@@ -109,6 +109,149 @@ xfile_create_fd(
return fd;
}
+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 maxpos,
+ loff_t *posp,
+ struct xfile_fcb **fcbp)
+{
+ struct xfile_fcb *fcb;
+ int ret;
+ int error;
+
+ /* No maximum range means that the caller gets a private memfd. */
+ if (maxpos == 0) {
+ *posp = 0;
+ return xfile_fcb_create(description, fcbp);
+ }
+
+ /* round up to page granularity so we can do mmap */
+ maxpos = roundup_64(maxpos, PAGE_SIZE);
+
+ 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;
+ loff_t pos;
+
+ ret = fstat(fcb->fd, &statbuf);
+ if (ret)
+ continue;
+ pos = roundup_64(statbuf.st_size, PAGE_SIZE);
+
+ /*
+ * Truncate up to ensure that the memfd can actually handle
+ * writes to the end of the range.
+ */
+ ret = ftruncate(fcb->fd, pos + maxpos);
+ if (ret)
+ continue;
+
+ fcb->refcount++;
+ *posp = pos;
+ *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, maxpos);
+ if (ret) {
+ error = -errno;
+ xfile_fcb_irele(fcb, 0, maxpos);
+ return error;
+ }
+
+ list_add_tail(&fcb->fcb_list, &fcb_list);
+ *posp = 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.
@@ -116,6 +259,7 @@ xfile_create_fd(
int
xfile_create(
const char *description,
+ unsigned long long maxpos,
struct xfile **xfilep)
{
struct xfile *xf;
@@ -125,13 +269,14 @@ xfile_create(
if (!xf)
return -ENOMEM;
- xf->fd = xfile_create_fd(description);
- if (xf->fd < 0) {
- error = -errno;
+ error = xfile_fcb_find(description, maxpos, &xf->partition_pos,
+ &xf->fcb);
+ if (error) {
kfree(xf);
return error;
}
+ xf->partition_bytes = maxpos;
*xfilep = xf;
return 0;
}
@@ -141,7 +286,7 @@ void
xfile_destroy(
struct xfile *xf)
{
- close(xf->fd);
+ xfile_fcb_irele(xf->fcb, xf->partition_pos, xf->partition_bytes);
kfree(xf);
}
@@ -149,6 +294,9 @@ 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;
@@ -172,7 +320,7 @@ xfile_load(
if (xfile_maxbytes(xf) - pos < count)
return -ENOMEM;
- ret = pread(xf->fd, buf, count, pos);
+ ret = pread(xf->fcb->fd, buf, count, pos + xf->partition_pos);
if (ret < 0)
return -errno;
if (ret != count)
@@ -198,7 +346,7 @@ xfile_store(
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 -errno;
if (ret != count)
@@ -214,6 +362,37 @@ 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;
@@ -230,7 +409,13 @@ 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;
@@ -6,11 +6,20 @@
#ifndef __LIBXFS_XFILE_H__
#define __LIBXFS_XFILE_H__
+struct xfile_fcb {
+ struct list_head fcb_list;
+ int fd;
+ unsigned int refcount;
+};
+
struct xfile {
- int fd;
+ struct xfile_fcb *fcb;
+ loff_t partition_pos;
+ uint64_t partition_bytes;
};
-int xfile_create(const char *description, struct xfile **xfilep);
+int xfile_create(const char *description, unsigned long long maxpos,
+ struct xfile **xfilep);
void xfile_destroy(struct xfile *xf);
ssize_t xfile_load(struct xfile *xf, void *buf, size_t count, loff_t pos);