mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-03 17:40:04 +00:00
![David Howells](/assets/img/avatar_default.png)
Make afs_write_begin() wait for a page that's marked PG_writeback because: (1) We need to avoid interference with the data being stored so that the data on the server ends up in a defined state. (2) page->private is used to track the window of dirty data within a page, but it's also used by the storage code to track what's being written, being cleared by the completion notification. Ownership can't be relinquished by the storage code until completion because it a store fails, the data must be remarked dirty. Tracing shows something like the following (edited): x86_64-linux-gn-15940 [1] afs_page_dirty: vn=ffff8800bef33800 9c75 begin 0-125 kworker/u8:3-114 [2] afs_page_dirty: vn=ffff8800bef33800 9c75 store+ 0-125 x86_64-linux-gn-15940 [1] afs_page_dirty: vn=ffff8800bef33800 9c75 begin 0-2052 kworker/u8:3-114 [2] afs_page_dirty: vn=ffff8800bef33800 9c75 clear 0-2052 kworker/u8:3-114 [2] afs_page_dirty: vn=ffff8800bef33800 9c75 store 0-0 kworker/u8:3-114 [2] afs_page_dirty: vn=ffff8800bef33800 9c75 WARN 0-0 The clear (completion) corresponding to the store+ (store continuation from a previous page) happens between the second begin (afs_write_begin) and the store corresponding to that. This results in the second store not seeing any data to write back, leading to the following warning: WARNING: CPU: 2 PID: 114 at ../fs/afs/write.c:403 afs_write_back_from_locked_page+0x19d/0x76c [kafs] Modules linked in: kafs(E) CPU: 2 PID: 114 Comm: kworker/u8:3 Tainted: G E 4.14.0-fscache+ #242 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Workqueue: writeback wb_workfn (flush-afs-2) task: ffff8800cad72600 task.stack: ffff8800cad44000 RIP: 0010:afs_write_back_from_locked_page+0x19d/0x76c [kafs] RSP: 0018:ffff8800cad47aa0 EFLAGS: 00010246 RAX: 0000000000000001 RBX: ffff8800bef33a20 RCX: 0000000000000000 RDX: 000000000000000f RSI: ffffffff81c5d0e0 RDI: ffff8800cad72e78 RBP: ffff8800d31ea1e8 R08: ffff8800c1358000 R09: ffff8800ca00e400 R10: ffff8800cad47a38 R11: ffff8800c5d9e400 R12: 0000000000000000 R13: ffffea0002d9df00 R14: ffffffffa0023c1c R15: 0000000000007fdf FS: 0000000000000000(0000) GS:ffff8800ca700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f85ac6c4000 CR3: 0000000001c10001 CR4: 00000000001606e0 Call Trace: ? clear_page_dirty_for_io+0x23a/0x267 afs_writepages_region+0x1be/0x286 [kafs] afs_writepages+0x60/0x127 [kafs] do_writepages+0x36/0x70 __writeback_single_inode+0x12f/0x635 writeback_sb_inodes+0x2cc/0x452 __writeback_inodes_wb+0x68/0x9f wb_writeback+0x208/0x470 ? wb_workfn+0x22b/0x565 wb_workfn+0x22b/0x565 ? worker_thread+0x230/0x2ac process_one_work+0x2cc/0x517 ? worker_thread+0x230/0x2ac worker_thread+0x1d4/0x2ac ? rescuer_thread+0x29b/0x29b kthread+0x15d/0x165 ? kthread_create_on_node+0x3f/0x3f ? call_usermodehelper_exec_async+0x118/0x11f ret_from_fork+0x24/0x30 Signed-off-by: David Howells <dhowells@redhat.com>
862 lines
20 KiB
C
862 lines
20 KiB
C
/* handling of writes to regular files and writing back to the server
|
|
*
|
|
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/backing-dev.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/pagevec.h>
|
|
#include "internal.h"
|
|
|
|
/*
|
|
* mark a page as having been made dirty and thus needing writeback
|
|
*/
|
|
int afs_set_page_dirty(struct page *page)
|
|
{
|
|
_enter("");
|
|
return __set_page_dirty_nobuffers(page);
|
|
}
|
|
|
|
/*
|
|
* partly or wholly fill a page that's under preparation for writing
|
|
*/
|
|
static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
|
|
loff_t pos, unsigned int len, struct page *page)
|
|
{
|
|
struct afs_read *req;
|
|
int ret;
|
|
|
|
_enter(",,%llu", (unsigned long long)pos);
|
|
|
|
req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *),
|
|
GFP_KERNEL);
|
|
if (!req)
|
|
return -ENOMEM;
|
|
|
|
atomic_set(&req->usage, 1);
|
|
req->pos = pos;
|
|
req->len = len;
|
|
req->nr_pages = 1;
|
|
req->pages[0] = page;
|
|
get_page(page);
|
|
|
|
ret = afs_fetch_data(vnode, key, req);
|
|
afs_put_read(req);
|
|
if (ret < 0) {
|
|
if (ret == -ENOENT) {
|
|
_debug("got NOENT from server"
|
|
" - marking file deleted and stale");
|
|
set_bit(AFS_VNODE_DELETED, &vnode->flags);
|
|
ret = -ESTALE;
|
|
}
|
|
}
|
|
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* prepare to perform part of a write to a page
|
|
*/
|
|
int afs_write_begin(struct file *file, struct address_space *mapping,
|
|
loff_t pos, unsigned len, unsigned flags,
|
|
struct page **pagep, void **fsdata)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
|
|
struct page *page;
|
|
struct key *key = afs_file_key(file);
|
|
unsigned long priv;
|
|
unsigned f, from = pos & (PAGE_SIZE - 1);
|
|
unsigned t, to = from + len;
|
|
pgoff_t index = pos >> PAGE_SHIFT;
|
|
int ret;
|
|
|
|
_enter("{%x:%u},{%lx},%u,%u",
|
|
vnode->fid.vid, vnode->fid.vnode, index, from, to);
|
|
|
|
/* We want to store information about how much of a page is altered in
|
|
* page->private.
|
|
*/
|
|
BUILD_BUG_ON(PAGE_SIZE > 32768 && sizeof(page->private) < 8);
|
|
|
|
page = grab_cache_page_write_begin(mapping, index, flags);
|
|
if (!page)
|
|
return -ENOMEM;
|
|
|
|
if (!PageUptodate(page) && len != PAGE_SIZE) {
|
|
ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page);
|
|
if (ret < 0) {
|
|
unlock_page(page);
|
|
put_page(page);
|
|
_leave(" = %d [prep]", ret);
|
|
return ret;
|
|
}
|
|
SetPageUptodate(page);
|
|
}
|
|
|
|
/* page won't leak in error case: it eventually gets cleaned off LRU */
|
|
*pagep = page;
|
|
|
|
try_again:
|
|
/* See if this page is already partially written in a way that we can
|
|
* merge the new write with.
|
|
*/
|
|
t = f = 0;
|
|
if (PagePrivate(page)) {
|
|
priv = page_private(page);
|
|
f = priv & AFS_PRIV_MAX;
|
|
t = priv >> AFS_PRIV_SHIFT;
|
|
ASSERTCMP(f, <=, t);
|
|
}
|
|
|
|
if (f != t) {
|
|
if (PageWriteback(page)) {
|
|
trace_afs_page_dirty(vnode, tracepoint_string("alrdy"),
|
|
page->index, priv);
|
|
goto flush_conflicting_write;
|
|
}
|
|
if (to < f || from > t)
|
|
goto flush_conflicting_write;
|
|
if (from < f)
|
|
f = from;
|
|
if (to > t)
|
|
t = to;
|
|
} else {
|
|
f = from;
|
|
t = to;
|
|
}
|
|
|
|
priv = (unsigned long)t << AFS_PRIV_SHIFT;
|
|
priv |= f;
|
|
trace_afs_page_dirty(vnode, tracepoint_string("begin"),
|
|
page->index, priv);
|
|
SetPagePrivate(page);
|
|
set_page_private(page, priv);
|
|
_leave(" = 0");
|
|
return 0;
|
|
|
|
/* The previous write and this write aren't adjacent or overlapping, so
|
|
* flush the page out.
|
|
*/
|
|
flush_conflicting_write:
|
|
_debug("flush conflict");
|
|
ret = write_one_page(page);
|
|
if (ret < 0) {
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
ret = lock_page_killable(page);
|
|
if (ret < 0) {
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
goto try_again;
|
|
}
|
|
|
|
/*
|
|
* finalise part of a write to a page
|
|
*/
|
|
int afs_write_end(struct file *file, struct address_space *mapping,
|
|
loff_t pos, unsigned len, unsigned copied,
|
|
struct page *page, void *fsdata)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
|
|
struct key *key = afs_file_key(file);
|
|
loff_t i_size, maybe_i_size;
|
|
int ret;
|
|
|
|
_enter("{%x:%u},{%lx}",
|
|
vnode->fid.vid, vnode->fid.vnode, page->index);
|
|
|
|
maybe_i_size = pos + copied;
|
|
|
|
i_size = i_size_read(&vnode->vfs_inode);
|
|
if (maybe_i_size > i_size) {
|
|
spin_lock(&vnode->wb_lock);
|
|
i_size = i_size_read(&vnode->vfs_inode);
|
|
if (maybe_i_size > i_size)
|
|
i_size_write(&vnode->vfs_inode, maybe_i_size);
|
|
spin_unlock(&vnode->wb_lock);
|
|
}
|
|
|
|
if (!PageUptodate(page)) {
|
|
if (copied < len) {
|
|
/* Try and load any missing data from the server. The
|
|
* unmarshalling routine will take care of clearing any
|
|
* bits that are beyond the EOF.
|
|
*/
|
|
ret = afs_fill_page(vnode, key, pos + copied,
|
|
len - copied, page);
|
|
if (ret < 0)
|
|
return ret;
|
|
}
|
|
SetPageUptodate(page);
|
|
}
|
|
|
|
set_page_dirty(page);
|
|
if (PageDirty(page))
|
|
_debug("dirtied");
|
|
unlock_page(page);
|
|
put_page(page);
|
|
|
|
return copied;
|
|
}
|
|
|
|
/*
|
|
* kill all the pages in the given range
|
|
*/
|
|
static void afs_kill_pages(struct address_space *mapping,
|
|
pgoff_t first, pgoff_t last)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
|
|
struct pagevec pv;
|
|
unsigned count, loop;
|
|
|
|
_enter("{%x:%u},%lx-%lx",
|
|
vnode->fid.vid, vnode->fid.vnode, first, last);
|
|
|
|
pagevec_init(&pv);
|
|
|
|
do {
|
|
_debug("kill %lx-%lx", first, last);
|
|
|
|
count = last - first + 1;
|
|
if (count > PAGEVEC_SIZE)
|
|
count = PAGEVEC_SIZE;
|
|
pv.nr = find_get_pages_contig(mapping, first, count, pv.pages);
|
|
ASSERTCMP(pv.nr, ==, count);
|
|
|
|
for (loop = 0; loop < count; loop++) {
|
|
struct page *page = pv.pages[loop];
|
|
ClearPageUptodate(page);
|
|
SetPageError(page);
|
|
end_page_writeback(page);
|
|
if (page->index >= first)
|
|
first = page->index + 1;
|
|
lock_page(page);
|
|
generic_error_remove_page(mapping, page);
|
|
}
|
|
|
|
__pagevec_release(&pv);
|
|
} while (first <= last);
|
|
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* Redirty all the pages in a given range.
|
|
*/
|
|
static void afs_redirty_pages(struct writeback_control *wbc,
|
|
struct address_space *mapping,
|
|
pgoff_t first, pgoff_t last)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
|
|
struct pagevec pv;
|
|
unsigned count, loop;
|
|
|
|
_enter("{%x:%u},%lx-%lx",
|
|
vnode->fid.vid, vnode->fid.vnode, first, last);
|
|
|
|
pagevec_init(&pv);
|
|
|
|
do {
|
|
_debug("redirty %lx-%lx", first, last);
|
|
|
|
count = last - first + 1;
|
|
if (count > PAGEVEC_SIZE)
|
|
count = PAGEVEC_SIZE;
|
|
pv.nr = find_get_pages_contig(mapping, first, count, pv.pages);
|
|
ASSERTCMP(pv.nr, ==, count);
|
|
|
|
for (loop = 0; loop < count; loop++) {
|
|
struct page *page = pv.pages[loop];
|
|
|
|
redirty_page_for_writepage(wbc, page);
|
|
end_page_writeback(page);
|
|
if (page->index >= first)
|
|
first = page->index + 1;
|
|
}
|
|
|
|
__pagevec_release(&pv);
|
|
} while (first <= last);
|
|
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* write to a file
|
|
*/
|
|
static int afs_store_data(struct address_space *mapping,
|
|
pgoff_t first, pgoff_t last,
|
|
unsigned offset, unsigned to)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
|
|
struct afs_fs_cursor fc;
|
|
struct afs_wb_key *wbk = NULL;
|
|
struct list_head *p;
|
|
int ret = -ENOKEY, ret2;
|
|
|
|
_enter("%s{%x:%u.%u},%lx,%lx,%x,%x",
|
|
vnode->volume->name,
|
|
vnode->fid.vid,
|
|
vnode->fid.vnode,
|
|
vnode->fid.unique,
|
|
first, last, offset, to);
|
|
|
|
spin_lock(&vnode->wb_lock);
|
|
p = vnode->wb_keys.next;
|
|
|
|
/* Iterate through the list looking for a valid key to use. */
|
|
try_next_key:
|
|
while (p != &vnode->wb_keys) {
|
|
wbk = list_entry(p, struct afs_wb_key, vnode_link);
|
|
_debug("wbk %u", key_serial(wbk->key));
|
|
ret2 = key_validate(wbk->key);
|
|
if (ret2 == 0)
|
|
goto found_key;
|
|
if (ret == -ENOKEY)
|
|
ret = ret2;
|
|
p = p->next;
|
|
}
|
|
|
|
spin_unlock(&vnode->wb_lock);
|
|
afs_put_wb_key(wbk);
|
|
_leave(" = %d [no keys]", ret);
|
|
return ret;
|
|
|
|
found_key:
|
|
refcount_inc(&wbk->usage);
|
|
spin_unlock(&vnode->wb_lock);
|
|
|
|
_debug("USE WB KEY %u", key_serial(wbk->key));
|
|
|
|
ret = -ERESTARTSYS;
|
|
if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) {
|
|
while (afs_select_fileserver(&fc)) {
|
|
fc.cb_break = vnode->cb_break + vnode->cb_s_break;
|
|
afs_fs_store_data(&fc, mapping, first, last, offset, to);
|
|
}
|
|
|
|
afs_check_for_remote_deletion(&fc, fc.vnode);
|
|
afs_vnode_commit_status(&fc, vnode, fc.cb_break);
|
|
ret = afs_end_vnode_operation(&fc);
|
|
}
|
|
|
|
switch (ret) {
|
|
case -EACCES:
|
|
case -EPERM:
|
|
case -ENOKEY:
|
|
case -EKEYEXPIRED:
|
|
case -EKEYREJECTED:
|
|
case -EKEYREVOKED:
|
|
_debug("next");
|
|
spin_lock(&vnode->wb_lock);
|
|
p = wbk->vnode_link.next;
|
|
afs_put_wb_key(wbk);
|
|
goto try_next_key;
|
|
}
|
|
|
|
afs_put_wb_key(wbk);
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Synchronously write back the locked page and any subsequent non-locked dirty
|
|
* pages.
|
|
*/
|
|
static int afs_write_back_from_locked_page(struct address_space *mapping,
|
|
struct writeback_control *wbc,
|
|
struct page *primary_page,
|
|
pgoff_t final_page)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
|
|
struct page *pages[8], *page;
|
|
unsigned long count, priv;
|
|
unsigned n, offset, to, f, t;
|
|
pgoff_t start, first, last;
|
|
int loop, ret;
|
|
|
|
_enter(",%lx", primary_page->index);
|
|
|
|
count = 1;
|
|
if (test_set_page_writeback(primary_page))
|
|
BUG();
|
|
|
|
/* Find all consecutive lockable dirty pages that have contiguous
|
|
* written regions, stopping when we find a page that is not
|
|
* immediately lockable, is not dirty or is missing, or we reach the
|
|
* end of the range.
|
|
*/
|
|
start = primary_page->index;
|
|
priv = page_private(primary_page);
|
|
offset = priv & AFS_PRIV_MAX;
|
|
to = priv >> AFS_PRIV_SHIFT;
|
|
trace_afs_page_dirty(vnode, tracepoint_string("store"),
|
|
primary_page->index, priv);
|
|
|
|
WARN_ON(offset == to);
|
|
if (offset == to)
|
|
trace_afs_page_dirty(vnode, tracepoint_string("WARN"),
|
|
primary_page->index, priv);
|
|
|
|
if (start >= final_page || to < PAGE_SIZE)
|
|
goto no_more;
|
|
|
|
start++;
|
|
do {
|
|
_debug("more %lx [%lx]", start, count);
|
|
n = final_page - start + 1;
|
|
if (n > ARRAY_SIZE(pages))
|
|
n = ARRAY_SIZE(pages);
|
|
n = find_get_pages_contig(mapping, start, ARRAY_SIZE(pages), pages);
|
|
_debug("fgpc %u", n);
|
|
if (n == 0)
|
|
goto no_more;
|
|
if (pages[0]->index != start) {
|
|
do {
|
|
put_page(pages[--n]);
|
|
} while (n > 0);
|
|
goto no_more;
|
|
}
|
|
|
|
for (loop = 0; loop < n; loop++) {
|
|
if (to != PAGE_SIZE)
|
|
break;
|
|
page = pages[loop];
|
|
if (page->index > final_page)
|
|
break;
|
|
if (!trylock_page(page))
|
|
break;
|
|
if (!PageDirty(page) || PageWriteback(page)) {
|
|
unlock_page(page);
|
|
break;
|
|
}
|
|
|
|
priv = page_private(page);
|
|
f = priv & AFS_PRIV_MAX;
|
|
t = priv >> AFS_PRIV_SHIFT;
|
|
if (f != 0) {
|
|
unlock_page(page);
|
|
break;
|
|
}
|
|
to = t;
|
|
|
|
trace_afs_page_dirty(vnode, tracepoint_string("store+"),
|
|
page->index, priv);
|
|
|
|
if (!clear_page_dirty_for_io(page))
|
|
BUG();
|
|
if (test_set_page_writeback(page))
|
|
BUG();
|
|
unlock_page(page);
|
|
put_page(page);
|
|
}
|
|
count += loop;
|
|
if (loop < n) {
|
|
for (; loop < n; loop++)
|
|
put_page(pages[loop]);
|
|
goto no_more;
|
|
}
|
|
|
|
start += loop;
|
|
} while (start <= final_page && count < 65536);
|
|
|
|
no_more:
|
|
/* We now have a contiguous set of dirty pages, each with writeback
|
|
* set; the first page is still locked at this point, but all the rest
|
|
* have been unlocked.
|
|
*/
|
|
unlock_page(primary_page);
|
|
|
|
first = primary_page->index;
|
|
last = first + count - 1;
|
|
|
|
_debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
|
|
|
|
ret = afs_store_data(mapping, first, last, offset, to);
|
|
switch (ret) {
|
|
case 0:
|
|
ret = count;
|
|
break;
|
|
|
|
default:
|
|
pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
|
|
/* Fall through */
|
|
case -EACCES:
|
|
case -EPERM:
|
|
case -ENOKEY:
|
|
case -EKEYEXPIRED:
|
|
case -EKEYREJECTED:
|
|
case -EKEYREVOKED:
|
|
afs_redirty_pages(wbc, mapping, first, last);
|
|
mapping_set_error(mapping, ret);
|
|
break;
|
|
|
|
case -EDQUOT:
|
|
case -ENOSPC:
|
|
afs_redirty_pages(wbc, mapping, first, last);
|
|
mapping_set_error(mapping, -ENOSPC);
|
|
break;
|
|
|
|
case -EROFS:
|
|
case -EIO:
|
|
case -EREMOTEIO:
|
|
case -EFBIG:
|
|
case -ENOENT:
|
|
case -ENOMEDIUM:
|
|
case -ENXIO:
|
|
afs_kill_pages(mapping, first, last);
|
|
mapping_set_error(mapping, ret);
|
|
break;
|
|
}
|
|
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* write a page back to the server
|
|
* - the caller locked the page for us
|
|
*/
|
|
int afs_writepage(struct page *page, struct writeback_control *wbc)
|
|
{
|
|
int ret;
|
|
|
|
_enter("{%lx},", page->index);
|
|
|
|
ret = afs_write_back_from_locked_page(page->mapping, wbc, page,
|
|
wbc->range_end >> PAGE_SHIFT);
|
|
if (ret < 0) {
|
|
_leave(" = %d", ret);
|
|
return 0;
|
|
}
|
|
|
|
wbc->nr_to_write -= ret;
|
|
|
|
_leave(" = 0");
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* write a region of pages back to the server
|
|
*/
|
|
static int afs_writepages_region(struct address_space *mapping,
|
|
struct writeback_control *wbc,
|
|
pgoff_t index, pgoff_t end, pgoff_t *_next)
|
|
{
|
|
struct page *page;
|
|
int ret, n;
|
|
|
|
_enter(",,%lx,%lx,", index, end);
|
|
|
|
do {
|
|
n = find_get_pages_range_tag(mapping, &index, end,
|
|
PAGECACHE_TAG_DIRTY, 1, &page);
|
|
if (!n)
|
|
break;
|
|
|
|
_debug("wback %lx", page->index);
|
|
|
|
/* at this point we hold neither mapping->tree_lock nor lock on
|
|
* the page itself: the page may be truncated or invalidated
|
|
* (changing page->mapping to NULL), or even swizzled back from
|
|
* swapper_space to tmpfs file mapping
|
|
*/
|
|
ret = lock_page_killable(page);
|
|
if (ret < 0) {
|
|
put_page(page);
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
if (page->mapping != mapping || !PageDirty(page)) {
|
|
unlock_page(page);
|
|
put_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (PageWriteback(page)) {
|
|
unlock_page(page);
|
|
if (wbc->sync_mode != WB_SYNC_NONE)
|
|
wait_on_page_writeback(page);
|
|
put_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (!clear_page_dirty_for_io(page))
|
|
BUG();
|
|
ret = afs_write_back_from_locked_page(mapping, wbc, page, end);
|
|
put_page(page);
|
|
if (ret < 0) {
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
wbc->nr_to_write -= ret;
|
|
|
|
cond_resched();
|
|
} while (index < end && wbc->nr_to_write > 0);
|
|
|
|
*_next = index;
|
|
_leave(" = 0 [%lx]", *_next);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* write some of the pending data back to the server
|
|
*/
|
|
int afs_writepages(struct address_space *mapping,
|
|
struct writeback_control *wbc)
|
|
{
|
|
pgoff_t start, end, next;
|
|
int ret;
|
|
|
|
_enter("");
|
|
|
|
if (wbc->range_cyclic) {
|
|
start = mapping->writeback_index;
|
|
end = -1;
|
|
ret = afs_writepages_region(mapping, wbc, start, end, &next);
|
|
if (start > 0 && wbc->nr_to_write > 0 && ret == 0)
|
|
ret = afs_writepages_region(mapping, wbc, 0, start,
|
|
&next);
|
|
mapping->writeback_index = next;
|
|
} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
|
|
end = (pgoff_t)(LLONG_MAX >> PAGE_SHIFT);
|
|
ret = afs_writepages_region(mapping, wbc, 0, end, &next);
|
|
if (wbc->nr_to_write > 0)
|
|
mapping->writeback_index = next;
|
|
} else {
|
|
start = wbc->range_start >> PAGE_SHIFT;
|
|
end = wbc->range_end >> PAGE_SHIFT;
|
|
ret = afs_writepages_region(mapping, wbc, start, end, &next);
|
|
}
|
|
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* completion of write to server
|
|
*/
|
|
void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
|
|
{
|
|
struct pagevec pv;
|
|
unsigned long priv;
|
|
unsigned count, loop;
|
|
pgoff_t first = call->first, last = call->last;
|
|
|
|
_enter("{%x:%u},{%lx-%lx}",
|
|
vnode->fid.vid, vnode->fid.vnode, first, last);
|
|
|
|
pagevec_init(&pv);
|
|
|
|
do {
|
|
_debug("done %lx-%lx", first, last);
|
|
|
|
count = last - first + 1;
|
|
if (count > PAGEVEC_SIZE)
|
|
count = PAGEVEC_SIZE;
|
|
pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping,
|
|
first, count, pv.pages);
|
|
ASSERTCMP(pv.nr, ==, count);
|
|
|
|
for (loop = 0; loop < count; loop++) {
|
|
priv = page_private(pv.pages[loop]);
|
|
trace_afs_page_dirty(vnode, tracepoint_string("clear"),
|
|
pv.pages[loop]->index, priv);
|
|
set_page_private(pv.pages[loop], 0);
|
|
end_page_writeback(pv.pages[loop]);
|
|
}
|
|
first += count;
|
|
__pagevec_release(&pv);
|
|
} while (first <= last);
|
|
|
|
afs_prune_wb_keys(vnode);
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* write to an AFS file
|
|
*/
|
|
ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
|
|
{
|
|
struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
|
|
ssize_t result;
|
|
size_t count = iov_iter_count(from);
|
|
|
|
_enter("{%x.%u},{%zu},",
|
|
vnode->fid.vid, vnode->fid.vnode, count);
|
|
|
|
if (IS_SWAPFILE(&vnode->vfs_inode)) {
|
|
printk(KERN_INFO
|
|
"AFS: Attempt to write to active swap file!\n");
|
|
return -EBUSY;
|
|
}
|
|
|
|
if (!count)
|
|
return 0;
|
|
|
|
result = generic_file_write_iter(iocb, from);
|
|
|
|
_leave(" = %zd", result);
|
|
return result;
|
|
}
|
|
|
|
/*
|
|
* flush any dirty pages for this process, and check for write errors.
|
|
* - the return status from this call provides a reliable indication of
|
|
* whether any write errors occurred for this process.
|
|
*/
|
|
int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
struct afs_vnode *vnode = AFS_FS_I(inode);
|
|
|
|
_enter("{%x:%u},{n=%pD},%d",
|
|
vnode->fid.vid, vnode->fid.vnode, file,
|
|
datasync);
|
|
|
|
return file_write_and_wait_range(file, start, end);
|
|
}
|
|
|
|
/*
|
|
* Flush out all outstanding writes on a file opened for writing when it is
|
|
* closed.
|
|
*/
|
|
int afs_flush(struct file *file, fl_owner_t id)
|
|
{
|
|
_enter("");
|
|
|
|
if ((file->f_mode & FMODE_WRITE) == 0)
|
|
return 0;
|
|
|
|
return vfs_fsync(file, 0);
|
|
}
|
|
|
|
/*
|
|
* notification that a previously read-only page is about to become writable
|
|
* - if it returns an error, the caller will deliver a bus error signal
|
|
*/
|
|
int afs_page_mkwrite(struct vm_fault *vmf)
|
|
{
|
|
struct file *file = vmf->vma->vm_file;
|
|
struct inode *inode = file_inode(file);
|
|
struct afs_vnode *vnode = AFS_FS_I(inode);
|
|
unsigned long priv;
|
|
|
|
_enter("{{%x:%u}},{%lx}",
|
|
vnode->fid.vid, vnode->fid.vnode, vmf->page->index);
|
|
|
|
sb_start_pagefault(inode->i_sb);
|
|
|
|
/* Wait for the page to be written to the cache before we allow it to
|
|
* be modified. We then assume the entire page will need writing back.
|
|
*/
|
|
#ifdef CONFIG_AFS_FSCACHE
|
|
fscache_wait_on_page_write(vnode->cache, vmf->page);
|
|
#endif
|
|
|
|
if (PageWriteback(vmf->page) &&
|
|
wait_on_page_bit_killable(vmf->page, PG_writeback) < 0)
|
|
return VM_FAULT_RETRY;
|
|
|
|
if (lock_page_killable(vmf->page) < 0)
|
|
return VM_FAULT_RETRY;
|
|
|
|
/* We mustn't change page->private until writeback is complete as that
|
|
* details the portion of the page we need to write back and we might
|
|
* need to redirty the page if there's a problem.
|
|
*/
|
|
wait_on_page_writeback(vmf->page);
|
|
|
|
priv = (unsigned long)PAGE_SIZE << AFS_PRIV_SHIFT; /* To */
|
|
priv |= 0; /* From */
|
|
trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"),
|
|
vmf->page->index, priv);
|
|
SetPagePrivate(vmf->page);
|
|
set_page_private(vmf->page, priv);
|
|
|
|
sb_end_pagefault(inode->i_sb);
|
|
return VM_FAULT_LOCKED;
|
|
}
|
|
|
|
/*
|
|
* Prune the keys cached for writeback. The caller must hold vnode->wb_lock.
|
|
*/
|
|
void afs_prune_wb_keys(struct afs_vnode *vnode)
|
|
{
|
|
LIST_HEAD(graveyard);
|
|
struct afs_wb_key *wbk, *tmp;
|
|
|
|
/* Discard unused keys */
|
|
spin_lock(&vnode->wb_lock);
|
|
|
|
if (!mapping_tagged(&vnode->vfs_inode.i_data, PAGECACHE_TAG_WRITEBACK) &&
|
|
!mapping_tagged(&vnode->vfs_inode.i_data, PAGECACHE_TAG_DIRTY)) {
|
|
list_for_each_entry_safe(wbk, tmp, &vnode->wb_keys, vnode_link) {
|
|
if (refcount_read(&wbk->usage) == 1)
|
|
list_move(&wbk->vnode_link, &graveyard);
|
|
}
|
|
}
|
|
|
|
spin_unlock(&vnode->wb_lock);
|
|
|
|
while (!list_empty(&graveyard)) {
|
|
wbk = list_entry(graveyard.next, struct afs_wb_key, vnode_link);
|
|
list_del(&wbk->vnode_link);
|
|
afs_put_wb_key(wbk);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Clean up a page during invalidation.
|
|
*/
|
|
int afs_launder_page(struct page *page)
|
|
{
|
|
struct address_space *mapping = page->mapping;
|
|
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
|
|
unsigned long priv;
|
|
unsigned int f, t;
|
|
int ret = 0;
|
|
|
|
_enter("{%lx}", page->index);
|
|
|
|
priv = page_private(page);
|
|
if (clear_page_dirty_for_io(page)) {
|
|
f = 0;
|
|
t = PAGE_SIZE;
|
|
if (PagePrivate(page)) {
|
|
f = priv & AFS_PRIV_MAX;
|
|
t = priv >> AFS_PRIV_SHIFT;
|
|
}
|
|
|
|
trace_afs_page_dirty(vnode, tracepoint_string("launder"),
|
|
page->index, priv);
|
|
ret = afs_store_data(mapping, page->index, page->index, t, f);
|
|
}
|
|
|
|
trace_afs_page_dirty(vnode, tracepoint_string("laundered"),
|
|
page->index, priv);
|
|
set_page_private(page, 0);
|
|
ClearPagePrivate(page);
|
|
|
|
#ifdef CONFIG_AFS_FSCACHE
|
|
if (PageFsCache(page)) {
|
|
fscache_wait_on_page_write(vnode->cache, page);
|
|
fscache_uncache_page(vnode->cache, page);
|
|
}
|
|
#endif
|
|
return ret;
|
|
}
|