linux/fs/afs/file.c

662 lines
15 KiB
C
Raw Normal View History

/* AFS filesystem file handling
*
* Copyright (C) 2002, 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/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/task_io_accounting_ops.h>
#include "internal.h"
static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
static int afs_readpage(struct file *file, struct page *page);
static void afs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
static int afs_releasepage(struct page *page, gfp_t gfp_flags);
static int afs_readpages(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
const struct file_operations afs_file_operations = {
.open = afs_open,
.flush = afs_flush,
.release = afs_release,
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.write_iter = afs_file_write,
.mmap = afs_file_mmap,
.splice_read = generic_file_splice_read,
.fsync = afs_fsync,
.lock = afs_lock,
.flock = afs_flock,
};
const struct inode_operations afs_file_inode_operations = {
.getattr = afs_getattr,
.setattr = afs_setattr,
.permission = afs_permission,
.listxattr = afs_listxattr,
};
const struct address_space_operations afs_fs_aops = {
.readpage = afs_readpage,
.readpages = afs_readpages,
.set_page_dirty = afs_set_page_dirty,
.launder_page = afs_launder_page,
.releasepage = afs_releasepage,
.invalidatepage = afs_invalidatepage,
.write_begin = afs_write_begin,
.write_end = afs_write_end,
.writepage = afs_writepage,
.writepages = afs_writepages,
};
static const struct vm_operations_struct afs_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = afs_page_mkwrite,
};
/*
* Discard a pin on a writeback key.
*/
void afs_put_wb_key(struct afs_wb_key *wbk)
{
if (refcount_dec_and_test(&wbk->usage)) {
key_put(wbk->key);
kfree(wbk);
}
}
/*
* Cache key for writeback.
*/
int afs_cache_wb_key(struct afs_vnode *vnode, struct afs_file *af)
{
struct afs_wb_key *wbk, *p;
wbk = kzalloc(sizeof(struct afs_wb_key), GFP_KERNEL);
if (!wbk)
return -ENOMEM;
refcount_set(&wbk->usage, 2);
wbk->key = af->key;
spin_lock(&vnode->wb_lock);
list_for_each_entry(p, &vnode->wb_keys, vnode_link) {
if (p->key == wbk->key)
goto found;
}
key_get(wbk->key);
list_add_tail(&wbk->vnode_link, &vnode->wb_keys);
spin_unlock(&vnode->wb_lock);
af->wb = wbk;
return 0;
found:
refcount_inc(&p->usage);
spin_unlock(&vnode->wb_lock);
af->wb = p;
kfree(wbk);
return 0;
}
/*
* open an AFS file or directory and attach a key to it
*/
int afs_open(struct inode *inode, struct file *file)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
struct afs_file *af;
struct key *key;
int ret;
_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
key = afs_request_key(vnode->volume->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
goto error;
}
af = kzalloc(sizeof(*af), GFP_KERNEL);
if (!af) {
ret = -ENOMEM;
goto error_key;
}
af->key = key;
ret = afs_validate(vnode, key);
if (ret < 0)
goto error_af;
if (file->f_mode & FMODE_WRITE) {
ret = afs_cache_wb_key(vnode, af);
if (ret < 0)
goto error_af;
}
file->private_data = af;
_leave(" = 0");
return 0;
error_af:
kfree(af);
error_key:
key_put(key);
error:
_leave(" = %d", ret);
return ret;
}
/*
* release an AFS file or directory and discard its key
*/
int afs_release(struct inode *inode, struct file *file)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
struct afs_file *af = file->private_data;
_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);
file->private_data = NULL;
if (af->wb)
afs_put_wb_key(af->wb);
key_put(af->key);
kfree(af);
afs_prune_wb_keys(vnode);
_leave(" = 0");
return 0;
}
/*
* Dispose of a ref to a read record.
*/
void afs_put_read(struct afs_read *req)
{
int i;
if (atomic_dec_and_test(&req->usage)) {
for (i = 0; i < req->nr_pages; i++)
if (req->pages[i])
put_page(req->pages[i]);
kfree(req);
}
}
#ifdef CONFIG_AFS_FSCACHE
/*
* deal with notification that a page was read from the cache
*/
static void afs_file_readpage_read_complete(struct page *page,
void *data,
int error)
{
_enter("%p,%p,%d", page, data, error);
/* if the read completes with an error, we just unlock the page and let
* the VM reissue the readpage */
if (!error)
SetPageUptodate(page);
unlock_page(page);
}
#endif
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
/*
* Fetch file data from the volume.
*/
int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *desc)
{
struct afs_fs_cursor fc;
int ret;
_enter("%s{%x:%u.%u},%x,,,",
vnode->volume->name,
vnode->fid.vid,
vnode->fid.vnode,
vnode->fid.unique,
key_serial(key));
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
fc.cb_break = vnode->cb_break + vnode->cb_s_break;
afs_fs_fetch_data(&fc, desc);
}
afs_check_for_remote_deletion(&fc, fc.vnode);
afs_vnode_commit_status(&fc, vnode, fc.cb_break);
ret = afs_end_vnode_operation(&fc);
}
_leave(" = %d", ret);
return ret;
}
/*
* read page from file, directory or symlink, given a key to use
*/
int afs_page_filler(void *data, struct page *page)
{
struct inode *inode = page->mapping->host;
struct afs_vnode *vnode = AFS_FS_I(inode);
struct afs_read *req;
struct key *key = data;
int ret;
_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
goto error;
/* is it cached? */
#ifdef CONFIG_AFS_FSCACHE
ret = fscache_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted (page in cache) */
case 0:
break;
/* page not yet cached */
case -ENODATA:
_debug("cache said ENODATA");
goto go_on;
/* page will not be cached */
case -ENOBUFS:
_debug("cache said ENOBUFS");
default:
go_on:
req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *),
GFP_KERNEL);
if (!req)
goto enomem;
/* We request a full page. If the page is a partial one at the
* end of the file, the server will return a short read and the
* unmarshalling code will clear the unfilled space.
*/
atomic_set(&req->usage, 1);
req->pos = (loff_t)page->index << PAGE_SHIFT;
req->len = PAGE_SIZE;
req->nr_pages = 1;
req->pages[0] = page;
get_page(page);
/* read the contents of the file from the server into the
* page */
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
ret = afs_fetch_data(vnode, key, req);
afs_put_read(req);
if (ret >= 0 && S_ISDIR(inode->i_mode) &&
!afs_dir_check_page(inode, page))
ret = -EIO;
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;
}
#ifdef CONFIG_AFS_FSCACHE
fscache_uncache_page(vnode->cache, page);
#endif
BUG_ON(PageFsCache(page));
if (ret == -EINTR ||
ret == -ENOMEM ||
ret == -ERESTARTSYS ||
ret == -EAGAIN)
goto error;
goto io_error;
}
SetPageUptodate(page);
/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page) &&
fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
fscache_uncache_page(vnode->cache, page);
BUG_ON(PageFsCache(page));
}
#endif
unlock_page(page);
}
_leave(" = 0");
return 0;
io_error:
SetPageError(page);
goto error;
enomem:
ret = -ENOMEM;
error:
unlock_page(page);
_leave(" = %d", ret);
return ret;
}
/*
* read page from file, directory or symlink, given a file to nominate the key
* to be used
*/
static int afs_readpage(struct file *file, struct page *page)
{
struct key *key;
int ret;
if (file) {
key = afs_file_key(file);
ASSERT(key != NULL);
ret = afs_page_filler(key, page);
} else {
struct inode *inode = page->mapping->host;
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
key = afs_request_key(AFS_FS_S(inode->i_sb)->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
} else {
ret = afs_page_filler(key, page);
key_put(key);
}
}
return ret;
}
/*
* Make pages available as they're filled.
*/
static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req)
{
#ifdef CONFIG_AFS_FSCACHE
struct afs_vnode *vnode = call->reply[0];
#endif
struct page *page = req->pages[req->index];
req->pages[req->index] = NULL;
SetPageUptodate(page);
/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page) &&
fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
fscache_uncache_page(vnode->cache, page);
BUG_ON(PageFsCache(page));
}
#endif
unlock_page(page);
put_page(page);
}
/*
* Read a contiguous set of pages.
*/
static int afs_readpages_one(struct file *file, struct address_space *mapping,
struct list_head *pages)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct afs_read *req;
struct list_head *p;
struct page *first, *page;
struct key *key = afs_file_key(file);
pgoff_t index;
int ret, n, i;
/* Count the number of contiguous pages at the front of the list. Note
* that the list goes prev-wards rather than next-wards.
*/
first = list_entry(pages->prev, struct page, lru);
index = first->index + 1;
n = 1;
for (p = first->lru.prev; p != pages; p = p->prev) {
page = list_entry(p, struct page, lru);
if (page->index != index)
break;
index++;
n++;
}
req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *) * n,
GFP_NOFS);
if (!req)
return -ENOMEM;
atomic_set(&req->usage, 1);
req->page_done = afs_readpages_page_done;
req->pos = first->index;
req->pos <<= PAGE_SHIFT;
/* Transfer the pages to the request. We add them in until one fails
* to add to the LRU and then we stop (as that'll make a hole in the
* contiguous run.
*
* Note that it's possible for the file size to change whilst we're
* doing this, but we rely on the server returning less than we asked
* for if the file shrank. We also rely on this to deal with a partial
* page at the end of the file.
*/
do {
page = list_entry(pages->prev, struct page, lru);
list_del(&page->lru);
index = page->index;
if (add_to_page_cache_lru(page, mapping, index,
readahead_gfp_mask(mapping))) {
#ifdef CONFIG_AFS_FSCACHE
fscache_uncache_page(vnode->cache, page);
#endif
put_page(page);
break;
}
req->pages[req->nr_pages++] = page;
req->len += PAGE_SIZE;
} while (req->nr_pages < n);
if (req->nr_pages == 0) {
kfree(req);
return 0;
}
afs: Overhaul volume and server record caching and fileserver rotation The current code assumes that volumes and servers are per-cell and are never shared, but this is not enforced, and, indeed, public cells do exist that are aliases of each other. Further, an organisation can, say, set up a public cell and a private cell with overlapping, but not identical, sets of servers. The difference is purely in the database attached to the VL servers. The current code will malfunction if it sees a server in two cells as it assumes global address -> server record mappings and that each server is in just one cell. Further, each server may have multiple addresses - and may have addresses of different families (IPv4 and IPv6, say). To this end, the following structural changes are made: (1) Server record management is overhauled: (a) Server records are made independent of cell. The namespace keeps track of them, volume records have lists of them and each vnode has a server on which its callback interest currently resides. (b) The cell record no longer keeps a list of servers known to be in that cell. (c) The server records are now kept in a flat list because there's no single address to sort on. (d) Server records are now keyed by their UUID within the namespace. (e) The addresses for a server are obtained with the VL.GetAddrsU rather than with VL.GetEntryByName, using the server's UUID as a parameter. (f) Cached server records are garbage collected after a period of non-use and are counted out of existence before purging is allowed to complete. This protects the work functions against rmmod. (g) The servers list is now in /proc/fs/afs/servers. (2) Volume record management is overhauled: (a) An RCU-replaceable server list is introduced. This tracks both servers and their coresponding callback interests. (b) The superblock is now keyed on cell record and numeric volume ID. (c) The volume record is now tied to the superblock which mounts it, and is activated when mounted and deactivated when unmounted. This makes it easier to handle the cache cookie without causing a double-use in fscache. (d) The volume record is loaded from the VLDB using VL.GetEntryByNameU to get the server UUID list. (e) The volume name is updated if it is seen to have changed when the volume is updated (the update is keyed on the volume ID). (3) The vlocation record is got rid of and VLDB records are no longer cached. Sufficient information is stored in the volume record, though an update to a volume record is now no longer shared between related volumes (volumes come in bundles of three: R/W, R/O and backup). and the following procedural changes are made: (1) The fileserver cursor introduced previously is now fleshed out and used to iterate over fileservers and their addresses. (2) Volume status is checked during iteration, and the server list is replaced if a change is detected. (3) Server status is checked during iteration, and the address list is replaced if a change is detected. (4) The abort code is saved into the address list cursor and -ECONNABORTED returned in afs_make_call() if a remote abort happened rather than translating the abort into an error message. This allows actions to be taken depending on the abort code more easily. (a) If a VMOVED abort is seen then this is handled by rechecking the volume and restarting the iteration. (b) If a VBUSY, VRESTARTING or VSALVAGING abort is seen then this is handled by sleeping for a short period and retrying and/or trying other servers that might serve that volume. A message is also displayed once until the condition has cleared. (c) If a VOFFLINE abort is seen, then this is handled as VBUSY for the moment. (d) If a VNOVOL abort is seen, the volume is rechecked in the VLDB to see if it has been deleted; if not, the fileserver is probably indicating that the volume couldn't be attached and needs salvaging. (e) If statfs() sees one of these aborts, it does not sleep, but rather returns an error, so as not to block the umount program. (5) The fileserver iteration functions in vnode.c are now merged into their callers and more heavily macroised around the cursor. vnode.c is removed. (6) Operations on a particular vnode are serialised on that vnode because the server will lock that vnode whilst it operates on it, so a second op sent will just have to wait. (7) Fileservers are probed with FS.GetCapabilities before being used. This is where service upgrade will be done. (8) A callback interest on a fileserver is set up before an FS operation is performed and passed through to afs_make_call() so that it can be set on the vnode if the operation returns a callback. The callback interest is passed through to afs_iget() also so that it can be set there too. In general, record updating is done on an as-needed basis when we try to access servers, volumes or vnodes rather than offloading it to work items and special threads. Notes: (1) Pre AFS-3.4 servers are no longer supported, though this can be added back if necessary (AFS-3.4 was released in 1998). (2) VBUSY is retried forever for the moment at intervals of 1s. (3) /proc/fs/afs/<cell>/servers no longer exists. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 23:27:50 +08:00
ret = afs_fetch_data(vnode, key, req);
if (ret < 0)
goto error;
task_io_account_read(PAGE_SIZE * req->nr_pages);
afs_put_read(req);
return 0;
error:
if (ret == -ENOENT) {
_debug("got NOENT from server"
" - marking file deleted and stale");
set_bit(AFS_VNODE_DELETED, &vnode->flags);
ret = -ESTALE;
}
for (i = 0; i < req->nr_pages; i++) {
page = req->pages[i];
if (page) {
#ifdef CONFIG_AFS_FSCACHE
fscache_uncache_page(vnode->cache, page);
#endif
SetPageError(page);
unlock_page(page);
}
}
afs_put_read(req);
return ret;
}
/*
* read a set of pages
*/
static int afs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct key *key = afs_file_key(file);
struct afs_vnode *vnode;
int ret = 0;
_enter("{%d},{%lu},,%d",
key_serial(key), mapping->host->i_ino, nr_pages);
ASSERT(key != NULL);
vnode = AFS_FS_I(mapping->host);
if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
_leave(" = -ESTALE");
return -ESTALE;
}
/* attempt to read as many of the pages as possible */
#ifdef CONFIG_AFS_FSCACHE
ret = fscache_read_or_alloc_pages(vnode->cache,
mapping,
pages,
&nr_pages,
afs_file_readpage_read_complete,
NULL,
mapping_gfp_mask(mapping));
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* all pages are being read from the cache */
case 0:
BUG_ON(!list_empty(pages));
BUG_ON(nr_pages != 0);
_leave(" = 0 [reading all]");
return 0;
/* there were pages that couldn't be read from the cache */
case -ENODATA:
case -ENOBUFS:
break;
/* other error */
default:
_leave(" = %d", ret);
return ret;
}
while (!list_empty(pages)) {
ret = afs_readpages_one(file, mapping, pages);
if (ret < 0)
break;
}
_leave(" = %d [netting]", ret);
return ret;
}
/*
* invalidate part or all of a page
* - release a page and clean up its private data if offset is 0 (indicating
* the entire page)
*/
static void afs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length)
{
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
unsigned long priv;
_enter("{%lu},%u,%u", page->index, offset, length);
BUG_ON(!PageLocked(page));
/* we clean up only if the entire page is being invalidated */
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
if (offset == 0 && length == PAGE_SIZE) {
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
fscache_wait_on_page_write(vnode->cache, page);
fscache_uncache_page(vnode->cache, page);
}
#endif
if (PagePrivate(page)) {
priv = page_private(page);
trace_afs_page_dirty(vnode, tracepoint_string("inval"),
page->index, priv);
set_page_private(page, 0);
ClearPagePrivate(page);
}
}
_leave("");
}
/*
* release a page and clean up its private state if it's not busy
* - return true if the page can now be released, false if not
*/
static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
unsigned long priv;
_enter("{{%x:%u}[%lu],%lx},%x",
vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
gfp_flags);
/* deny if page is being written to the cache and the caller hasn't
* elected to wait */
#ifdef CONFIG_AFS_FSCACHE
FS-Cache: Handle pages pending storage that get evicted under OOM conditions Handle netfs pages that the vmscan algorithm wants to evict from the pagecache under OOM conditions, but that are waiting for write to the cache. Under these conditions, vmscan calls the releasepage() function of the netfs, asking if a page can be discarded. The problem is typified by the following trace of a stuck process: kslowd005 D 0000000000000000 0 4253 2 0x00000080 ffff88001b14f370 0000000000000046 ffff880020d0d000 0000000000000007 0000000000000006 0000000000000001 ffff88001b14ffd8 ffff880020d0d2a8 000000000000ddf0 00000000000118c0 00000000000118c0 ffff880020d0d2a8 Call Trace: [<ffffffffa00782d8>] __fscache_wait_on_page_write+0x8b/0xa7 [fscache] [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34 [<ffffffffa0078240>] ? __fscache_check_page_write+0x63/0x70 [fscache] [<ffffffffa00b671d>] nfs_fscache_release_page+0x4e/0xc4 [nfs] [<ffffffffa00927f0>] nfs_release_page+0x3c/0x41 [nfs] [<ffffffff810885d3>] try_to_release_page+0x32/0x3b [<ffffffff81093203>] shrink_page_list+0x316/0x4ac [<ffffffff8109372b>] shrink_inactive_list+0x392/0x67c [<ffffffff813532fa>] ? __mutex_unlock_slowpath+0x100/0x10b [<ffffffff81058df0>] ? trace_hardirqs_on_caller+0x10c/0x130 [<ffffffff8135330e>] ? mutex_unlock+0x9/0xb [<ffffffff81093aa2>] shrink_list+0x8d/0x8f [<ffffffff81093d1c>] shrink_zone+0x278/0x33c [<ffffffff81052d6c>] ? ktime_get_ts+0xad/0xba [<ffffffff81094b13>] try_to_free_pages+0x22e/0x392 [<ffffffff81091e24>] ? isolate_pages_global+0x0/0x212 [<ffffffff8108e743>] __alloc_pages_nodemask+0x3dc/0x5cf [<ffffffff81089529>] grab_cache_page_write_begin+0x65/0xaa [<ffffffff8110f8c0>] ext3_write_begin+0x78/0x1eb [<ffffffff81089ec5>] generic_file_buffered_write+0x109/0x28c [<ffffffff8103cb69>] ? current_fs_time+0x22/0x29 [<ffffffff8108a509>] __generic_file_aio_write+0x350/0x385 [<ffffffff8108a588>] ? generic_file_aio_write+0x4a/0xae [<ffffffff8108a59e>] generic_file_aio_write+0x60/0xae [<ffffffff810b2e82>] do_sync_write+0xe3/0x120 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34 [<ffffffff810b18e1>] ? __dentry_open+0x1a5/0x2b8 [<ffffffff810b1a76>] ? dentry_open+0x82/0x89 [<ffffffffa00e693c>] cachefiles_write_page+0x298/0x335 [cachefiles] [<ffffffffa0077147>] fscache_write_op+0x178/0x2c2 [fscache] [<ffffffffa0075656>] fscache_op_execute+0x7a/0xd1 [fscache] [<ffffffff81082093>] slow_work_execute+0x18f/0x2d1 [<ffffffff8108239a>] slow_work_thread+0x1c5/0x308 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34 [<ffffffff810821d5>] ? slow_work_thread+0x0/0x308 [<ffffffff8104be91>] kthread+0x7a/0x82 [<ffffffff8100beda>] child_rip+0xa/0x20 [<ffffffff8100b87c>] ? restore_args+0x0/0x30 [<ffffffff8102ef83>] ? tg_shares_up+0x171/0x227 [<ffffffff8104be17>] ? kthread+0x0/0x82 [<ffffffff8100bed0>] ? child_rip+0x0/0x20 In the above backtrace, the following is happening: (1) A page storage operation is being executed by a slow-work thread (fscache_write_op()). (2) FS-Cache farms the operation out to the cache to perform (cachefiles_write_page()). (3) CacheFiles is then calling Ext3 to perform the actual write, using Ext3's standard write (do_sync_write()) under KERNEL_DS directly from the netfs page. (4) However, for Ext3 to perform the write, it must allocate some memory, in particular, it must allocate at least one page cache page into which it can copy the data from the netfs page. (5) Under OOM conditions, the memory allocator can't immediately come up with a page, so it uses vmscan to find something to discard (try_to_free_pages()). (6) vmscan finds a clean netfs page it might be able to discard (possibly the one it's trying to write out). (7) The netfs is called to throw the page away (nfs_release_page()) - but it's called with __GFP_WAIT, so the netfs decides to wait for the store to complete (__fscache_wait_on_page_write()). (8) This blocks a slow-work processing thread - possibly against itself. The system ends up stuck because it can't write out any netfs pages to the cache without allocating more memory. To avoid this, we make FS-Cache cancel some writes that aren't in the middle of actually being performed. This means that some data won't make it into the cache this time. To support this, a new FS-Cache function is added fscache_maybe_release_page() that replaces what the netfs releasepage() functions used to do with respect to the cache. The decisions fscache_maybe_release_page() makes are counted and displayed through /proc/fs/fscache/stats on a line labelled "VmScan". There are four counters provided: "nos=N" - pages that weren't pending storage; "gon=N" - pages that were pending storage when we first looked, but weren't by the time we got the object lock; "bsy=N" - pages that we ignored as they were actively being written when we looked; and "can=N" - pages that we cancelled the storage of. What I'd really like to do is alter the behaviour of the cancellation heuristics, depending on how necessary it is to expel pages. If there are plenty of other pages that aren't waiting to be written to the cache that could be ejected first, then it would be nice to hold up on immediate cancellation of cache writes - but I don't see a way of doing that. Signed-off-by: David Howells <dhowells@redhat.com>
2009-11-20 02:11:35 +08:00
if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
_leave(" = F [cache busy]");
return 0;
}
#endif
if (PagePrivate(page)) {
priv = page_private(page);
trace_afs_page_dirty(vnode, tracepoint_string("rel"),
page->index, priv);
set_page_private(page, 0);
ClearPagePrivate(page);
}
/* indicate that the page can be released */
_leave(" = T");
return 1;
}
/*
* Handle setting up a memory mapping on an AFS file.
*/
static int afs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
int ret;
ret = generic_file_mmap(file, vma);
if (ret == 0)
vma->vm_ops = &afs_vm_ops;
return ret;
}