@@ -314,7 +314,7 @@ static inline void libxfs_buftarg_drain(struct xfs_buftarg *btp)
void libxfs_buftarg_free(struct xfs_buftarg *btp);
int xfile_alloc_buftarg(struct xfs_mount *mp, const char *descr,
- struct xfs_buftarg **btpp);
+ unsigned long long maxrange, struct xfs_buftarg **btpp);
void xfile_free_buftarg(struct xfs_buftarg *btp);
#endif /* __XFS_MOUNT_H__ */
@@ -483,13 +483,14 @@ int
xfile_alloc_buftarg(
struct xfs_mount *mp,
const char *descr,
+ unsigned long long maxrange,
struct xfs_buftarg **btpp)
{
struct xfs_buftarg *btp;
struct xfile *xfile;
int error;
- error = xfile_create(descr, &xfile);
+ error = xfile_create(descr, maxrange, &xfile);
if (error)
return error;
@@ -127,6 +127,146 @@ xfile_create_fd(
return fd;
}
+struct xfile_fcb {
+ struct list_head fcb_list;
+ int fd;
+ unsigned int refcount;
+};
+
+static LIST_HEAD(fcb_list);
+static pthread_mutex_t fcb_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+/* Create a new memfd. */
+static inline int
+xfile_fcb_create(
+ const char *description,
+ struct xfile_fcb **fcbp)
+{
+ struct xfile_fcb *fcb;
+ int fd;
+
+ fd = xfile_create_fd(description);
+ if (fd < 0)
+ return -errno;
+
+ fcb = malloc(sizeof(struct xfile_fcb));
+ if (!fcb) {
+ close(fd);
+ return -ENOMEM;
+ }
+
+ list_head_init(&fcb->fcb_list);
+ fcb->fd = fd;
+ fcb->refcount = 1;
+
+ *fcbp = fcb;
+ return 0;
+}
+
+/* Release an xfile control block */
+static void
+xfile_fcb_irele(
+ struct xfile_fcb *fcb,
+ loff_t pos,
+ uint64_t len)
+{
+ /*
+ * If this memfd is linked only to itself, it's private, so we can
+ * close it without taking any locks.
+ */
+ if (list_empty(&fcb->fcb_list)) {
+ close(fcb->fd);
+ free(fcb);
+ return;
+ }
+
+ pthread_mutex_lock(&fcb_mutex);
+ if (--fcb->refcount == 0) {
+ /* If we're the last user of this memfd file, kill it fast. */
+ list_del(&fcb->fcb_list);
+ close(fcb->fd);
+ free(fcb);
+ } else if (len > 0) {
+ struct stat statbuf;
+ int ret;
+
+ /*
+ * If we were using the end of a partitioned file, free the
+ * address space. IOWs, bonus points if you delete these in
+ * reverse-order of creation.
+ */
+ ret = fstat(fcb->fd, &statbuf);
+ if (!ret && statbuf.st_size == pos + len) {
+ ret = ftruncate(fcb->fd, pos);
+ }
+ }
+ pthread_mutex_unlock(&fcb_mutex);
+}
+
+/*
+ * Find an memfd that can accomodate the given amount of address space.
+ */
+static int
+xfile_fcb_find(
+ const char *description,
+ uint64_t maxrange,
+ loff_t *pos,
+ struct xfile_fcb **fcbp)
+{
+ struct xfile_fcb *fcb;
+ int ret;
+ int error;
+
+ /* No maximum range means that the caller gets a private memfd. */
+ if (maxrange == 0) {
+ *pos = 0;
+ return xfile_fcb_create(description, fcbp);
+ }
+
+ pthread_mutex_lock(&fcb_mutex);
+
+ /*
+ * If we only need a certain number of byte range, look for one with
+ * available file range.
+ */
+ list_for_each_entry(fcb, &fcb_list, fcb_list) {
+ struct stat statbuf;
+
+ ret = fstat(fcb->fd, &statbuf);
+ if (ret)
+ continue;
+
+ ret = ftruncate(fcb->fd, statbuf.st_size + maxrange);
+ if (ret)
+ continue;
+
+ fcb->refcount++;
+ *pos = statbuf.st_size;
+ *fcbp = fcb;
+ goto out_unlock;
+ }
+
+ /* Otherwise, open a new memfd and add it to our list. */
+ error = xfile_fcb_create(description, &fcb);
+ if (error)
+ return error;
+
+ ret = ftruncate(fcb->fd, maxrange);
+ if (ret) {
+ error = -errno;
+ xfile_fcb_irele(fcb, 0, maxrange);
+ return error;
+ }
+
+ list_add_tail(&fcb->fcb_list, &fcb_list);
+ *pos = 0;
+ *fcbp = fcb;
+
+out_unlock:
+ pthread_mutex_unlock(&fcb_mutex);
+ return error;
+}
+
/*
* Create an xfile of the given size. The description will be used in the
* trace output.
@@ -134,6 +274,7 @@ xfile_create_fd(
int
xfile_create(
const char *description,
+ unsigned long long maxrange,
struct xfile **xfilep)
{
struct xfile *xf;
@@ -143,13 +284,14 @@ xfile_create(
if (!xf)
return -ENOMEM;
- xf->fd = xfile_create_fd(description);
- if (xf->fd < 0) {
- error = -errno;
+ error = xfile_fcb_find(description, maxrange, &xf->partition_pos,
+ &xf->fcb);
+ if (error) {
kmem_free(xf);
return error;
}
+ xf->partition_bytes = maxrange;
*xfilep = xf;
return 0;
}
@@ -159,7 +301,7 @@ void
xfile_destroy(
struct xfile *xf)
{
- close(xf->fd);
+ xfile_fcb_irele(xf->fcb, xf->partition_pos, xf->partition_bytes);
kmem_free(xf);
}
@@ -167,6 +309,9 @@ static inline loff_t
xfile_maxbytes(
struct xfile *xf)
{
+ if (xf->partition_bytes > 0)
+ return xf->partition_bytes;
+
if (sizeof(loff_t) == 8)
return LLONG_MAX;
return LONG_MAX;
@@ -192,7 +337,7 @@ xfile_pread(
if (xfile_maxbytes(xf) - pos < count)
return -EFBIG;
- ret = pread(xf->fd, buf, count, pos);
+ ret = pread(xf->fcb->fd, buf, count, pos + xf->partition_pos);
if (ret >= 0)
return ret;
return -errno;
@@ -218,7 +363,7 @@ xfile_pwrite(
if (xfile_maxbytes(xf) - pos < count)
return -EFBIG;
- ret = pwrite(xf->fd, buf, count, pos);
+ ret = pwrite(xf->fcb->fd, buf, count, pos + xf->partition_pos);
if (ret >= 0)
return ret;
return -errno;
@@ -232,6 +377,37 @@ xfile_bytes(
struct xfile_stat xs;
int ret;
+ if (xf->partition_bytes > 0) {
+ loff_t data_pos = xf->partition_pos;
+ loff_t stop_pos = data_pos + xf->partition_bytes;
+ loff_t hole_pos;
+ unsigned long long bytes = 0;
+
+ data_pos = lseek(xf->fcb->fd, data_pos, SEEK_DATA);
+ while (data_pos >= 0 && data_pos < stop_pos) {
+ hole_pos = lseek(xf->fcb->fd, data_pos, SEEK_HOLE);
+ if (hole_pos < 0) {
+ /* save error, break */
+ data_pos = hole_pos;
+ break;
+ }
+ if (hole_pos >= stop_pos) {
+ bytes += stop_pos - data_pos;
+ return bytes;
+ }
+ bytes += hole_pos - data_pos;
+
+ data_pos = lseek(xf->fcb->fd, hole_pos, SEEK_DATA);
+ }
+ if (data_pos < 0) {
+ if (errno == ENXIO)
+ return bytes;
+ return xf->partition_bytes;
+ }
+
+ return bytes;
+ }
+
ret = xfile_stat(xf, &xs);
if (ret)
return 0;
@@ -248,7 +424,13 @@ xfile_stat(
struct stat ks;
int error;
- error = fstat(xf->fd, &ks);
+ if (xf->partition_bytes > 0) {
+ statbuf->size = xf->partition_bytes;
+ statbuf->bytes = xf->partition_bytes;
+ return 0;
+ }
+
+ error = fstat(xf->fcb->fd, &ks);
if (error)
return -errno;
@@ -275,7 +457,7 @@ xfile_dump(
}
/* reroute our xfile to stdin and shut everything else */
- dup2(xf->fd, 0);
+ dup2(xf->fcb->fd, 0);
for (i = 3; i < 1024; i++)
close(i);
@@ -292,7 +474,7 @@ xfile_prealloc(
int error;
count = min(count, xfile_maxbytes(xf) - pos);
- error = fallocate(xf->fd, 0, pos, count);
+ error = fallocate(xf->fcb->fd, 0, pos + xf->partition_pos, count);
if (error)
return -errno;
return 0;
@@ -6,13 +6,18 @@
#ifndef __LIBXFS_XFILE_H__
#define __LIBXFS_XFILE_H__
+struct xfile_fcb;
+
struct xfile {
- int fd;
+ struct xfile_fcb *fcb;
+ loff_t partition_pos;
+ uint64_t partition_bytes;
};
void xfile_libinit(void);
-int xfile_create(const char *description, struct xfile **xfilep);
+int xfile_create(const char *description, unsigned long long maxrange,
+ struct xfile **xfilep);
void xfile_destroy(struct xfile *xf);
ssize_t xfile_pread(struct xfile *xf, void *buf, size_t count, loff_t pos);