mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2024-12-28 16:53:49 +00:00
c4f1450ecc
Because it uses DIO writes, cachefiles is unable to make a write to the backing file if that write is not aligned to and sized according to the backing file's DIO block alignment. This makes it tricky to handle a write to the cache where the EOF on the network file is not correctly aligned. To get around this, netfslib attempts to tell the driver it is calling how much more data there is available beyond the EOF that it can use to pad the write (netfslib preclears the part of the folio above the EOF). However, it tries to tell the cache what the maximum length is, but doesn't calculate this correctly; and, in any case, cachefiles actually ignores the value and just skips the block. Fix this by: (1) Change the value passed to indicate the amount of extra data that can be added to the operation (now ->submit_extendable_to). This is much simpler to calculate as it's just the end of the folio minus the top of the data within the folio - rather than having to account for data spread over multiple folios. (2) Make cachefiles add some of this data if the subrequest it is given ends at the network file's i_size if the extra data is sufficient to pad out to a whole block. Signed-off-by: David Howells <dhowells@redhat.com> cc: Jeff Layton <jlayton@kernel.org> cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20240814203850.2240469-22-dhowells@redhat.com/ # v2 Signed-off-by: Christian Brauner <brauner@kernel.org>
761 lines
20 KiB
C
761 lines
20 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/* kiocb-using read/write
|
|
*
|
|
* Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*/
|
|
|
|
#include <linux/mount.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/file.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/falloc.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <trace/events/fscache.h>
|
|
#include "internal.h"
|
|
|
|
struct cachefiles_kiocb {
|
|
struct kiocb iocb;
|
|
refcount_t ki_refcnt;
|
|
loff_t start;
|
|
union {
|
|
size_t skipped;
|
|
size_t len;
|
|
};
|
|
struct cachefiles_object *object;
|
|
netfs_io_terminated_t term_func;
|
|
void *term_func_priv;
|
|
bool was_async;
|
|
unsigned int inval_counter; /* Copy of cookie->inval_counter */
|
|
u64 b_writing;
|
|
};
|
|
|
|
static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki)
|
|
{
|
|
if (refcount_dec_and_test(&ki->ki_refcnt)) {
|
|
cachefiles_put_object(ki->object, cachefiles_obj_put_ioreq);
|
|
fput(ki->iocb.ki_filp);
|
|
kfree(ki);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Handle completion of a read from the cache.
|
|
*/
|
|
static void cachefiles_read_complete(struct kiocb *iocb, long ret)
|
|
{
|
|
struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
|
|
struct inode *inode = file_inode(ki->iocb.ki_filp);
|
|
|
|
_enter("%ld", ret);
|
|
|
|
if (ret < 0)
|
|
trace_cachefiles_io_error(ki->object, inode, ret,
|
|
cachefiles_trace_read_error);
|
|
|
|
if (ki->term_func) {
|
|
if (ret >= 0) {
|
|
if (ki->object->cookie->inval_counter == ki->inval_counter)
|
|
ki->skipped += ret;
|
|
else
|
|
ret = -ESTALE;
|
|
}
|
|
|
|
ki->term_func(ki->term_func_priv, ret, ki->was_async);
|
|
}
|
|
|
|
cachefiles_put_kiocb(ki);
|
|
}
|
|
|
|
/*
|
|
* Initiate a read from the cache.
|
|
*/
|
|
static int cachefiles_read(struct netfs_cache_resources *cres,
|
|
loff_t start_pos,
|
|
struct iov_iter *iter,
|
|
enum netfs_read_from_hole read_hole,
|
|
netfs_io_terminated_t term_func,
|
|
void *term_func_priv)
|
|
{
|
|
struct cachefiles_object *object;
|
|
struct cachefiles_kiocb *ki;
|
|
struct file *file;
|
|
unsigned int old_nofs;
|
|
ssize_t ret = -ENOBUFS;
|
|
size_t len = iov_iter_count(iter), skipped = 0;
|
|
|
|
if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
|
|
goto presubmission_error;
|
|
|
|
fscache_count_read();
|
|
object = cachefiles_cres_object(cres);
|
|
file = cachefiles_cres_file(cres);
|
|
|
|
_enter("%pD,%li,%llx,%zx/%llx",
|
|
file, file_inode(file)->i_ino, start_pos, len,
|
|
i_size_read(file_inode(file)));
|
|
|
|
/* If the caller asked us to seek for data before doing the read, then
|
|
* we should do that now. If we find a gap, we fill it with zeros.
|
|
*/
|
|
if (read_hole != NETFS_READ_HOLE_IGNORE) {
|
|
loff_t off = start_pos, off2;
|
|
|
|
off2 = cachefiles_inject_read_error();
|
|
if (off2 == 0)
|
|
off2 = vfs_llseek(file, off, SEEK_DATA);
|
|
if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO && off2 != -ENXIO) {
|
|
skipped = 0;
|
|
ret = off2;
|
|
goto presubmission_error;
|
|
}
|
|
|
|
if (off2 == -ENXIO || off2 >= start_pos + len) {
|
|
/* The region is beyond the EOF or there's no more data
|
|
* in the region, so clear the rest of the buffer and
|
|
* return success.
|
|
*/
|
|
ret = -ENODATA;
|
|
if (read_hole == NETFS_READ_HOLE_FAIL)
|
|
goto presubmission_error;
|
|
|
|
iov_iter_zero(len, iter);
|
|
skipped = len;
|
|
ret = 0;
|
|
goto presubmission_error;
|
|
}
|
|
|
|
skipped = off2 - off;
|
|
iov_iter_zero(skipped, iter);
|
|
}
|
|
|
|
ret = -ENOMEM;
|
|
ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
|
|
if (!ki)
|
|
goto presubmission_error;
|
|
|
|
refcount_set(&ki->ki_refcnt, 2);
|
|
ki->iocb.ki_filp = file;
|
|
ki->iocb.ki_pos = start_pos + skipped;
|
|
ki->iocb.ki_flags = IOCB_DIRECT;
|
|
ki->iocb.ki_ioprio = get_current_ioprio();
|
|
ki->skipped = skipped;
|
|
ki->object = object;
|
|
ki->inval_counter = cres->inval_counter;
|
|
ki->term_func = term_func;
|
|
ki->term_func_priv = term_func_priv;
|
|
ki->was_async = true;
|
|
|
|
if (ki->term_func)
|
|
ki->iocb.ki_complete = cachefiles_read_complete;
|
|
|
|
get_file(ki->iocb.ki_filp);
|
|
cachefiles_grab_object(object, cachefiles_obj_get_ioreq);
|
|
|
|
trace_cachefiles_read(object, file_inode(file), ki->iocb.ki_pos, len - skipped);
|
|
old_nofs = memalloc_nofs_save();
|
|
ret = cachefiles_inject_read_error();
|
|
if (ret == 0)
|
|
ret = vfs_iocb_iter_read(file, &ki->iocb, iter);
|
|
memalloc_nofs_restore(old_nofs);
|
|
switch (ret) {
|
|
case -EIOCBQUEUED:
|
|
goto in_progress;
|
|
|
|
case -ERESTARTSYS:
|
|
case -ERESTARTNOINTR:
|
|
case -ERESTARTNOHAND:
|
|
case -ERESTART_RESTARTBLOCK:
|
|
/* There's no easy way to restart the syscall since other AIO's
|
|
* may be already running. Just fail this IO with EINTR.
|
|
*/
|
|
ret = -EINTR;
|
|
fallthrough;
|
|
default:
|
|
ki->was_async = false;
|
|
cachefiles_read_complete(&ki->iocb, ret);
|
|
if (ret > 0)
|
|
ret = 0;
|
|
break;
|
|
}
|
|
|
|
in_progress:
|
|
cachefiles_put_kiocb(ki);
|
|
_leave(" = %zd", ret);
|
|
return ret;
|
|
|
|
presubmission_error:
|
|
if (term_func)
|
|
term_func(term_func_priv, ret < 0 ? ret : skipped, false);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Query the occupancy of the cache in a region, returning where the next chunk
|
|
* of data starts and how long it is.
|
|
*/
|
|
static int cachefiles_query_occupancy(struct netfs_cache_resources *cres,
|
|
loff_t start, size_t len, size_t granularity,
|
|
loff_t *_data_start, size_t *_data_len)
|
|
{
|
|
struct cachefiles_object *object;
|
|
struct file *file;
|
|
loff_t off, off2;
|
|
|
|
*_data_start = -1;
|
|
*_data_len = 0;
|
|
|
|
if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
|
|
return -ENOBUFS;
|
|
|
|
object = cachefiles_cres_object(cres);
|
|
file = cachefiles_cres_file(cres);
|
|
granularity = max_t(size_t, object->volume->cache->bsize, granularity);
|
|
|
|
_enter("%pD,%li,%llx,%zx/%llx",
|
|
file, file_inode(file)->i_ino, start, len,
|
|
i_size_read(file_inode(file)));
|
|
|
|
off = cachefiles_inject_read_error();
|
|
if (off == 0)
|
|
off = vfs_llseek(file, start, SEEK_DATA);
|
|
if (off == -ENXIO)
|
|
return -ENODATA; /* Beyond EOF */
|
|
if (off < 0 && off >= (loff_t)-MAX_ERRNO)
|
|
return -ENOBUFS; /* Error. */
|
|
if (round_up(off, granularity) >= start + len)
|
|
return -ENODATA; /* No data in range */
|
|
|
|
off2 = cachefiles_inject_read_error();
|
|
if (off2 == 0)
|
|
off2 = vfs_llseek(file, off, SEEK_HOLE);
|
|
if (off2 == -ENXIO)
|
|
return -ENODATA; /* Beyond EOF */
|
|
if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO)
|
|
return -ENOBUFS; /* Error. */
|
|
|
|
/* Round away partial blocks */
|
|
off = round_up(off, granularity);
|
|
off2 = round_down(off2, granularity);
|
|
if (off2 <= off)
|
|
return -ENODATA;
|
|
|
|
*_data_start = off;
|
|
if (off2 > start + len)
|
|
*_data_len = len;
|
|
else
|
|
*_data_len = off2 - off;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Handle completion of a write to the cache.
|
|
*/
|
|
static void cachefiles_write_complete(struct kiocb *iocb, long ret)
|
|
{
|
|
struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
|
|
struct cachefiles_object *object = ki->object;
|
|
struct inode *inode = file_inode(ki->iocb.ki_filp);
|
|
|
|
_enter("%ld", ret);
|
|
|
|
if (ki->was_async)
|
|
kiocb_end_write(iocb);
|
|
|
|
if (ret < 0)
|
|
trace_cachefiles_io_error(object, inode, ret,
|
|
cachefiles_trace_write_error);
|
|
|
|
atomic_long_sub(ki->b_writing, &object->volume->cache->b_writing);
|
|
set_bit(FSCACHE_COOKIE_HAVE_DATA, &object->cookie->flags);
|
|
if (ki->term_func)
|
|
ki->term_func(ki->term_func_priv, ret, ki->was_async);
|
|
cachefiles_put_kiocb(ki);
|
|
}
|
|
|
|
/*
|
|
* Initiate a write to the cache.
|
|
*/
|
|
int __cachefiles_write(struct cachefiles_object *object,
|
|
struct file *file,
|
|
loff_t start_pos,
|
|
struct iov_iter *iter,
|
|
netfs_io_terminated_t term_func,
|
|
void *term_func_priv)
|
|
{
|
|
struct cachefiles_cache *cache;
|
|
struct cachefiles_kiocb *ki;
|
|
unsigned int old_nofs;
|
|
ssize_t ret;
|
|
size_t len = iov_iter_count(iter);
|
|
|
|
fscache_count_write();
|
|
cache = object->volume->cache;
|
|
|
|
_enter("%pD,%li,%llx,%zx/%llx",
|
|
file, file_inode(file)->i_ino, start_pos, len,
|
|
i_size_read(file_inode(file)));
|
|
|
|
ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
|
|
if (!ki) {
|
|
if (term_func)
|
|
term_func(term_func_priv, -ENOMEM, false);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
refcount_set(&ki->ki_refcnt, 2);
|
|
ki->iocb.ki_filp = file;
|
|
ki->iocb.ki_pos = start_pos;
|
|
ki->iocb.ki_flags = IOCB_DIRECT | IOCB_WRITE;
|
|
ki->iocb.ki_ioprio = get_current_ioprio();
|
|
ki->object = object;
|
|
ki->start = start_pos;
|
|
ki->len = len;
|
|
ki->term_func = term_func;
|
|
ki->term_func_priv = term_func_priv;
|
|
ki->was_async = true;
|
|
ki->b_writing = (len + (1 << cache->bshift) - 1) >> cache->bshift;
|
|
|
|
if (ki->term_func)
|
|
ki->iocb.ki_complete = cachefiles_write_complete;
|
|
atomic_long_add(ki->b_writing, &cache->b_writing);
|
|
|
|
get_file(ki->iocb.ki_filp);
|
|
cachefiles_grab_object(object, cachefiles_obj_get_ioreq);
|
|
|
|
trace_cachefiles_write(object, file_inode(file), ki->iocb.ki_pos, len);
|
|
old_nofs = memalloc_nofs_save();
|
|
ret = cachefiles_inject_write_error();
|
|
if (ret == 0)
|
|
ret = vfs_iocb_iter_write(file, &ki->iocb, iter);
|
|
memalloc_nofs_restore(old_nofs);
|
|
switch (ret) {
|
|
case -EIOCBQUEUED:
|
|
goto in_progress;
|
|
|
|
case -ERESTARTSYS:
|
|
case -ERESTARTNOINTR:
|
|
case -ERESTARTNOHAND:
|
|
case -ERESTART_RESTARTBLOCK:
|
|
/* There's no easy way to restart the syscall since other AIO's
|
|
* may be already running. Just fail this IO with EINTR.
|
|
*/
|
|
ret = -EINTR;
|
|
fallthrough;
|
|
default:
|
|
ki->was_async = false;
|
|
cachefiles_write_complete(&ki->iocb, ret);
|
|
if (ret > 0)
|
|
ret = 0;
|
|
break;
|
|
}
|
|
|
|
in_progress:
|
|
cachefiles_put_kiocb(ki);
|
|
_leave(" = %zd", ret);
|
|
return ret;
|
|
}
|
|
|
|
static int cachefiles_write(struct netfs_cache_resources *cres,
|
|
loff_t start_pos,
|
|
struct iov_iter *iter,
|
|
netfs_io_terminated_t term_func,
|
|
void *term_func_priv)
|
|
{
|
|
if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) {
|
|
if (term_func)
|
|
term_func(term_func_priv, -ENOBUFS, false);
|
|
return -ENOBUFS;
|
|
}
|
|
|
|
return __cachefiles_write(cachefiles_cres_object(cres),
|
|
cachefiles_cres_file(cres),
|
|
start_pos, iter,
|
|
term_func, term_func_priv);
|
|
}
|
|
|
|
static inline enum netfs_io_source
|
|
cachefiles_do_prepare_read(struct netfs_cache_resources *cres,
|
|
loff_t start, size_t *_len, loff_t i_size,
|
|
unsigned long *_flags, ino_t netfs_ino)
|
|
{
|
|
enum cachefiles_prepare_read_trace why;
|
|
struct cachefiles_object *object = NULL;
|
|
struct cachefiles_cache *cache;
|
|
struct fscache_cookie *cookie = fscache_cres_cookie(cres);
|
|
const struct cred *saved_cred;
|
|
struct file *file = cachefiles_cres_file(cres);
|
|
enum netfs_io_source ret = NETFS_DOWNLOAD_FROM_SERVER;
|
|
size_t len = *_len;
|
|
loff_t off, to;
|
|
ino_t ino = file ? file_inode(file)->i_ino : 0;
|
|
int rc;
|
|
|
|
_enter("%zx @%llx/%llx", len, start, i_size);
|
|
|
|
if (start >= i_size) {
|
|
ret = NETFS_FILL_WITH_ZEROES;
|
|
why = cachefiles_trace_read_after_eof;
|
|
goto out_no_object;
|
|
}
|
|
|
|
if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) {
|
|
__set_bit(NETFS_SREQ_COPY_TO_CACHE, _flags);
|
|
why = cachefiles_trace_read_no_data;
|
|
if (!test_bit(NETFS_SREQ_ONDEMAND, _flags))
|
|
goto out_no_object;
|
|
}
|
|
|
|
/* The object and the file may be being created in the background. */
|
|
if (!file) {
|
|
why = cachefiles_trace_read_no_file;
|
|
if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
|
|
goto out_no_object;
|
|
file = cachefiles_cres_file(cres);
|
|
if (!file)
|
|
goto out_no_object;
|
|
ino = file_inode(file)->i_ino;
|
|
}
|
|
|
|
object = cachefiles_cres_object(cres);
|
|
cache = object->volume->cache;
|
|
cachefiles_begin_secure(cache, &saved_cred);
|
|
retry:
|
|
off = cachefiles_inject_read_error();
|
|
if (off == 0)
|
|
off = vfs_llseek(file, start, SEEK_DATA);
|
|
if (off < 0 && off >= (loff_t)-MAX_ERRNO) {
|
|
if (off == (loff_t)-ENXIO) {
|
|
why = cachefiles_trace_read_seek_nxio;
|
|
goto download_and_store;
|
|
}
|
|
trace_cachefiles_io_error(object, file_inode(file), off,
|
|
cachefiles_trace_seek_error);
|
|
why = cachefiles_trace_read_seek_error;
|
|
goto out;
|
|
}
|
|
|
|
if (off >= start + len) {
|
|
why = cachefiles_trace_read_found_hole;
|
|
goto download_and_store;
|
|
}
|
|
|
|
if (off > start) {
|
|
off = round_up(off, cache->bsize);
|
|
len = off - start;
|
|
*_len = len;
|
|
why = cachefiles_trace_read_found_part;
|
|
goto download_and_store;
|
|
}
|
|
|
|
to = cachefiles_inject_read_error();
|
|
if (to == 0)
|
|
to = vfs_llseek(file, start, SEEK_HOLE);
|
|
if (to < 0 && to >= (loff_t)-MAX_ERRNO) {
|
|
trace_cachefiles_io_error(object, file_inode(file), to,
|
|
cachefiles_trace_seek_error);
|
|
why = cachefiles_trace_read_seek_error;
|
|
goto out;
|
|
}
|
|
|
|
if (to < start + len) {
|
|
if (start + len >= i_size)
|
|
to = round_up(to, cache->bsize);
|
|
else
|
|
to = round_down(to, cache->bsize);
|
|
len = to - start;
|
|
*_len = len;
|
|
}
|
|
|
|
why = cachefiles_trace_read_have_data;
|
|
ret = NETFS_READ_FROM_CACHE;
|
|
goto out;
|
|
|
|
download_and_store:
|
|
__set_bit(NETFS_SREQ_COPY_TO_CACHE, _flags);
|
|
if (test_bit(NETFS_SREQ_ONDEMAND, _flags)) {
|
|
rc = cachefiles_ondemand_read(object, start, len);
|
|
if (!rc) {
|
|
__clear_bit(NETFS_SREQ_ONDEMAND, _flags);
|
|
goto retry;
|
|
}
|
|
ret = NETFS_INVALID_READ;
|
|
}
|
|
out:
|
|
cachefiles_end_secure(cache, saved_cred);
|
|
out_no_object:
|
|
trace_cachefiles_prep_read(object, start, len, *_flags, ret, why, ino, netfs_ino);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Prepare a read operation, shortening it to a cached/uncached
|
|
* boundary as appropriate.
|
|
*/
|
|
static enum netfs_io_source cachefiles_prepare_read(struct netfs_io_subrequest *subreq,
|
|
unsigned long long i_size)
|
|
{
|
|
return cachefiles_do_prepare_read(&subreq->rreq->cache_resources,
|
|
subreq->start, &subreq->len, i_size,
|
|
&subreq->flags, subreq->rreq->inode->i_ino);
|
|
}
|
|
|
|
/*
|
|
* Prepare an on-demand read operation, shortening it to a cached/uncached
|
|
* boundary as appropriate.
|
|
*/
|
|
static enum netfs_io_source
|
|
cachefiles_prepare_ondemand_read(struct netfs_cache_resources *cres,
|
|
loff_t start, size_t *_len, loff_t i_size,
|
|
unsigned long *_flags, ino_t ino)
|
|
{
|
|
return cachefiles_do_prepare_read(cres, start, _len, i_size, _flags, ino);
|
|
}
|
|
|
|
/*
|
|
* Prepare for a write to occur.
|
|
*/
|
|
int __cachefiles_prepare_write(struct cachefiles_object *object,
|
|
struct file *file,
|
|
loff_t *_start, size_t *_len, size_t upper_len,
|
|
bool no_space_allocated_yet)
|
|
{
|
|
struct cachefiles_cache *cache = object->volume->cache;
|
|
loff_t start = *_start, pos;
|
|
size_t len = *_len;
|
|
int ret;
|
|
|
|
/* Round to DIO size */
|
|
start = round_down(*_start, PAGE_SIZE);
|
|
if (start != *_start || *_len > upper_len) {
|
|
/* Probably asked to cache a streaming write written into the
|
|
* pagecache when the cookie was temporarily out of service to
|
|
* culling.
|
|
*/
|
|
fscache_count_dio_misfit();
|
|
return -ENOBUFS;
|
|
}
|
|
|
|
*_len = round_up(len, PAGE_SIZE);
|
|
|
|
/* We need to work out whether there's sufficient disk space to perform
|
|
* the write - but we can skip that check if we have space already
|
|
* allocated.
|
|
*/
|
|
if (no_space_allocated_yet)
|
|
goto check_space;
|
|
|
|
pos = cachefiles_inject_read_error();
|
|
if (pos == 0)
|
|
pos = vfs_llseek(file, start, SEEK_DATA);
|
|
if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
|
|
if (pos == -ENXIO)
|
|
goto check_space; /* Unallocated tail */
|
|
trace_cachefiles_io_error(object, file_inode(file), pos,
|
|
cachefiles_trace_seek_error);
|
|
return pos;
|
|
}
|
|
if ((u64)pos >= (u64)start + *_len)
|
|
goto check_space; /* Unallocated region */
|
|
|
|
/* We have a block that's at least partially filled - if we're low on
|
|
* space, we need to see if it's fully allocated. If it's not, we may
|
|
* want to cull it.
|
|
*/
|
|
if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE,
|
|
cachefiles_has_space_check) == 0)
|
|
return 0; /* Enough space to simply overwrite the whole block */
|
|
|
|
pos = cachefiles_inject_read_error();
|
|
if (pos == 0)
|
|
pos = vfs_llseek(file, start, SEEK_HOLE);
|
|
if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
|
|
trace_cachefiles_io_error(object, file_inode(file), pos,
|
|
cachefiles_trace_seek_error);
|
|
return pos;
|
|
}
|
|
if ((u64)pos >= (u64)start + *_len)
|
|
return 0; /* Fully allocated */
|
|
|
|
/* Partially allocated, but insufficient space: cull. */
|
|
fscache_count_no_write_space();
|
|
ret = cachefiles_inject_remove_error();
|
|
if (ret == 0)
|
|
ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
|
|
start, *_len);
|
|
if (ret < 0) {
|
|
trace_cachefiles_io_error(object, file_inode(file), ret,
|
|
cachefiles_trace_fallocate_error);
|
|
cachefiles_io_error_obj(object,
|
|
"CacheFiles: fallocate failed (%d)\n", ret);
|
|
ret = -EIO;
|
|
}
|
|
|
|
return ret;
|
|
|
|
check_space:
|
|
return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE,
|
|
cachefiles_has_space_for_write);
|
|
}
|
|
|
|
static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
|
|
loff_t *_start, size_t *_len, size_t upper_len,
|
|
loff_t i_size, bool no_space_allocated_yet)
|
|
{
|
|
struct cachefiles_object *object = cachefiles_cres_object(cres);
|
|
struct cachefiles_cache *cache = object->volume->cache;
|
|
const struct cred *saved_cred;
|
|
int ret;
|
|
|
|
if (!cachefiles_cres_file(cres)) {
|
|
if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE))
|
|
return -ENOBUFS;
|
|
if (!cachefiles_cres_file(cres))
|
|
return -ENOBUFS;
|
|
}
|
|
|
|
cachefiles_begin_secure(cache, &saved_cred);
|
|
ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres),
|
|
_start, _len, upper_len,
|
|
no_space_allocated_yet);
|
|
cachefiles_end_secure(cache, saved_cred);
|
|
return ret;
|
|
}
|
|
|
|
static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq)
|
|
{
|
|
struct netfs_io_request *wreq = subreq->rreq;
|
|
struct netfs_cache_resources *cres = &wreq->cache_resources;
|
|
struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
|
|
|
|
_enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start);
|
|
|
|
stream->sreq_max_len = MAX_RW_COUNT;
|
|
stream->sreq_max_segs = BIO_MAX_VECS;
|
|
|
|
if (!cachefiles_cres_file(cres)) {
|
|
if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE))
|
|
return netfs_prepare_write_failed(subreq);
|
|
if (!cachefiles_cres_file(cres))
|
|
return netfs_prepare_write_failed(subreq);
|
|
}
|
|
}
|
|
|
|
static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
|
|
{
|
|
struct netfs_io_request *wreq = subreq->rreq;
|
|
struct netfs_cache_resources *cres = &wreq->cache_resources;
|
|
struct cachefiles_object *object = cachefiles_cres_object(cres);
|
|
struct cachefiles_cache *cache = object->volume->cache;
|
|
struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
|
|
const struct cred *saved_cred;
|
|
size_t off, pre, post, len = subreq->len;
|
|
loff_t start = subreq->start;
|
|
int ret;
|
|
|
|
_enter("W=%x[%x] %llx-%llx",
|
|
wreq->debug_id, subreq->debug_index, start, start + len - 1);
|
|
|
|
/* We need to start on the cache granularity boundary */
|
|
off = start & (CACHEFILES_DIO_BLOCK_SIZE - 1);
|
|
if (off) {
|
|
pre = CACHEFILES_DIO_BLOCK_SIZE - off;
|
|
if (pre >= len) {
|
|
fscache_count_dio_misfit();
|
|
netfs_write_subrequest_terminated(subreq, len, false);
|
|
return;
|
|
}
|
|
subreq->transferred += pre;
|
|
start += pre;
|
|
len -= pre;
|
|
iov_iter_advance(&subreq->io_iter, pre);
|
|
}
|
|
|
|
/* We also need to end on the cache granularity boundary */
|
|
if (start + len == wreq->i_size) {
|
|
size_t part = len % CACHEFILES_DIO_BLOCK_SIZE;
|
|
size_t need = CACHEFILES_DIO_BLOCK_SIZE - part;
|
|
|
|
if (part && stream->submit_extendable_to >= need) {
|
|
len += need;
|
|
subreq->len += need;
|
|
subreq->io_iter.count += need;
|
|
}
|
|
}
|
|
|
|
post = len & (CACHEFILES_DIO_BLOCK_SIZE - 1);
|
|
if (post) {
|
|
len -= post;
|
|
if (len == 0) {
|
|
fscache_count_dio_misfit();
|
|
netfs_write_subrequest_terminated(subreq, post, false);
|
|
return;
|
|
}
|
|
iov_iter_truncate(&subreq->io_iter, len);
|
|
}
|
|
|
|
cachefiles_begin_secure(cache, &saved_cred);
|
|
ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres),
|
|
&start, &len, len, true);
|
|
cachefiles_end_secure(cache, saved_cred);
|
|
if (ret < 0) {
|
|
netfs_write_subrequest_terminated(subreq, ret, false);
|
|
return;
|
|
}
|
|
|
|
cachefiles_write(&subreq->rreq->cache_resources,
|
|
subreq->start, &subreq->io_iter,
|
|
netfs_write_subrequest_terminated, subreq);
|
|
}
|
|
|
|
/*
|
|
* Clean up an operation.
|
|
*/
|
|
static void cachefiles_end_operation(struct netfs_cache_resources *cres)
|
|
{
|
|
struct file *file = cachefiles_cres_file(cres);
|
|
|
|
if (file)
|
|
fput(file);
|
|
fscache_end_cookie_access(fscache_cres_cookie(cres), fscache_access_io_end);
|
|
}
|
|
|
|
static const struct netfs_cache_ops cachefiles_netfs_cache_ops = {
|
|
.end_operation = cachefiles_end_operation,
|
|
.read = cachefiles_read,
|
|
.write = cachefiles_write,
|
|
.issue_write = cachefiles_issue_write,
|
|
.prepare_read = cachefiles_prepare_read,
|
|
.prepare_write = cachefiles_prepare_write,
|
|
.prepare_write_subreq = cachefiles_prepare_write_subreq,
|
|
.prepare_ondemand_read = cachefiles_prepare_ondemand_read,
|
|
.query_occupancy = cachefiles_query_occupancy,
|
|
};
|
|
|
|
/*
|
|
* Open the cache file when beginning a cache operation.
|
|
*/
|
|
bool cachefiles_begin_operation(struct netfs_cache_resources *cres,
|
|
enum fscache_want_state want_state)
|
|
{
|
|
struct cachefiles_object *object = cachefiles_cres_object(cres);
|
|
|
|
if (!cachefiles_cres_file(cres)) {
|
|
cres->ops = &cachefiles_netfs_cache_ops;
|
|
if (object->file) {
|
|
spin_lock(&object->lock);
|
|
if (!cres->cache_priv2 && object->file)
|
|
cres->cache_priv2 = get_file(object->file);
|
|
spin_unlock(&object->lock);
|
|
}
|
|
}
|
|
|
|
if (!cachefiles_cres_file(cres) && want_state != FSCACHE_WANT_PARAMS) {
|
|
pr_err("failed to get cres->file\n");
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|