#include "module.h"
#include "block/raw-posix-aio.h"
-#ifdef CONFIG_COCOA
+#if defined(__APPLE__) && (__MACH__)
#include <paths.h>
#include <sys/param.h>
#include <IOKit/IOKitLib.h>
#include <sys/param.h>
#include <linux/cdrom.h>
#include <linux/fd.h>
+#include <linux/fs.h>
+#endif
+#ifdef CONFIG_FIEMAP
+#include <linux/fiemap.h>
#endif
#if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
#include <sys/disk.h>
int use_aio;
void *aio_ctx;
#endif
- uint8_t *aligned_buf;
- unsigned aligned_buf_size;
#ifdef CONFIG_XFS
bool is_xfs : 1;
#endif
} BDRVRawState;
+typedef struct BDRVRawReopenState {
+ int fd;
+ int open_flags;
+#ifdef CONFIG_LINUX_AIO
+ int use_aio;
+#endif
+} BDRVRawReopenState;
+
static int fd_open(BlockDriverState *bs);
static int64_t raw_getlength(BlockDriverState *bs);
}
#endif
+static void raw_parse_flags(int bdrv_flags, int *open_flags)
+{
+ assert(open_flags != NULL);
+
+ *open_flags |= O_BINARY;
+ *open_flags &= ~O_ACCMODE;
+ if (bdrv_flags & BDRV_O_RDWR) {
+ *open_flags |= O_RDWR;
+ } else {
+ *open_flags |= O_RDONLY;
+ }
+
+ /* Use O_DSYNC for write-through caching, no flags for write-back caching,
+ * and O_DIRECT for no caching. */
+ if ((bdrv_flags & BDRV_O_NOCACHE)) {
+ *open_flags |= O_DIRECT;
+ }
+}
+
+#ifdef CONFIG_LINUX_AIO
+static int raw_set_aio(void **aio_ctx, int *use_aio, int bdrv_flags)
+{
+ int ret = -1;
+ assert(aio_ctx != NULL);
+ assert(use_aio != NULL);
+ /*
+ * Currently Linux do AIO only for files opened with O_DIRECT
+ * specified so check NOCACHE flag too
+ */
+ if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
+ (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
+
+ /* if non-NULL, laio_init() has already been run */
+ if (*aio_ctx == NULL) {
+ *aio_ctx = laio_init();
+ if (!*aio_ctx) {
+ goto error;
+ }
+ }
+ *use_aio = 1;
+ } else {
+ *use_aio = 0;
+ }
+
+ ret = 0;
+
+error:
+ return ret;
+}
+#endif
+
static int raw_open_common(BlockDriverState *bs, const char *filename,
int bdrv_flags, int open_flags)
{
return ret;
}
- s->open_flags = open_flags | O_BINARY;
- s->open_flags &= ~O_ACCMODE;
- if (bdrv_flags & BDRV_O_RDWR) {
- s->open_flags |= O_RDWR;
- } else {
- s->open_flags |= O_RDONLY;
- }
-
- /* Use O_DSYNC for write-through caching, no flags for write-back caching,
- * and O_DIRECT for no caching. */
- if ((bdrv_flags & BDRV_O_NOCACHE))
- s->open_flags |= O_DIRECT;
- if (!(bdrv_flags & BDRV_O_CACHE_WB))
- s->open_flags |= O_DSYNC;
+ s->open_flags = open_flags;
+ raw_parse_flags(bdrv_flags, &s->open_flags);
s->fd = -1;
fd = qemu_open(filename, s->open_flags, 0644);
return ret;
}
s->fd = fd;
- s->aligned_buf = NULL;
-
- if ((bdrv_flags & BDRV_O_NOCACHE)) {
- /*
- * Allocate a buffer for read/modify/write cycles. Chose the size
- * pessimistically as we don't know the block size yet.
- */
- s->aligned_buf_size = 32 * MAX_BLOCKSIZE;
- s->aligned_buf = qemu_memalign(MAX_BLOCKSIZE, s->aligned_buf_size);
- if (s->aligned_buf == NULL) {
- goto out_close;
- }
- }
/* We're falling back to POSIX AIO in some cases so init always */
if (paio_init() < 0) {
- goto out_free_buf;
+ goto out_close;
}
#ifdef CONFIG_LINUX_AIO
- /*
- * Currently Linux do AIO only for files opened with O_DIRECT
- * specified so check NOCACHE flag too
- */
- if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
- (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
-
- s->aio_ctx = laio_init();
- if (!s->aio_ctx) {
- goto out_free_buf;
- }
- s->use_aio = 1;
- } else
-#endif
- {
-#ifdef CONFIG_LINUX_AIO
- s->use_aio = 0;
-#endif
+ if (raw_set_aio(&s->aio_ctx, &s->use_aio, bdrv_flags)) {
+ goto out_close;
}
+#endif
#ifdef CONFIG_XFS
if (platform_test_xfs_fd(s->fd)) {
return 0;
-out_free_buf:
- qemu_vfree(s->aligned_buf);
out_close:
- close(fd);
+ qemu_close(fd);
return -errno;
}
return raw_open_common(bs, filename, flags, 0);
}
+static int raw_reopen_prepare(BDRVReopenState *state,
+ BlockReopenQueue *queue, Error **errp)
+{
+ BDRVRawState *s;
+ BDRVRawReopenState *raw_s;
+ int ret = 0;
+
+ assert(state != NULL);
+ assert(state->bs != NULL);
+
+ s = state->bs->opaque;
+
+ state->opaque = g_malloc0(sizeof(BDRVRawReopenState));
+ raw_s = state->opaque;
+
+#ifdef CONFIG_LINUX_AIO
+ raw_s->use_aio = s->use_aio;
+
+ /* we can use s->aio_ctx instead of a copy, because the use_aio flag is
+ * valid in the 'false' condition even if aio_ctx is set, and raw_set_aio()
+ * won't override aio_ctx if aio_ctx is non-NULL */
+ if (raw_set_aio(&s->aio_ctx, &raw_s->use_aio, state->flags)) {
+ return -1;
+ }
+#endif
+
+ raw_parse_flags(state->flags, &raw_s->open_flags);
+
+ raw_s->fd = -1;
+
+ int fcntl_flags = O_APPEND | O_ASYNC | O_NONBLOCK;
+#ifdef O_NOATIME
+ fcntl_flags |= O_NOATIME;
+#endif
+
+ if ((raw_s->open_flags & ~fcntl_flags) == (s->open_flags & ~fcntl_flags)) {
+ /* dup the original fd */
+ /* TODO: use qemu fcntl wrapper */
+#ifdef F_DUPFD_CLOEXEC
+ raw_s->fd = fcntl(s->fd, F_DUPFD_CLOEXEC, 0);
+#else
+ raw_s->fd = dup(s->fd);
+ if (raw_s->fd != -1) {
+ qemu_set_cloexec(raw_s->fd);
+ }
+#endif
+ if (raw_s->fd >= 0) {
+ ret = fcntl_setfl(raw_s->fd, raw_s->open_flags);
+ if (ret) {
+ qemu_close(raw_s->fd);
+ raw_s->fd = -1;
+ }
+ }
+ }
+
+ /* If we cannot use fcntl, or fcntl failed, fall back to qemu_open() */
+ if (raw_s->fd == -1) {
+ assert(!(raw_s->open_flags & O_CREAT));
+ raw_s->fd = qemu_open(state->bs->filename, raw_s->open_flags);
+ if (raw_s->fd == -1) {
+ ret = -1;
+ }
+ }
+ return ret;
+}
+
+
+static void raw_reopen_commit(BDRVReopenState *state)
+{
+ BDRVRawReopenState *raw_s = state->opaque;
+ BDRVRawState *s = state->bs->opaque;
+
+ s->open_flags = raw_s->open_flags;
+
+ qemu_close(s->fd);
+ s->fd = raw_s->fd;
+#ifdef CONFIG_LINUX_AIO
+ s->use_aio = raw_s->use_aio;
+#endif
+
+ g_free(state->opaque);
+ state->opaque = NULL;
+}
+
+
+static void raw_reopen_abort(BDRVReopenState *state)
+{
+ BDRVRawReopenState *raw_s = state->opaque;
+
+ /* nothing to do if NULL, we didn't get far enough */
+ if (raw_s == NULL) {
+ return;
+ }
+
+ if (raw_s->fd >= 0) {
+ qemu_close(raw_s->fd);
+ raw_s->fd = -1;
+ }
+ g_free(state->opaque);
+ state->opaque = NULL;
+}
+
+
/* XXX: use host sector size if necessary with:
#ifdef DIOCGSECTORSIZE
{
* boundary. Check if this is the case or tell the low-level
* driver that it needs to copy the buffer.
*/
- if (s->aligned_buf) {
+ if ((bs->open_flags & BDRV_O_NOCACHE)) {
if (!qiov_is_aligned(bs, qiov)) {
type |= QEMU_AIO_MISALIGNED;
#ifdef CONFIG_LINUX_AIO
{
BDRVRawState *s = bs->opaque;
if (s->fd >= 0) {
- close(s->fd);
+ qemu_close(s->fd);
s->fd = -1;
- if (s->aligned_buf != NULL)
- qemu_vfree(s->aligned_buf);
}
}
}
if (size == 0)
#endif
-#ifdef CONFIG_COCOA
+#if defined(__APPLE__) && defined(__MACH__)
size = LONG_LONG_MAX;
#else
size = lseek(fd, 0LL, SEEK_END);
options++;
}
- fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
- 0644);
+ fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+ 0644);
if (fd < 0) {
result = -errno;
} else {
if (ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
result = -errno;
}
- if (close(fd) != 0) {
+ if (qemu_close(fd) != 0) {
result = -errno;
}
}
return result;
}
+/*
+ * Returns true iff the specified sector is present in the disk image. Drivers
+ * not implementing the functionality are assumed to not support backing files,
+ * hence all their sectors are reported as allocated.
+ *
+ * If 'sector_num' is beyond the end of the disk image the return value is 0
+ * and 'pnum' is set to 0.
+ *
+ * 'pnum' is set to the number of sectors (including and immediately following
+ * the specified sector) that are known to be in the same
+ * allocated/unallocated state.
+ *
+ * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
+ * beyond the end of the disk image it will be clamped.
+ */
+static int coroutine_fn raw_co_is_allocated(BlockDriverState *bs,
+ int64_t sector_num,
+ int nb_sectors, int *pnum)
+{
+ off_t start, data, hole;
+ int ret;
+
+ ret = fd_open(bs);
+ if (ret < 0) {
+ return ret;
+ }
+
+ start = sector_num * BDRV_SECTOR_SIZE;
+
+#ifdef CONFIG_FIEMAP
+
+ BDRVRawState *s = bs->opaque;
+ struct {
+ struct fiemap fm;
+ struct fiemap_extent fe;
+ } f;
+
+ f.fm.fm_start = start;
+ f.fm.fm_length = (int64_t)nb_sectors * BDRV_SECTOR_SIZE;
+ f.fm.fm_flags = 0;
+ f.fm.fm_extent_count = 1;
+ f.fm.fm_reserved = 0;
+ if (ioctl(s->fd, FS_IOC_FIEMAP, &f) == -1) {
+ /* Assume everything is allocated. */
+ *pnum = nb_sectors;
+ return 1;
+ }
+
+ if (f.fm.fm_mapped_extents == 0) {
+ /* No extents found, data is beyond f.fm.fm_start + f.fm.fm_length.
+ * f.fm.fm_start + f.fm.fm_length must be clamped to the file size!
+ */
+ off_t length = lseek(s->fd, 0, SEEK_END);
+ hole = f.fm.fm_start;
+ data = MIN(f.fm.fm_start + f.fm.fm_length, length);
+ } else {
+ data = f.fe.fe_logical;
+ hole = f.fe.fe_logical + f.fe.fe_length;
+ }
+
+#elif defined SEEK_HOLE && defined SEEK_DATA
+
+ BDRVRawState *s = bs->opaque;
+
+ hole = lseek(s->fd, start, SEEK_HOLE);
+ if (hole == -1) {
+ /* -ENXIO indicates that sector_num was past the end of the file.
+ * There is a virtual hole there. */
+ assert(errno != -ENXIO);
+
+ /* Most likely EINVAL. Assume everything is allocated. */
+ *pnum = nb_sectors;
+ return 1;
+ }
+
+ if (hole > start) {
+ data = start;
+ } else {
+ /* On a hole. We need another syscall to find its end. */
+ data = lseek(s->fd, start, SEEK_DATA);
+ if (data == -1) {
+ data = lseek(s->fd, 0, SEEK_END);
+ }
+ }
+#else
+ *pnum = nb_sectors;
+ return 1;
+#endif
+
+ if (data <= start) {
+ /* On a data extent, compute sectors to the end of the extent. */
+ *pnum = MIN(nb_sectors, (hole - start) / BDRV_SECTOR_SIZE);
+ return 1;
+ } else {
+ /* On a hole, compute sectors to the beginning of the next extent. */
+ *pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
+ return 0;
+ }
+}
+
#ifdef CONFIG_XFS
static int xfs_discard(BDRVRawState *s, int64_t sector_num, int nb_sectors)
{
.instance_size = sizeof(BDRVRawState),
.bdrv_probe = NULL, /* no probe for protocols */
.bdrv_file_open = raw_open,
+ .bdrv_reopen_prepare = raw_reopen_prepare,
+ .bdrv_reopen_commit = raw_reopen_commit,
+ .bdrv_reopen_abort = raw_reopen_abort,
.bdrv_close = raw_close,
.bdrv_create = raw_create,
.bdrv_co_discard = raw_co_discard,
+ .bdrv_co_is_allocated = raw_co_is_allocated,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
/***********************************************/
/* host device */
-#ifdef CONFIG_COCOA
+#if defined(__APPLE__) && defined(__MACH__)
static kern_return_t FindEjectableCDMedia( io_iterator_t *mediaIterator );
static kern_return_t GetBSDPath( io_iterator_t mediaIterator, char *bsdPath, CFIndex maxPathSize );
{
BDRVRawState *s = bs->opaque;
-#ifdef CONFIG_COCOA
+#if defined(__APPLE__) && defined(__MACH__)
if (strstart(filename, "/dev/cdrom", NULL)) {
kern_return_t kernResult;
io_iterator_t mediaIterator;
if ( bsdPath[ 0 ] != '\0' ) {
strcat(bsdPath,"s0");
/* some CDs don't have a partition 0 */
- fd = open(bsdPath, O_RDONLY | O_BINARY | O_LARGEFILE);
+ fd = qemu_open(bsdPath, O_RDONLY | O_BINARY | O_LARGEFILE);
if (fd < 0) {
bsdPath[strlen(bsdPath)-1] = '1';
} else {
- close(fd);
+ qemu_close(fd);
}
filename = bsdPath;
}
last_media_present = (s->fd >= 0);
if (s->fd >= 0 &&
(get_clock() - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
- close(s->fd);
+ qemu_close(s->fd);
s->fd = -1;
#ifdef DEBUG_FLOPPY
printf("Floppy closed\n");
#endif
return -EIO;
}
- s->fd = open(bs->filename, s->open_flags & ~O_NONBLOCK);
+ s->fd = qemu_open(bs->filename, s->open_flags & ~O_NONBLOCK);
if (s->fd < 0) {
s->fd_error_time = get_clock();
s->fd_got_error = 1;
options++;
}
- fd = open(filename, O_WRONLY | O_BINARY);
+ fd = qemu_open(filename, O_WRONLY | O_BINARY);
if (fd < 0)
return -errno;
else if (lseek(fd, 0, SEEK_END) < total_size * BDRV_SECTOR_SIZE)
ret = -ENOSPC;
- close(fd);
+ qemu_close(fd);
return ret;
}
return ret;
/* close fd so that we can reopen it as needed */
- close(s->fd);
+ qemu_close(s->fd);
s->fd = -1;
s->fd_media_changed = 1;
struct floppy_struct fdparam;
struct stat st;
- if (strstart(filename, "/dev/fd", NULL))
+ if (strstart(filename, "/dev/fd", NULL) &&
+ !strstart(filename, "/dev/fdset/", NULL)) {
prio = 50;
+ }
- fd = open(filename, O_RDONLY | O_NONBLOCK);
+ fd = qemu_open(filename, O_RDONLY | O_NONBLOCK);
if (fd < 0) {
goto out;
}
prio = 100;
outc:
- close(fd);
+ qemu_close(fd);
out:
return prio;
}
return ret;
}
-static void floppy_eject(BlockDriverState *bs, int eject_flag)
+static void floppy_eject(BlockDriverState *bs, bool eject_flag)
{
BDRVRawState *s = bs->opaque;
int fd;
if (s->fd >= 0) {
- close(s->fd);
+ qemu_close(s->fd);
s->fd = -1;
}
- fd = open(bs->filename, s->open_flags | O_NONBLOCK);
+ fd = qemu_open(bs->filename, s->open_flags | O_NONBLOCK);
if (fd >= 0) {
if (ioctl(fd, FDEJECT, 0) < 0)
perror("FDEJECT");
- close(fd);
+ qemu_close(fd);
}
}
int prio = 0;
struct stat st;
- fd = open(filename, O_RDONLY | O_NONBLOCK);
+ fd = qemu_open(filename, O_RDONLY | O_NONBLOCK);
if (fd < 0) {
goto out;
}
prio = 100;
outc:
- close(fd);
+ qemu_close(fd);
out:
return prio;
}
return 0;
}
-static void cdrom_eject(BlockDriverState *bs, int eject_flag)
+static void cdrom_eject(BlockDriverState *bs, bool eject_flag)
{
BDRVRawState *s = bs->opaque;
* FreeBSD seems to not notice sometimes...
*/
if (s->fd >= 0)
- close(s->fd);
- fd = open(bs->filename, s->open_flags, 0644);
+ qemu_close(s->fd);
+ fd = qemu_open(bs->filename, s->open_flags, 0644);
if (fd < 0) {
s->fd = -1;
return -EIO;
return raw_getlength(bs) > 0;
}
-static void cdrom_eject(BlockDriverState *bs, int eject_flag)
+static void cdrom_eject(BlockDriverState *bs, bool eject_flag)
{
BDRVRawState *s = bs->opaque;
projects / qemu.git / blobdiff