*/
#include "qemu/osdep.h"
#include <zlib.h>
-#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/iov.h"
-#include "qemu/sockets.h"
-#include "qemu/coroutine.h"
-#include "migration/migration.h"
-#include "migration/qemu-file.h"
+#include "migration.h"
+#include "qemu-file.h"
#include "trace.h"
#define IO_BUF_SIZE 32768
int buf_size; /* 0 when writing */
uint8_t buf[IO_BUF_SIZE];
+ DECLARE_BITMAP(may_free, MAX_IOV_SIZE);
struct iovec iov[MAX_IOV_SIZE];
unsigned int iovcnt;
bool qemu_file_is_writable(QEMUFile *f)
{
- return f->ops->writev_buffer || f->ops->put_buffer;
+ return f->ops->writev_buffer;
+}
+
+static void qemu_iovec_release_ram(QEMUFile *f)
+{
+ struct iovec iov;
+ unsigned long idx;
+
+ /* Find and release all the contiguous memory ranges marked as may_free. */
+ idx = find_next_bit(f->may_free, f->iovcnt, 0);
+ if (idx >= f->iovcnt) {
+ return;
+ }
+ iov = f->iov[idx];
+
+ /* The madvise() in the loop is called for iov within a continuous range and
+ * then reinitialize the iov. And in the end, madvise() is called for the
+ * last iov.
+ */
+ while ((idx = find_next_bit(f->may_free, f->iovcnt, idx + 1)) < f->iovcnt) {
+ /* check for adjacent buffer and coalesce them */
+ if (iov.iov_base + iov.iov_len == f->iov[idx].iov_base) {
+ iov.iov_len += f->iov[idx].iov_len;
+ continue;
+ }
+ if (qemu_madvise(iov.iov_base, iov.iov_len, QEMU_MADV_DONTNEED) < 0) {
+ error_report("migrate: madvise DONTNEED failed %p %zd: %s",
+ iov.iov_base, iov.iov_len, strerror(errno));
+ }
+ iov = f->iov[idx];
+ }
+ if (qemu_madvise(iov.iov_base, iov.iov_len, QEMU_MADV_DONTNEED) < 0) {
+ error_report("migrate: madvise DONTNEED failed %p %zd: %s",
+ iov.iov_base, iov.iov_len, strerror(errno));
+ }
+ memset(f->may_free, 0, sizeof(f->may_free));
}
/**
return;
}
- if (f->ops->writev_buffer) {
- if (f->iovcnt > 0) {
- expect = iov_size(f->iov, f->iovcnt);
- ret = f->ops->writev_buffer(f->opaque, f->iov, f->iovcnt, f->pos);
- }
- } else {
- if (f->buf_index > 0) {
- expect = f->buf_index;
- ret = f->ops->put_buffer(f->opaque, f->buf, f->pos, f->buf_index);
- }
+ if (f->iovcnt > 0) {
+ expect = iov_size(f->iov, f->iovcnt);
+ ret = f->ops->writev_buffer(f->opaque, f->iov, f->iovcnt, f->pos);
+
+ qemu_iovec_release_ram(f);
}
if (ret >= 0) {
if (f->hooks && f->hooks->save_page) {
int ret = f->hooks->save_page(f, f->opaque, block_offset,
offset, size, bytes_sent);
+ if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
+ f->bytes_xfer += size;
+ }
- if (ret != RAM_SAVE_CONTROL_DELAYED) {
+ if (ret != RAM_SAVE_CONTROL_DELAYED &&
+ ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (bytes_sent && *bytes_sent > 0) {
qemu_update_position(f, *bytes_sent);
} else if (ret < 0) {
return len;
}
-int qemu_get_fd(QEMUFile *f)
-{
- if (f->ops->get_fd) {
- return f->ops->get_fd(f->opaque);
- }
- return -1;
-}
-
void qemu_update_position(QEMUFile *f, size_t size)
{
f->pos += size;
return ret;
}
-static void add_to_iovec(QEMUFile *f, const uint8_t *buf, size_t size)
+static void add_to_iovec(QEMUFile *f, const uint8_t *buf, size_t size,
+ bool may_free)
{
/* check for adjacent buffer and coalesce them */
if (f->iovcnt > 0 && buf == f->iov[f->iovcnt - 1].iov_base +
- f->iov[f->iovcnt - 1].iov_len) {
+ f->iov[f->iovcnt - 1].iov_len &&
+ may_free == test_bit(f->iovcnt - 1, f->may_free))
+ {
f->iov[f->iovcnt - 1].iov_len += size;
} else {
+ if (may_free) {
+ set_bit(f->iovcnt, f->may_free);
+ }
f->iov[f->iovcnt].iov_base = (uint8_t *)buf;
f->iov[f->iovcnt++].iov_len = size;
}
}
}
-void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, size_t size)
+void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, size_t size,
+ bool may_free)
{
- if (!f->ops->writev_buffer) {
- qemu_put_buffer(f, buf, size);
- return;
- }
-
if (f->last_error) {
return;
}
f->bytes_xfer += size;
- add_to_iovec(f, buf, size);
+ add_to_iovec(f, buf, size, may_free);
}
void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
}
memcpy(f->buf + f->buf_index, buf, l);
f->bytes_xfer += l;
- if (f->ops->writev_buffer) {
- add_to_iovec(f, f->buf + f->buf_index, l);
- }
+ add_to_iovec(f, f->buf + f->buf_index, l, false);
f->buf_index += l;
if (f->buf_index == IO_BUF_SIZE) {
qemu_fflush(f);
f->buf[f->buf_index] = v;
f->bytes_xfer++;
- if (f->ops->writev_buffer) {
- add_to_iovec(f, f->buf + f->buf_index, 1);
- }
+ add_to_iovec(f, f->buf + f->buf_index, 1, false);
f->buf_index++;
if (f->buf_index == IO_BUF_SIZE) {
qemu_fflush(f);
int64_t ret = f->pos;
int i;
- if (f->ops->writev_buffer) {
- for (i = 0; i < f->iovcnt; i++) {
- ret += f->iov[i].iov_len;
- }
- } else {
- ret += f->buf_index;
+ for (i = 0; i < f->iovcnt; i++) {
+ ret += f->iov[i].iov_len;
}
return ret;
return v;
}
-/* compress size bytes of data start at p with specific compression
- * level and store the compressed data to the buffer of f.
- */
+/* return the size after compression, or negative value on error */
+static int qemu_compress_data(z_stream *stream, uint8_t *dest, size_t dest_len,
+ const uint8_t *source, size_t source_len)
+{
+ int err;
+
+ err = deflateReset(stream);
+ if (err != Z_OK) {
+ return -1;
+ }
+
+ stream->avail_in = source_len;
+ stream->next_in = (uint8_t *)source;
+ stream->avail_out = dest_len;
+ stream->next_out = dest;
+
+ err = deflate(stream, Z_FINISH);
+ if (err != Z_STREAM_END) {
+ return -1;
+ }
+
+ return stream->next_out - dest;
+}
-ssize_t qemu_put_compression_data(QEMUFile *f, const uint8_t *p, size_t size,
- int level)
+/* Compress size bytes of data start at p and store the compressed
+ * data to the buffer of f.
+ *
+ * When f is not writable, return -1 if f has no space to save the
+ * compressed data.
+ * When f is wirtable and it has no space to save the compressed data,
+ * do fflush first, if f still has no space to save the compressed
+ * data, return -1.
+ */
+ssize_t qemu_put_compression_data(QEMUFile *f, z_stream *stream,
+ const uint8_t *p, size_t size)
{
ssize_t blen = IO_BUF_SIZE - f->buf_index - sizeof(int32_t);
if (blen < compressBound(size)) {
- return 0;
+ if (!qemu_file_is_writable(f)) {
+ return -1;
+ }
+ qemu_fflush(f);
+ blen = IO_BUF_SIZE - sizeof(int32_t);
+ if (blen < compressBound(size)) {
+ return -1;
+ }
}
- if (compress2(f->buf + f->buf_index + sizeof(int32_t), (uLongf *)&blen,
- (Bytef *)p, size, level) != Z_OK) {
- error_report("Compress Failed!");
- return 0;
+
+ blen = qemu_compress_data(stream, f->buf + f->buf_index + sizeof(int32_t),
+ blen, p, size);
+ if (blen < 0) {
+ return -1;
}
+
qemu_put_be32(f, blen);
+ if (f->ops->writev_buffer) {
+ add_to_iovec(f, f->buf + f->buf_index, blen, false);
+ }
f->buf_index += blen;
+ if (f->buf_index == IO_BUF_SIZE) {
+ qemu_fflush(f);
+ }
return blen + sizeof(int32_t);
}
len = f_src->buf_index;
qemu_put_buffer(f_des, f_src->buf, f_src->buf_index);
f_src->buf_index = 0;
+ f_src->iovcnt = 0;
}
return len;
}
return res == len ? res : 0;
}
+/*
+ * Put a string with one preceding byte containing its length. The length of
+ * the string should be less than 256.
+ */
+void qemu_put_counted_string(QEMUFile *f, const char *str)
+{
+ size_t len = strlen(str);
+
+ assert(len < 256);
+ qemu_put_byte(f, len);
+ qemu_put_buffer(f, (const uint8_t *)str, len);
+}
+
/*
* Set the blocking state of the QEMUFile.
* Note: On some transports the OS only keeps a single blocking state for
{
if (f->ops->set_blocking) {
f->ops->set_blocking(f->opaque, block);
- } else {
- if (block) {
- qemu_set_block(qemu_get_fd(f));
- } else {
- qemu_set_nonblock(qemu_get_fd(f));
- }
}
}
projects / mirror_qemu.git / blobdiff