);
+ return -1;
+ }
+
+ return 0;
+}
+
+__attribute__ ((unused))
+static int uffd_read_events(int uffd, struct uffd_msg *msgs, int count);
+__attribute__ ((unused))
+static bool uffd_poll_events(int uffd, int tmo);
+
+/**
+ * uffd_read_events: read pending UFFD events
+ *
+ * Returns number of fetched messages, 0 if non is available or
+ * negative value in case of an error
+ *
+ * @uffd: UFFD file descriptor
+ * @msgs: pointer to message buffer
+ * @count: number of messages that can fit in the buffer
+ */
+static int uffd_read_events(int uffd, struct uffd_msg *msgs, int count)
+{
+ ssize_t res;
+ do {
+ res = read(uffd, msgs, count * sizeof(struct uffd_msg));
+ } while (res < 0 && errno == EINTR);
+
+ if ((res < 0 && errno == EAGAIN)) {
+ return 0;
+ }
+ if (res < 0) {
+ error_report("uffd_read_events() failed: errno=%i", errno);
+ return -1;
+ }
+
+ return (int) (res / sizeof(struct uffd_msg));
+}
+
+/**
+ * uffd_poll_events: poll UFFD file descriptor for read
+ *
+ * Returns true if events are available for read, false otherwise
+ *
+ * @uffd: UFFD file descriptor
+ * @tmo: timeout in milliseconds, 0 for non-blocking operation,
+ * negative value for infinite wait
+ */
+static bool uffd_poll_events(int uffd, int tmo)
+{
+ int res;
+ struct pollfd poll_fd = { .fd = uffd, .events = POLLIN, .revents = 0 };
+
+ do {
+ res = poll(&poll_fd, 1, tmo);
+ } while (res < 0 && errno == EINTR);
+
+ if (res == 0) {
+ return false;
+ }
+ if (res < 0) {
+ error_report("uffd_poll_events() failed: errno=%i", errno);
+ return false;
+ }
+
+ return (poll_fd.revents & POLLIN) != 0;
+}
+
static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock
*block,
ram_addr_t offset, uint8_t *source_buf);
@@ -3788,6 +3971,90 @@ static int ram_resume_prepare(MigrationState *s, void
*opaque)
return 0;
}
+/**
+ * ram_write_tracking_start: start UFFD-WP memory tracking
+ *
+ * Returns 0 for success or negative value in case of error
+ *
+ */
+int ram_write_tracking_start(void)
+{
+ int uffd;
+ RAMState *rs = ram_state;
+ RAMBlock *bs;
+
+ /* Open UFFD file descriptor */
+ uffd = uffd_create_fd();
+ if (uffd < 0) {
+ return uffd;
+ }
+ rs->uffdio_fd = uffd;
+
+ RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+ /* Nothing to do with read-only and MMIO-writable regions */
+ if (bs->mr->readonly || bs->mr->rom_device) {
+ continue;
+ }
+
+ /* Register block memory with UFFD to track writes */
+ if (uffd_register_memory(rs->uffdio_fd, (hwaddr) bs->host,
+ bs->max_length, false, true)) {
+ goto fail;
+ }
+ /* Apply UFFD write protection to the block memory range */
+ if (uffd_protect_memory(rs->uffdio_fd, (hwaddr) bs->host,
+ bs->max_length, true)) {
+ goto fail;
+ }
+ bs->flags |= RAM_UF_WRITEPROTECT;
+
+ info_report("UFFD-WP write-tracking enabled: "
+ "block_id=%s page_size=%zu start=%p length=%lu "
+ "romd_mode=%i ram=%i readonly=%i nonvolatile=%i rom_device=%i",
+ bs->idstr, bs->page_size, bs->host, bs->max_length,
+ bs->mr->romd_mode, bs->mr->ram, bs->mr->readonly,
+ bs->mr->nonvolatile, bs->mr->rom_device);
+ }
+
+ return 0;
+
+fail:
+ uffd_close_fd(uffd);
+ rs->uffdio_fd = -1;
+ return -1;
+}
+
+/**
+ * ram_write_tracking_stop: stop UFFD-WP memory tracking and remove protection
+ */
+void ram_write_tracking_stop(void)
+{
+ RAMState *rs = ram_state;
+ RAMBlock *bs;
+ assert(rs->uffdio_fd >= 0);
+
+ RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+ if ((bs->flags & RAM_UF_WRITEPROTECT) == 0) {
+ continue;
+ }
+ info_report("UFFD-WP write-tracking disabled: "
+ "block_id=%s page_size=%zu start=%p length=%lu "
+ "romd_mode=%i ram=%i readonly=%i nonvolatile=%i rom_device=%i",
+ bs->idstr, bs->page_size, bs->host, bs->max_length,
+ bs->mr->romd_mode, bs->mr->ram, bs->mr->readonly,
+ bs->mr->nonvolatile, bs->mr->rom_device);
+ /* Cleanup flags */
+ bs->flags &= ~RAM_UF_WRITEPROTECT;
+ }
+
+ /*
+ * Close UFFD file descriptor to remove protection,
+ * release registered memory regions and flush wait queues
+ */
+ uffd_close_fd(rs->uffdio_fd);
+ rs->uffdio_fd = -1;
+}
+
static SaveVMHandlers savevm_ram_handlers = {
.save_setup = ram_save_setup,
.save_live_iterate = ram_save_iterate,
diff --git a/migration/ram.h b/migration/ram.h
index 011e85414e..3611cb51de 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -79,4 +79,8 @@ void colo_flush_ram_cache(void);
void colo_release_ram_cache(void);
void colo_incoming_start_dirty_log(void);
+/* Live snapshots */
+int ram_write_tracking_start(void);
+void ram_write_tracking_stop(void);
+
#endif
--
2.25.1