qemu-e2k/migration/qemu-file.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

946 lines
23 KiB
C
Raw Normal View History

/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <zlib.h>
#include "qemu/madvise.h"
#include "qemu/error-report.h"
#include "qemu/iov.h"
#include "migration.h"
#include "migration-stats.h"
#include "qemu-file.h"
#include "trace.h"
#include "options.h"
#include "qapi/error.h"
#include "rdma.h"
#include "io/channel-file.h"
#define IO_BUF_SIZE 32768
osdep: Make MIN/MAX evaluate arguments only once I'm not aware of any immediate bugs in qemu where a second runtime evaluation of the arguments to MIN() or MAX() causes a problem, but proactively preventing such abuse is easier than falling prey to an unintended case down the road. At any rate, here's the conversation that sparked the current patch: https://lists.gnu.org/archive/html/qemu-devel/2018-12/msg05718.html Update the MIN/MAX macros to only evaluate their argument once at runtime; this uses typeof(1 ? (a) : (b)) to ensure that we are promoting the temporaries to the same type as the final comparison (we have to trigger type promotion, as typeof(bitfield) won't compile; and we can't use typeof((a) + (b)) or even typeof((a) + 0), as some of our uses of MAX are on void* pointers where such addition is undefined). However, we are unable to work around gcc refusing to compile ({}) in a constant context (such as the array length of a static variable), even when only used in the dead branch of a __builtin_choose_expr(), so we have to provide a second macro pair MIN_CONST and MAX_CONST for use when both arguments are known to be compile-time constants and where the result must also be usable as a constant; this second form evaluates arguments multiple times but that doesn't matter for constants. By using a void expression as the expansion if a non-constant is presented to this second form, we can enlist the compiler to ensure the double evaluation is not attempted on non-constants. Alas, as both macros now rely on compiler intrinsics, they are no longer usable in preprocessor #if conditions; those will just have to be open-coded or the logic rewritten into #define or runtime 'if' conditions (but where the compiler dead-code-elimination will probably still apply). I tested that both gcc 10.1.1 and clang 10.0.0 produce errors for all forms of macro mis-use. As the errors can sometimes be cryptic, I'm demonstrating the gcc output: Use of MIN when MIN_CONST is needed: In file included from /home/eblake/qemu/qemu-img.c:25: /home/eblake/qemu/include/qemu/osdep.h:249:5: error: braced-group within expression allowed only inside a function 249 | ({ \ | ^ /home/eblake/qemu/qemu-img.c:92:12: note: in expansion of macro ‘MIN’ 92 | char array[MIN(1, 2)] = ""; | ^~~ Use of MIN_CONST when MIN is needed: /home/eblake/qemu/qemu-img.c: In function ‘is_allocated_sectors’: /home/eblake/qemu/qemu-img.c:1225:15: error: void value not ignored as it ought to be 1225 | i = MIN_CONST(i, n); | ^ Use of MIN in the preprocessor: In file included from /home/eblake/qemu/accel/tcg/translate-all.c:20: /home/eblake/qemu/accel/tcg/translate-all.c: In function ‘page_check_range’: /home/eblake/qemu/include/qemu/osdep.h:249:6: error: token "{" is not valid in preprocessor expressions 249 | ({ \ | ^ Fix the resulting callsites that used #if or computed a compile-time constant min or max to use the new macros. cpu-defs.h is interesting, as CPU_TLB_DYN_MAX_BITS is sometimes used as a constant and sometimes dynamic. It may be worth improving glib's MIN/MAX definitions to be saner, but that is a task for another day. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200625162602.700741-1-eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2020-06-25 18:26:02 +02:00
#define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
struct QEMUFile {
QIOChannel *ioc;
bool is_writable;
int buf_index;
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;
int last_error;
Error *last_error_obj;
};
/*
* Stop a file from being read/written - not all backing files can do this
* typically only sockets can.
*
* TODO: convert to propagate Error objects instead of squashing
* to a fixed errno value
*/
int qemu_file_shutdown(QEMUFile *f)
{
Error *err = NULL;
/*
* We must set qemufile error before the real shutdown(), otherwise
* there can be a race window where we thought IO all went though
* (because last_error==NULL) but actually IO has already stopped.
*
* If without correct ordering, the race can happen like this:
*
* page receiver other thread
* ------------- ------------
* qemu_get_buffer()
* do shutdown()
* returns 0 (buffer all zero)
* (we didn't check this retcode)
* try to detect IO error
* last_error==NULL, IO okay
* install ALL-ZERO page
* set last_error
* --> guest crash!
*/
if (!f->last_error) {
qemu_file_set_error(f, -EIO);
}
if (!qio_channel_has_feature(f->ioc,
QIO_CHANNEL_FEATURE_SHUTDOWN)) {
return -ENOSYS;
}
if (qio_channel_shutdown(f->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, &err) < 0) {
error_report_err(err);
return -EIO;
}
return 0;
}
static QEMUFile *qemu_file_new_impl(QIOChannel *ioc, bool is_writable)
{
QEMUFile *f;
f = g_new0(QEMUFile, 1);
object_ref(ioc);
f->ioc = ioc;
f->is_writable = is_writable;
return f;
}
/*
* Result: QEMUFile* for a 'return path' for comms in the opposite direction
* NULL if not available
*/
QEMUFile *qemu_file_get_return_path(QEMUFile *f)
{
return qemu_file_new_impl(f->ioc, !f->is_writable);
}
QEMUFile *qemu_file_new_output(QIOChannel *ioc)
{
return qemu_file_new_impl(ioc, true);
}
QEMUFile *qemu_file_new_input(QIOChannel *ioc)
{
return qemu_file_new_impl(ioc, false);
}
/*
* Get last error for stream f with optional Error*
*
* Return negative error value if there has been an error on previous
* operations, return 0 if no error happened.
*
* If errp is specified, a verbose error message will be copied over.
*/
int qemu_file_get_error_obj(QEMUFile *f, Error **errp)
{
if (!f->last_error) {
return 0;
}
/* There is an error */
if (errp) {
if (f->last_error_obj) {
*errp = error_copy(f->last_error_obj);
} else {
error_setg_errno(errp, -f->last_error, "Channel error");
}
}
return f->last_error;
}
/*
* Get last error for either stream f1 or f2 with optional Error*.
* The error returned (non-zero) can be either from f1 or f2.
*
* If any of the qemufile* is NULL, then skip the check on that file.
*
* When there is no error on both qemufile, zero is returned.
*/
int qemu_file_get_error_obj_any(QEMUFile *f1, QEMUFile *f2, Error **errp)
{
int ret = 0;
if (f1) {
ret = qemu_file_get_error_obj(f1, errp);
/* If there's already error detected, return */
if (ret) {
return ret;
}
}
if (f2) {
ret = qemu_file_get_error_obj(f2, errp);
}
return ret;
}
/*
* Set the last error for stream f with optional Error*
*/
void qemu_file_set_error_obj(QEMUFile *f, int ret, Error *err)
{
if (f->last_error == 0 && ret) {
f->last_error = ret;
error_propagate(&f->last_error_obj, err);
} else if (err) {
error_report_err(err);
}
}
/*
* Get last error for stream f
*
* Return negative error value if there has been an error on previous
* operations, return 0 if no error happened.
*
*/
int qemu_file_get_error(QEMUFile *f)
{
return f->last_error;
}
/*
* Set the last error for stream f
*/
void qemu_file_set_error(QEMUFile *f, int ret)
{
qemu_file_set_error_obj(f, ret, NULL);
}
static bool qemu_file_is_writable(QEMUFile *f)
{
return f->is_writable;
}
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));
}
bool qemu_file_is_seekable(QEMUFile *f)
{
return qio_channel_has_feature(f->ioc, QIO_CHANNEL_FEATURE_SEEKABLE);
}
/**
* Flushes QEMUFile buffer
*
* This will flush all pending data. If data was only partially flushed, it
* will set an error state.
*/
int qemu_fflush(QEMUFile *f)
{
if (!qemu_file_is_writable(f)) {
return f->last_error;
}
if (f->last_error) {
return f->last_error;
}
if (f->iovcnt > 0) {
Error *local_error = NULL;
if (qio_channel_writev_all(f->ioc,
f->iov, f->iovcnt,
&local_error) < 0) {
qemu_file_set_error_obj(f, -EIO, local_error);
} else {
uint64_t size = iov_size(f->iov, f->iovcnt);
stat64_add(&mig_stats.qemu_file_transferred, size);
}
qemu_iovec_release_ram(f);
}
f->buf_index = 0;
f->iovcnt = 0;
return f->last_error;
}
/*
* Attempt to fill the buffer from the underlying file
* Returns the number of bytes read, or negative value for an error.
*
* Note that it can return a partially full buffer even in a not error/not EOF
* case if the underlying file descriptor gives a short read, and that can
* happen even on a blocking fd.
*/
static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
{
int len;
int pending;
Error *local_error = NULL;
assert(!qemu_file_is_writable(f));
pending = f->buf_size - f->buf_index;
if (pending > 0) {
memmove(f->buf, f->buf + f->buf_index, pending);
}
f->buf_index = 0;
f->buf_size = pending;
if (qemu_file_get_error(f)) {
return 0;
}
do {
len = qio_channel_read(f->ioc,
(char *)f->buf + pending,
IO_BUF_SIZE - pending,
&local_error);
if (len == QIO_CHANNEL_ERR_BLOCK) {
if (qemu_in_coroutine()) {
qio_channel_yield(f->ioc, G_IO_IN);
} else {
qio_channel_wait(f->ioc, G_IO_IN);
}
} else if (len < 0) {
len = -EIO;
}
} while (len == QIO_CHANNEL_ERR_BLOCK);
if (len > 0) {
f->buf_size += len;
} else if (len == 0) {
qemu_file_set_error_obj(f, -EIO, local_error);
} else {
qemu_file_set_error_obj(f, len, local_error);
}
return len;
}
/** Closes the file
*
* Returns negative error value if any error happened on previous operations or
* while closing the file. Returns 0 or positive number on success.
*
* The meaning of return value on success depends on the specific backend
* being used.
*/
int qemu_fclose(QEMUFile *f)
{
int ret = qemu_fflush(f);
int ret2 = qio_channel_close(f->ioc, NULL);
if (ret >= 0) {
ret = ret2;
}
g_clear_pointer(&f->ioc, object_unref);
error_free(f->last_error_obj);
g_free(f);
trace_qemu_file_fclose();
return ret;
}
/*
* Add buf to iovec. Do flush if iovec is full.
*
* Return values:
* 1 iovec is full and flushed
* 0 iovec is not flushed
*
*/
static int 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 &&
may_free == test_bit(f->iovcnt - 1, f->may_free))
{
f->iov[f->iovcnt - 1].iov_len += size;
} else {
migration: fix the memory overwriting risk in add_to_iovec When testing migration, a Segmentation fault qemu core is generated. 0 error_free (err=0x1) 1 0x00007f8b862df647 in qemu_fclose (f=f@entry=0x55e06c247640) 2 0x00007f8b8516d59a in migrate_fd_cleanup (s=s@entry=0x55e06c0e1ef0) 3 0x00007f8b8516d66c in migrate_fd_cleanup_bh (opaque=0x55e06c0e1ef0) 4 0x00007f8b8626a47f in aio_bh_poll (ctx=ctx@entry=0x55e06b5a16d0) 5 0x00007f8b8626e71f in aio_dispatch (ctx=0x55e06b5a16d0) 6 0x00007f8b8626a33d in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) 7 0x00007f8b866bdba4 in g_main_context_dispatch () 8 0x00007f8b8626cde9 in glib_pollfds_poll () 9 0x00007f8b8626ce62 in os_host_main_loop_wait (timeout=<optimized out>) 10 0x00007f8b8626cffd in main_loop_wait (nonblocking=nonblocking@entry=0) 11 0x00007f8b862ef01f in main_loop () Using gdb print the struct QEMUFile f = { ..., iovcnt = 65, last_error = 21984, last_error_obj = 0x1, shutdown = true } Well iovcnt is overflow, because the max size of MAX_IOV_SIZE is 64. struct QEMUFile { ...; struct iovec iov[MAX_IOV_SIZE]; unsigned int iovcnt; int last_error; Error *last_error_obj; bool shutdown; }; iovcnt and last_error is overwrited by add_to_iovec(). Right now, add_to_iovec() increase iovcnt before check the limit. And it seems that add_to_iovec() assumes that iovcnt will set to zero in qemu_fflush(). But qemu_fflush() will directly return when f->shutdown is true. The situation may occur when libvirtd restart during migration, after f->shutdown is set, before calling qemu_file_set_error() in qemu_file_shutdown(). So the safiest way is checking the iovcnt before increasing it. Signed-off-by: Feng Lin <linfeng23@huawei.com> Message-Id: <20210625062138.1899-1-linfeng23@huawei.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Fix typo in 'writeable' which is actually misnamed 'writable'
2021-06-25 08:21:38 +02:00
if (f->iovcnt >= MAX_IOV_SIZE) {
/* Should only happen if a previous fflush failed */
assert(qemu_file_get_error(f) || !qemu_file_is_writable(f));
migration: fix the memory overwriting risk in add_to_iovec When testing migration, a Segmentation fault qemu core is generated. 0 error_free (err=0x1) 1 0x00007f8b862df647 in qemu_fclose (f=f@entry=0x55e06c247640) 2 0x00007f8b8516d59a in migrate_fd_cleanup (s=s@entry=0x55e06c0e1ef0) 3 0x00007f8b8516d66c in migrate_fd_cleanup_bh (opaque=0x55e06c0e1ef0) 4 0x00007f8b8626a47f in aio_bh_poll (ctx=ctx@entry=0x55e06b5a16d0) 5 0x00007f8b8626e71f in aio_dispatch (ctx=0x55e06b5a16d0) 6 0x00007f8b8626a33d in aio_ctx_dispatch (source=<optimized out>, callback=<optimized out>, user_data=<optimized out>) 7 0x00007f8b866bdba4 in g_main_context_dispatch () 8 0x00007f8b8626cde9 in glib_pollfds_poll () 9 0x00007f8b8626ce62 in os_host_main_loop_wait (timeout=<optimized out>) 10 0x00007f8b8626cffd in main_loop_wait (nonblocking=nonblocking@entry=0) 11 0x00007f8b862ef01f in main_loop () Using gdb print the struct QEMUFile f = { ..., iovcnt = 65, last_error = 21984, last_error_obj = 0x1, shutdown = true } Well iovcnt is overflow, because the max size of MAX_IOV_SIZE is 64. struct QEMUFile { ...; struct iovec iov[MAX_IOV_SIZE]; unsigned int iovcnt; int last_error; Error *last_error_obj; bool shutdown; }; iovcnt and last_error is overwrited by add_to_iovec(). Right now, add_to_iovec() increase iovcnt before check the limit. And it seems that add_to_iovec() assumes that iovcnt will set to zero in qemu_fflush(). But qemu_fflush() will directly return when f->shutdown is true. The situation may occur when libvirtd restart during migration, after f->shutdown is set, before calling qemu_file_set_error() in qemu_file_shutdown(). So the safiest way is checking the iovcnt before increasing it. Signed-off-by: Feng Lin <linfeng23@huawei.com> Message-Id: <20210625062138.1899-1-linfeng23@huawei.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Fix typo in 'writeable' which is actually misnamed 'writable'
2021-06-25 08:21:38 +02:00
return 1;
}
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;
}
if (f->iovcnt >= MAX_IOV_SIZE) {
qemu_fflush(f);
return 1;
}
return 0;
}
static void add_buf_to_iovec(QEMUFile *f, size_t len)
{
if (!add_to_iovec(f, f->buf + f->buf_index, len, false)) {
f->buf_index += len;
if (f->buf_index == IO_BUF_SIZE) {
qemu_fflush(f);
}
}
}
void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, size_t size,
bool may_free)
{
if (f->last_error) {
return;
}
add_to_iovec(f, buf, size, may_free);
}
void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
{
size_t l;
if (f->last_error) {
return;
}
while (size > 0) {
l = IO_BUF_SIZE - f->buf_index;
if (l > size) {
l = size;
}
memcpy(f->buf + f->buf_index, buf, l);
add_buf_to_iovec(f, l);
if (qemu_file_get_error(f)) {
break;
}
buf += l;
size -= l;
}
}
void qemu_put_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen,
off_t pos)
{
Error *err = NULL;
size_t ret;
if (f->last_error) {
return;
}
qemu_fflush(f);
ret = qio_channel_pwrite(f->ioc, (char *)buf, buflen, pos, &err);
if (err) {
qemu_file_set_error_obj(f, -EIO, err);
return;
}
if ((ssize_t)ret == QIO_CHANNEL_ERR_BLOCK) {
qemu_file_set_error_obj(f, -EAGAIN, NULL);
return;
}
if (ret != buflen) {
error_setg(&err, "Partial write of size %zu, expected %zu", ret,
buflen);
qemu_file_set_error_obj(f, -EIO, err);
return;
}
stat64_add(&mig_stats.qemu_file_transferred, buflen);
return;
}
size_t qemu_get_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen,
off_t pos)
{
Error *err = NULL;
size_t ret;
if (f->last_error) {
return 0;
}
ret = qio_channel_pread(f->ioc, (char *)buf, buflen, pos, &err);
if ((ssize_t)ret == -1 || err) {
qemu_file_set_error_obj(f, -EIO, err);
return 0;
}
if ((ssize_t)ret == QIO_CHANNEL_ERR_BLOCK) {
qemu_file_set_error_obj(f, -EAGAIN, NULL);
return 0;
}
if (ret != buflen) {
error_setg(&err, "Partial read of size %zu, expected %zu", ret, buflen);
qemu_file_set_error_obj(f, -EIO, err);
return 0;
}
return ret;
}
void qemu_set_offset(QEMUFile *f, off_t off, int whence)
{
Error *err = NULL;
off_t ret;
if (qemu_file_is_writable(f)) {
qemu_fflush(f);
} else {
/* Drop all cached buffers if existed; will trigger a re-fill later */
f->buf_index = 0;
f->buf_size = 0;
}
ret = qio_channel_io_seek(f->ioc, off, whence, &err);
if (ret == (off_t)-1) {
qemu_file_set_error_obj(f, -EIO, err);
}
}
off_t qemu_get_offset(QEMUFile *f)
{
Error *err = NULL;
off_t ret;
qemu_fflush(f);
ret = qio_channel_io_seek(f->ioc, 0, SEEK_CUR, &err);
if (ret == (off_t)-1) {
qemu_file_set_error_obj(f, -EIO, err);
}
return ret;
}
void qemu_put_byte(QEMUFile *f, int v)
{
if (f->last_error) {
return;
}
f->buf[f->buf_index] = v;
add_buf_to_iovec(f, 1);
}
void qemu_file_skip(QEMUFile *f, int size)
{
if (f->buf_index + size <= f->buf_size) {
f->buf_index += size;
}
}
/*
* Read 'size' bytes from file (at 'offset') without moving the
* pointer and set 'buf' to point to that data.
*
* It will return size bytes unless there was an error, in which case it will
* return as many as it managed to read (assuming blocking fd's which
* all current QEMUFile are)
*/
size_t coroutine_mixed_fn qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t size, size_t offset)
{
ssize_t pending;
size_t index;
assert(!qemu_file_is_writable(f));
assert(offset < IO_BUF_SIZE);
assert(size <= IO_BUF_SIZE - offset);
/* The 1st byte to read from */
index = f->buf_index + offset;
/* The number of available bytes starting at index */
pending = f->buf_size - index;
/*
* qemu_fill_buffer might return just a few bytes, even when there isn't
* an error, so loop collecting them until we get enough.
*/
while (pending < size) {
int received = qemu_fill_buffer(f);
if (received <= 0) {
break;
}
index = f->buf_index + offset;
pending = f->buf_size - index;
}
if (pending <= 0) {
return 0;
}
if (size > pending) {
size = pending;
}
*buf = f->buf + index;
return size;
}
/*
* Read 'size' bytes of data from the file into buf.
* 'size' can be larger than the internal buffer.
*
* It will return size bytes unless there was an error, in which case it will
* return as many as it managed to read (assuming blocking fd's which
* all current QEMUFile are)
*/
size_t coroutine_mixed_fn qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size)
{
size_t pending = size;
size_t done = 0;
while (pending > 0) {
size_t res;
uint8_t *src;
res = qemu_peek_buffer(f, &src, MIN(pending, IO_BUF_SIZE), 0);
if (res == 0) {
return done;
}
memcpy(buf, src, res);
qemu_file_skip(f, res);
buf += res;
pending -= res;
done += res;
}
return done;
}
/*
* Read 'size' bytes of data from the file.
* 'size' can be larger than the internal buffer.
*
* The data:
* may be held on an internal buffer (in which case *buf is updated
* to point to it) that is valid until the next qemu_file operation.
* OR
* will be copied to the *buf that was passed in.
*
* The code tries to avoid the copy if possible.
*
* It will return size bytes unless there was an error, in which case it will
* return as many as it managed to read (assuming blocking fd's which
* all current QEMUFile are)
*
* Note: Since **buf may get changed, the caller should take care to
* keep a pointer to the original buffer if it needs to deallocate it.
*/
size_t coroutine_mixed_fn qemu_get_buffer_in_place(QEMUFile *f, uint8_t **buf, size_t size)
{
if (size < IO_BUF_SIZE) {
size_t res;
uint8_t *src = NULL;
res = qemu_peek_buffer(f, &src, size, 0);
if (res == size) {
qemu_file_skip(f, res);
*buf = src;
return res;
}
}
return qemu_get_buffer(f, *buf, size);
}
/*
* Peeks a single byte from the buffer; this isn't guaranteed to work if
* offset leaves a gap after the previous read/peeked data.
*/
int coroutine_mixed_fn qemu_peek_byte(QEMUFile *f, int offset)
{
int index = f->buf_index + offset;
assert(!qemu_file_is_writable(f));
assert(offset < IO_BUF_SIZE);
if (index >= f->buf_size) {
qemu_fill_buffer(f);
index = f->buf_index + offset;
if (index >= f->buf_size) {
return 0;
}
}
return f->buf[index];
}
int coroutine_mixed_fn qemu_get_byte(QEMUFile *f)
{
int result;
result = qemu_peek_byte(f, 0);
qemu_file_skip(f, 1);
return result;
}
uint64_t qemu_file_transferred(QEMUFile *f)
{
uint64_t ret = stat64_get(&mig_stats.qemu_file_transferred);
int i;
g_assert(qemu_file_is_writable(f));
for (i = 0; i < f->iovcnt; i++) {
ret += f->iov[i].iov_len;
}
return ret;
}
void qemu_put_be16(QEMUFile *f, unsigned int v)
{
qemu_put_byte(f, v >> 8);
qemu_put_byte(f, v);
}
void qemu_put_be32(QEMUFile *f, unsigned int v)
{
qemu_put_byte(f, v >> 24);
qemu_put_byte(f, v >> 16);
qemu_put_byte(f, v >> 8);
qemu_put_byte(f, v);
}
void qemu_put_be64(QEMUFile *f, uint64_t v)
{
qemu_put_be32(f, v >> 32);
qemu_put_be32(f, v);
}
unsigned int qemu_get_be16(QEMUFile *f)
{
unsigned int v;
v = qemu_get_byte(f) << 8;
v |= qemu_get_byte(f);
return v;
}
unsigned int qemu_get_be32(QEMUFile *f)
{
unsigned int v;
v = (unsigned int)qemu_get_byte(f) << 24;
v |= qemu_get_byte(f) << 16;
v |= qemu_get_byte(f) << 8;
v |= qemu_get_byte(f);
return v;
}
uint64_t qemu_get_be64(QEMUFile *f)
{
uint64_t v;
v = (uint64_t)qemu_get_be32(f) << 32;
v |= qemu_get_be32(f);
return v;
}
/* 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;
}
/* Compress size bytes of data start at p and store the compressed
* data to the buffer of f.
*
* Since the file is dummy file with empty_ops, return -1 if f has no space to
* save the compressed data.
*/
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 -1;
}
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);
add_buf_to_iovec(f, blen);
return blen + sizeof(int32_t);
}
/* Put the data in the buffer of f_src to the buffer of f_des, and
* then reset the buf_index of f_src to 0.
*/
int qemu_put_qemu_file(QEMUFile *f_des, QEMUFile *f_src)
{
int len = 0;
if (f_src->buf_index > 0) {
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;
}
/*
* Check if the writable buffer is empty
*/
bool qemu_file_buffer_empty(QEMUFile *file)
{
assert(qemu_file_is_writable(file));
return !file->iovcnt;
}
/*
* Get a string whose length is determined by a single preceding byte
* A preallocated 256 byte buffer must be passed in.
* Returns: len on success and a 0 terminated string in the buffer
* else 0
* (Note a 0 length string will return 0 either way)
*/
size_t coroutine_fn qemu_get_counted_string(QEMUFile *f, char buf[256])
{
size_t len = qemu_get_byte(f);
size_t res = qemu_get_buffer(f, (uint8_t *)buf, len);
buf[res] = 0;
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
* both directions, and thus changing the blocking on the main
* QEMUFile can also affect the return path.
*/
void qemu_file_set_blocking(QEMUFile *f, bool block)
{
qio_channel_set_blocking(f->ioc, block, NULL);
}
/*
* qemu_file_get_ioc:
*
* Get the ioc object for the file, without incrementing
* the reference count.
*
* Returns: the ioc object
*/
QIOChannel *qemu_file_get_ioc(QEMUFile *file)
{
return file->ioc;
}
/*
* Read size bytes from QEMUFile f and write them to fd.
*/
int qemu_file_get_to_fd(QEMUFile *f, int fd, size_t size)
{
while (size) {
size_t pending = f->buf_size - f->buf_index;
ssize_t rc;
if (!pending) {
rc = qemu_fill_buffer(f);
if (rc < 0) {
return rc;
}
if (rc == 0) {
return -EIO;
}
continue;
}
rc = write(fd, f->buf + f->buf_index, MIN(pending, size));
if (rc < 0) {
return -errno;
}
if (rc == 0) {
return -EIO;
}
f->buf_index += rc;
size -= rc;
}
return 0;
}