2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2007-04-27 06:55:03 +08:00
|
|
|
* Copyright (c) 2002, 2007 Red Hat, Inc. All rights reserved.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* This software may be freely redistributed under the terms of the
|
|
|
|
* GNU General Public License.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program; if not, write to the Free Software
|
|
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
|
|
*
|
2008-06-06 13:46:18 +08:00
|
|
|
* Authors: David Woodhouse <dwmw2@infradead.org>
|
2005-04-17 06:20:36 +08:00
|
|
|
* David Howells <dhowells@redhat.com>
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/init.h>
|
2007-04-27 06:55:03 +08:00
|
|
|
#include <linux/circ_buf.h>
|
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-21 05:22:52 +08:00
|
|
|
#include <linux/sched.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include "internal.h"
|
2007-04-27 06:55:03 +08:00
|
|
|
|
2017-11-02 23:27:49 +08:00
|
|
|
/*
|
|
|
|
* allow the fileserver to request callback state (re-)initialisation
|
|
|
|
*/
|
|
|
|
void afs_init_callback_state(struct afs_server *server)
|
|
|
|
{
|
afs: Fix in-progess ops to ignore server-level callback invalidation
The in-kernel afs filesystem client counts the number of server-level
callback invalidation events (CB.InitCallBackState* RPC operations) that it
receives from the server. This is stored in cb_s_break in various
structures, including afs_server and afs_vnode.
If an inode is examined by afs_validate(), say, the afs_server copy is
compared, along with other break counters, to those in afs_vnode, and if
one or more of the counters do not match, it is considered that the
server's callback promise is broken. At points where this happens,
AFS_VNODE_CB_PROMISED is cleared to indicate that the status must be
refetched from the server.
afs_validate() issues an FS.FetchStatus operation to get updated metadata -
and based on the updated data_version may invalidate the pagecache too.
However, the break counters are also used to determine whether to note a
new callback in the vnode (which would set the AFS_VNODE_CB_PROMISED flag)
and whether to cache the permit data included in the YFSFetchStatus record
by the server.
The problem comes when the server sends us a CB.InitCallBackState op. The
first such instance doesn't cause cb_s_break to be incremented, but rather
causes AFS_SERVER_FL_NEW to be cleared - but thereafter, say some hours
after last use and all the volumes have been automatically unmounted and
the server has forgotten about the client[*], this *will* likely cause an
increment.
[*] There are other circumstances too, such as the server restarting or
needing to make space in its callback table.
Note that the server won't send us a CB.InitCallBackState op until we talk
to it again.
So what happens is:
(1) A mount for a new volume is attempted, a inode is created for the root
vnode and vnode->cb_s_break and AFS_VNODE_CB_PROMISED aren't set
immediately, as we don't have a nominated server to talk to yet - and
we may iterate through a few to find one.
(2) Before the operation happens, afs_fetch_status(), say, notes in the
cursor (fc.cb_break) the break counter sum from the vnode, volume and
server counters, but the server->cb_s_break is currently 0.
(3) We send FS.FetchStatus to the server. The server sends us back
CB.InitCallBackState. We increment server->cb_s_break.
(4) Our FS.FetchStatus completes. The reply includes a callback record.
(5) xdr_decode_AFSCallBack()/xdr_decode_YFSCallBack() check to see whether
the callback promise was broken by checking the break counter sum from
step (2) against the current sum.
This fails because of step (3), so we don't set the callback record
and, importantly, don't set AFS_VNODE_CB_PROMISED on the vnode.
This does not preclude the syscall from progressing, and we don't loop here
rechecking the status, but rather assume it's good enough for one round
only and will need to be rechecked next time.
(6) afs_validate() it triggered on the vnode, probably called from
d_revalidate() checking the parent directory.
(7) afs_validate() notes that AFS_VNODE_CB_PROMISED isn't set, so doesn't
update vnode->cb_s_break and assumes the vnode to be invalid.
(8) afs_validate() needs to calls afs_fetch_status(). Go back to step (2)
and repeat, every time the vnode is validated.
This primarily affects volume root dir vnodes. Everything subsequent to
those inherit an already incremented cb_s_break upon mounting.
The issue is that we assume that the callback record and the cached permit
information in a reply from the server can't be trusted after getting a
server break - but this is wrong since the server makes sure things are
done in the right order, holding up our ops if necessary[*].
[*] There is an extremely unlikely scenario where a reply from before the
CB.InitCallBackState could get its delivery deferred till after - at
which point we think we have a promise when we don't. This, however,
requires unlucky mass packet loss to one call.
AFS_SERVER_FL_NEW tries to paper over the cracks for the initial mount from
a server we've never contacted before, but this should be unnecessary.
It's also further insulated from the problem on an initial mount by
querying the server first with FS.GetCapabilities, which triggers the
CB.InitCallBackState.
Fix this by
(1) Remove AFS_SERVER_FL_NEW.
(2) In afs_calc_vnode_cb_break(), don't include cb_s_break in the
calculation.
(3) In afs_cb_is_broken(), don't include cb_s_break in the check.
Signed-off-by: David Howells <dhowells@redhat.com>
2019-04-13 15:37:37 +08:00
|
|
|
server->cb_s_break++;
|
2007-04-27 06:55:03 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* actually break a callback
|
|
|
|
*/
|
2019-06-21 01:12:16 +08:00
|
|
|
void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason)
|
2007-04-27 06:55:03 +08:00
|
|
|
{
|
|
|
|
_enter("");
|
|
|
|
|
2018-04-06 21:17:26 +08:00
|
|
|
clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
|
2017-11-02 23:27:49 +08:00
|
|
|
if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
|
|
|
|
vnode->cb_break++;
|
|
|
|
afs_clear_permits(vnode);
|
2007-04-27 06:55:03 +08:00
|
|
|
|
2019-05-11 06:03:31 +08:00
|
|
|
if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB)
|
2007-07-16 14:40:12 +08:00
|
|
|
afs_lock_may_be_available(vnode);
|
2019-06-21 01:12:16 +08:00
|
|
|
|
|
|
|
trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, true);
|
|
|
|
} else {
|
|
|
|
trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, false);
|
2007-04-27 06:55:03 +08:00
|
|
|
}
|
2018-10-20 07:57:58 +08:00
|
|
|
}
|
2017-11-02 23:27:49 +08:00
|
|
|
|
2019-06-21 01:12:16 +08:00
|
|
|
void afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason)
|
2018-10-20 07:57:58 +08:00
|
|
|
{
|
|
|
|
write_seqlock(&vnode->cb_lock);
|
2019-06-21 01:12:16 +08:00
|
|
|
__afs_break_callback(vnode, reason);
|
2017-11-02 23:27:49 +08:00
|
|
|
write_sequnlock(&vnode->cb_lock);
|
2007-04-27 06:55:03 +08:00
|
|
|
}
|
|
|
|
|
2020-03-27 23:02:44 +08:00
|
|
|
/*
|
2020-04-30 08:03:49 +08:00
|
|
|
* Look up a volume by volume ID under RCU conditions.
|
2020-03-27 23:02:44 +08:00
|
|
|
*/
|
2020-04-30 08:03:49 +08:00
|
|
|
static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
|
|
|
|
afs_volid_t vid)
|
2020-03-27 23:02:44 +08:00
|
|
|
{
|
2020-04-30 08:03:49 +08:00
|
|
|
struct afs_volume *volume = NULL;
|
2020-03-27 23:02:44 +08:00
|
|
|
struct rb_node *p;
|
|
|
|
int seq = 0;
|
|
|
|
|
|
|
|
do {
|
|
|
|
/* Unfortunately, rbtree walking doesn't give reliable results
|
|
|
|
* under just the RCU read lock, so we have to check for
|
|
|
|
* changes.
|
|
|
|
*/
|
2020-04-30 08:03:49 +08:00
|
|
|
read_seqbegin_or_lock(&cell->volume_lock, &seq);
|
2020-03-27 23:02:44 +08:00
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
p = rcu_dereference_raw(cell->volumes.rb_node);
|
2020-03-27 23:02:44 +08:00
|
|
|
while (p) {
|
2020-04-30 08:03:49 +08:00
|
|
|
volume = rb_entry(p, struct afs_volume, cell_node);
|
2020-03-27 23:02:44 +08:00
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
if (volume->vid < vid)
|
2020-03-27 23:02:44 +08:00
|
|
|
p = rcu_dereference_raw(p->rb_left);
|
2020-04-30 08:03:49 +08:00
|
|
|
else if (volume->vid > vid)
|
2020-03-27 23:02:44 +08:00
|
|
|
p = rcu_dereference_raw(p->rb_right);
|
|
|
|
else
|
|
|
|
break;
|
2020-04-30 08:03:49 +08:00
|
|
|
volume = NULL;
|
2020-03-27 23:02:44 +08:00
|
|
|
}
|
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
} while (need_seqretry(&cell->volume_lock, seq));
|
2020-03-27 23:02:44 +08:00
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
done_seqretry(&cell->volume_lock, seq);
|
|
|
|
return volume;
|
2020-03-27 23:02:44 +08:00
|
|
|
}
|
|
|
|
|
2007-04-27 06:55:03 +08:00
|
|
|
/*
|
|
|
|
* allow the fileserver to explicitly break one callback
|
|
|
|
* - happens when
|
|
|
|
* - the backing file is changed
|
|
|
|
* - a lock is released
|
|
|
|
*/
|
2020-04-30 08:03:49 +08:00
|
|
|
static void afs_break_one_callback(struct afs_volume *volume,
|
|
|
|
struct afs_fid *fid)
|
2007-04-27 06:55:03 +08:00
|
|
|
{
|
2020-04-30 08:03:49 +08:00
|
|
|
struct super_block *sb;
|
2007-04-27 06:55:03 +08:00
|
|
|
struct afs_vnode *vnode;
|
2017-11-02 23:27:49 +08:00
|
|
|
struct inode *inode;
|
2007-04-27 06:55:03 +08:00
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
if (fid->vnode == 0 && fid->unique == 0) {
|
|
|
|
/* The callback break applies to an entire volume. */
|
|
|
|
write_lock(&volume->cb_v_break_lock);
|
|
|
|
volume->cb_v_break++;
|
|
|
|
trace_afs_cb_break(fid, volume->cb_v_break,
|
|
|
|
afs_cb_break_for_volume_callback, false);
|
|
|
|
write_unlock(&volume->cb_v_break_lock);
|
|
|
|
return;
|
|
|
|
}
|
2018-05-13 05:31:33 +08:00
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
/* See if we can find a matching inode - even an I_NEW inode needs to
|
|
|
|
* be marked as it can have its callback broken before we finish
|
|
|
|
* setting up the local inode.
|
|
|
|
*/
|
|
|
|
sb = rcu_dereference(volume->sb);
|
|
|
|
if (!sb)
|
|
|
|
return;
|
|
|
|
|
|
|
|
inode = find_inode_rcu(sb, fid->vnode, afs_ilookup5_test_by_fid, fid);
|
|
|
|
if (inode) {
|
|
|
|
vnode = AFS_FS_I(inode);
|
|
|
|
afs_break_callback(vnode, afs_cb_break_for_callback);
|
|
|
|
} else {
|
|
|
|
trace_afs_cb_miss(fid, afs_cb_break_for_callback);
|
2017-11-02 23:27:49 +08:00
|
|
|
}
|
2020-03-27 23:02:44 +08:00
|
|
|
}
|
2007-04-27 06:55:03 +08:00
|
|
|
|
2020-03-27 23:02:44 +08:00
|
|
|
static void afs_break_some_callbacks(struct afs_server *server,
|
|
|
|
struct afs_callback_break *cbb,
|
|
|
|
size_t *_count)
|
|
|
|
{
|
|
|
|
struct afs_callback_break *residue = cbb;
|
2020-04-30 08:03:49 +08:00
|
|
|
struct afs_volume *volume;
|
2020-03-27 23:02:44 +08:00
|
|
|
afs_volid_t vid = cbb->fid.vid;
|
|
|
|
size_t i;
|
|
|
|
|
2020-04-30 08:03:49 +08:00
|
|
|
volume = afs_lookup_volume_rcu(server->cell, vid);
|
2020-03-27 23:02:44 +08:00
|
|
|
|
|
|
|
/* TODO: Find all matching volumes if we couldn't match the server and
|
|
|
|
* break them anyway.
|
|
|
|
*/
|
|
|
|
|
|
|
|
for (i = *_count; i > 0; cbb++, i--) {
|
|
|
|
if (cbb->fid.vid == vid) {
|
|
|
|
_debug("- Fid { vl=%08llx n=%llu u=%u }",
|
|
|
|
cbb->fid.vid,
|
|
|
|
cbb->fid.vnode,
|
|
|
|
cbb->fid.unique);
|
|
|
|
--*_count;
|
2020-04-30 08:03:49 +08:00
|
|
|
if (volume)
|
|
|
|
afs_break_one_callback(volume, &cbb->fid);
|
2020-03-27 23:02:44 +08:00
|
|
|
} else {
|
|
|
|
*residue++ = *cbb;
|
|
|
|
}
|
|
|
|
}
|
2007-04-27 06:49:28 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* allow the fileserver to break callback promises
|
|
|
|
*/
|
2007-04-27 06:55:03 +08:00
|
|
|
void afs_break_callbacks(struct afs_server *server, size_t count,
|
2018-04-10 04:12:31 +08:00
|
|
|
struct afs_callback_break *callbacks)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-04-27 06:55:03 +08:00
|
|
|
_enter("%p,%zu,", server, count);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-04-27 06:55:03 +08:00
|
|
|
ASSERT(server != NULL);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2020-03-27 23:02:44 +08:00
|
|
|
rcu_read_lock();
|
2018-05-13 05:31:33 +08:00
|
|
|
|
2020-03-27 23:02:44 +08:00
|
|
|
while (count > 0)
|
|
|
|
afs_break_some_callbacks(server, callbacks, &count);
|
2007-04-27 06:55:03 +08:00
|
|
|
|
2020-03-27 23:02:44 +08:00
|
|
|
rcu_read_unlock();
|
2007-04-27 06:55:03 +08:00
|
|
|
return;
|
|
|
|
}
|