@@ -1915,19 +1915,13 @@ four of those five higher level data structures.
The fifth use case is discussed in the :ref:`realtime summary <rtsummary>` case
study.
-The most general storage interface supported by the xfile enables the reading
-and writing of arbitrary quantities of data at arbitrary offsets in the xfile.
-This capability is provided by ``xfile_pread`` and ``xfile_pwrite`` functions,
-which behave similarly to their userspace counterparts.
XFS is very record-based, which suggests that the ability to load and store
complete records is important.
-To support these cases, a pair of ``xfile_obj_load`` and ``xfile_obj_store``
-functions are provided to read and persist objects into an xfile.
-They are internally the same as pread and pwrite, except that they treat any
-error as an out of memory error.
-For online repair, squashing error conditions in this manner is an acceptable
-behavior because the only reaction is to abort the operation back to userspace.
-All five xfile usecases can be serviced by these four functions.
+To support these cases, a pair of ``xfile_load`` and ``xfile_store``
+functions are provided to read and persist objects into an xfile that treat any
+error as an out of memory error. For online repair, squashing error conditions
+in this manner is an acceptable behavior because the only reaction is to abort
+the operation back to userspace.
However, no discussion of file access idioms is complete without answering the
question, "But what about mmap?"
@@ -1939,10 +1933,9 @@ tmpfs can only push a pagecache folio to the swap cache if the folio is neither
pinned nor locked, which means the xfile must not pin too many folios.
Short term direct access to xfile contents is done by locking the pagecache
-folio and mapping it into kernel address space.
-Programmatic access (e.g. pread and pwrite) uses this mechanism.
-Folio locks are not supposed to be held for long periods of time, so long
-term direct access to xfile contents is done by bumping the folio refcount,
+folio and mapping it into kernel address space. Object load and store uses this
+mechanism. Folio locks are not supposed to be held for long periods of time, so
+long term direct access to xfile contents is done by bumping the folio refcount,
mapping it into kernel address space, and dropping the folio lock.
These long term users *must* be responsive to memory reclaim by hooking into
the shrinker infrastructure to know when to release folios.
@@ -118,7 +118,7 @@ xfsum_load(
xfs_rtsumoff_t sumoff,
union xfs_suminfo_raw *rawinfo)
{
- return xfile_obj_load(sc->xfile, rawinfo,
+ return xfile_load(sc->xfile, rawinfo,
sizeof(union xfs_suminfo_raw),
sumoff << XFS_WORDLOG);
}
@@ -129,7 +129,7 @@ xfsum_store(
xfs_rtsumoff_t sumoff,
const union xfs_suminfo_raw rawinfo)
{
- return xfile_obj_store(sc->xfile, &rawinfo,
+ return xfile_store(sc->xfile, &rawinfo,
sizeof(union xfs_suminfo_raw),
sumoff << XFS_WORDLOG);
}
@@ -141,7 +141,7 @@ xfsum_copyout(
union xfs_suminfo_raw *rawinfo,
unsigned int nr_words)
{
- return xfile_obj_load(sc->xfile, rawinfo, nr_words << XFS_WORDLOG,
+ return xfile_load(sc->xfile, rawinfo, nr_words << XFS_WORDLOG,
sumoff << XFS_WORDLOG);
}
@@ -903,8 +903,8 @@ DECLARE_EVENT_CLASS(xfile_class,
DEFINE_EVENT(xfile_class, name, \
TP_PROTO(struct xfile *xf, loff_t pos, unsigned long long bytecount), \
TP_ARGS(xf, pos, bytecount))
-DEFINE_XFILE_EVENT(xfile_pread);
-DEFINE_XFILE_EVENT(xfile_pwrite);
+DEFINE_XFILE_EVENT(xfile_load);
+DEFINE_XFILE_EVENT(xfile_store);
DEFINE_XFILE_EVENT(xfile_seek_data);
DEFINE_XFILE_EVENT(xfile_get_page);
DEFINE_XFILE_EVENT(xfile_put_page);
@@ -136,7 +136,7 @@ xfarray_load(
if (idx >= array->nr)
return -ENODATA;
- return xfile_obj_load(array->xfile, ptr, array->obj_size,
+ return xfile_load(array->xfile, ptr, array->obj_size,
xfarray_pos(array, idx));
}
@@ -152,7 +152,7 @@ xfarray_is_unset(
if (array->unset_slots == 0)
return false;
- error = xfile_obj_load(array->xfile, temp, array->obj_size, pos);
+ error = xfile_load(array->xfile, temp, array->obj_size, pos);
if (!error && xfarray_element_is_null(array, temp))
return true;
@@ -184,7 +184,7 @@ xfarray_unset(
return 0;
memset(temp, 0, array->obj_size);
- error = xfile_obj_store(array->xfile, temp, array->obj_size, pos);
+ error = xfile_store(array->xfile, temp, array->obj_size, pos);
if (error)
return error;
@@ -209,7 +209,7 @@ xfarray_store(
ASSERT(!xfarray_element_is_null(array, ptr));
- ret = xfile_obj_store(array->xfile, ptr, array->obj_size,
+ ret = xfile_store(array->xfile, ptr, array->obj_size,
xfarray_pos(array, idx));
if (ret)
return ret;
@@ -245,12 +245,12 @@ xfarray_store_anywhere(
for (pos = 0;
pos < endpos && array->unset_slots > 0;
pos += array->obj_size) {
- error = xfile_obj_load(array->xfile, temp, array->obj_size,
+ error = xfile_load(array->xfile, temp, array->obj_size,
pos);
if (error || !xfarray_element_is_null(array, temp))
continue;
- error = xfile_obj_store(array->xfile, ptr, array->obj_size,
+ error = xfile_store(array->xfile, ptr, array->obj_size,
pos);
if (error)
return error;
@@ -552,7 +552,7 @@ xfarray_isort(
trace_xfarray_isort(si, lo, hi);
xfarray_sort_bump_loads(si);
- error = xfile_obj_load(si->array->xfile, scratch, len, lo_pos);
+ error = xfile_load(si->array->xfile, scratch, len, lo_pos);
if (error)
return error;
@@ -560,7 +560,7 @@ xfarray_isort(
sort(scratch, hi - lo + 1, si->array->obj_size, si->cmp_fn, NULL);
xfarray_sort_bump_stores(si);
- return xfile_obj_store(si->array->xfile, scratch, len, lo_pos);
+ return xfile_store(si->array->xfile, scratch, len, lo_pos);
}
/* Grab a page for sorting records. */
@@ -858,7 +858,7 @@ xfarray_sort_load_cached(
if (xfarray_sort_terminated(si, &error))
return error;
- return xfile_obj_load(si->array->xfile, ptr,
+ return xfile_load(si->array->xfile, ptr,
si->array->obj_size, idx_pos);
}
@@ -118,13 +118,11 @@ xfile_destroy(
}
/*
- * Read a memory object directly from the xfile's page cache. Unlike regular
- * pread, we return -E2BIG and -EFBIG for reads that are too large or at too
- * high an offset, instead of truncating the read. Otherwise, we return
- * bytes read or an error code, like regular pread.
+ * Load an object. Since we're treating this file as "memory", any error or
+ * short IO is treated as a failure to allocate memory.
*/
-ssize_t
-xfile_pread(
+int
+xfile_load(
struct xfile *xf,
void *buf,
size_t count,
@@ -133,16 +131,15 @@ xfile_pread(
struct inode *inode = file_inode(xf->file);
struct address_space *mapping = inode->i_mapping;
struct page *page = NULL;
- ssize_t read = 0;
unsigned int pflags;
int error = 0;
if (count > MAX_RW_COUNT)
- return -E2BIG;
+ return -ENOMEM;
if (inode->i_sb->s_maxbytes - pos < count)
- return -EFBIG;
+ return -ENOMEM;
- trace_xfile_pread(xf, pos, count);
+ trace_xfile_load(xf, pos, count);
pflags = memalloc_nofs_save();
while (count > 0) {
@@ -160,8 +157,10 @@ xfile_pread(
__GFP_NOWARN);
if (IS_ERR(page)) {
error = PTR_ERR(page);
- if (error != -ENOMEM)
+ if (error != -ENOMEM) {
+ error = -ENOMEM;
break;
+ }
memset(buf, 0, len);
goto advance;
@@ -185,23 +184,18 @@ xfile_pread(
count -= len;
pos += len;
buf += len;
- read += len;
}
memalloc_nofs_restore(pflags);
- if (read > 0)
- return read;
return error;
}
/*
- * Write a memory object directly to the xfile's page cache. Unlike regular
- * pwrite, we return -E2BIG and -EFBIG for writes that are too large or at too
- * high an offset, instead of truncating the write. Otherwise, we return
- * bytes written or an error code, like regular pwrite.
+ * Store an object. Since we're treating this file as "memory", any error or
+ * short IO is treated as a failure to allocate memory.
*/
-ssize_t
-xfile_pwrite(
+int
+xfile_store(
struct xfile *xf,
const void *buf,
size_t count,
@@ -211,16 +205,15 @@ xfile_pwrite(
struct address_space *mapping = inode->i_mapping;
const struct address_space_operations *aops = mapping->a_ops;
struct page *page = NULL;
- ssize_t written = 0;
unsigned int pflags;
int error = 0;
if (count > MAX_RW_COUNT)
- return -E2BIG;
+ return -ENOMEM;
if (inode->i_sb->s_maxbytes - pos < count)
- return -EFBIG;
+ return -ENOMEM;
- trace_xfile_pwrite(xf, pos, count);
+ trace_xfile_store(xf, pos, count);
pflags = memalloc_nofs_save();
while (count > 0) {
@@ -239,8 +232,10 @@ xfile_pwrite(
*/
error = aops->write_begin(NULL, mapping, pos, len, &page,
&fsdata);
- if (error)
+ if (error) {
+ error = -ENOMEM;
break;
+ }
/*
* xfile pages must never be mapped into userspace, so we skip
@@ -259,13 +254,14 @@ xfile_pwrite(
ret = aops->write_end(NULL, mapping, pos, len, len, page,
fsdata);
if (ret < 0) {
- error = ret;
+ error = -ENOMEM;
break;
}
- written += ret;
- if (ret != len)
+ if (ret != len) {
+ error = -ENOMEM;
break;
+ }
count -= ret;
pos += ret;
@@ -273,8 +269,6 @@ xfile_pwrite(
}
memalloc_nofs_restore(pflags);
- if (written > 0)
- return written;
return error;
}
@@ -29,38 +29,10 @@ struct xfile {
int xfile_create(const char *description, loff_t isize, struct xfile **xfilep);
void xfile_destroy(struct xfile *xf);
-ssize_t xfile_pread(struct xfile *xf, void *buf, size_t count, loff_t pos);
-ssize_t xfile_pwrite(struct xfile *xf, const void *buf, size_t count,
+int xfile_load(struct xfile *xf, void *buf, size_t count, loff_t pos);
+int xfile_store(struct xfile *xf, const void *buf, size_t count,
loff_t pos);
-/*
- * Load an object. Since we're treating this file as "memory", any error or
- * short IO is treated as a failure to allocate memory.
- */
-static inline int
-xfile_obj_load(struct xfile *xf, void *buf, size_t count, loff_t pos)
-{
- ssize_t ret = xfile_pread(xf, buf, count, pos);
-
- if (ret < 0 || ret != count)
- return -ENOMEM;
- return 0;
-}
-
-/*
- * Store an object. Since we're treating this file as "memory", any error or
- * short IO is treated as a failure to allocate memory.
- */
-static inline int
-xfile_obj_store(struct xfile *xf, const void *buf, size_t count, loff_t pos)
-{
- ssize_t ret = xfile_pwrite(xf, buf, count, pos);
-
- if (ret < 0 || ret != count)
- return -ENOMEM;
- return 0;
-}
-
loff_t xfile_seek_data(struct xfile *xf, loff_t pos);
int xfile_get_page(struct xfile *xf, loff_t offset, unsigned int len,