linux/fs/afs/fs_operation.c
David Howells 16069e1349 afs: Parse the VolSync record in the reply of a number of RPC ops
A number of fileserver RPC operations return a VolSync record as part of
their reply that gives some information about the state of the volume being
accessed, including:

 (1) A volume Creation timestamp.  For an RW volume, this is the time at
     which the volume was created; if it changes, the RW volume was
     presumably restored from a backup and all cached data should be
     scrubbed as Data Version numbers could regress on the files in the
     volume.

     For an RO volume, this is the time it was last snapshotted from the RW
     volume.  It is expected to advance each time this happens; if it
     regresses, cached data should be scrubbed.

 (2) A volume Update timestamp (Auristor only).  For an RW volume, this is
     updated any time any change is made to a volume or its contents.  If
     it regresses, all cached data must be scrubbed.

     For an RO volume, this is a copy of the RW volume's Update timestamp
     at the point of snapshotting.  It can be used as a version number when
     checking to see if a callback on a RO volume was due to a snapshot.
     If it regresses, all cached data must be scrubbed.

but this is currently not made use of by the in-kernel afs filesystem.

Make the afs filesystem use this by:

 (1) Add an update time field to the afs_volsync struct and use a value of
     TIME64_MIN in both that and the creation time to indicate that they
     are unset.

 (2) Add creation and update time fields to the afs_volume struct and use
     this to track the two timestamps.

 (3) Add a volsync_lock mutex to the afs_volume struct to control
     modification access for when we detect a change in these values.

 (3) Add a 'pre-op volsync' struct to the afs_operation struct to record
     the state of the volume tracking before the op.

 (4) Add a new counter, cb_scrub, to the afs_volume struct to count events
     that require all data to be scrubbed.  A copy is placed in the
     afs_vnode struct (inode) and if they no longer match, a scrub takes
     place.

 (5) When the result of an operation is being parsed, parse the VolSync
     data too, if it is provided.  Note that the two timestamps are handled
     separately, since they don't work in quite the same way.

     - If the afs_volume tracking is unset, just set it and do nothing
       else.

     - If the result timestamps are the same as the ones in afs_volume, do
       nothing.

     - If the timestamps regress, increment cb_scrub if not already done
       so.

     - If the creation timestamp on a RW volume changes, increment cb_scrub
       if not already done so.

     - If the creation timestamp on a RO volume advances, update the server
       list and see if the current server has been excluded, if so reissue
       the op.  Once over half of the replication sites have been updated,
       increment cb_ro_snapshot to indicate updates may be required and
       switch over to excluding unupdated replication sites.

     - If the creation timestamp on a Backup volume advances, just
       increment cb_ro_snapshot to trigger updates.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
2024-01-01 16:37:27 +00:00

282 lines
6.5 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/* Fileserver-directed operation handling.
*
* Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include "internal.h"
static atomic_t afs_operation_debug_counter;
/*
* Create an operation against a volume.
*/
struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *volume)
{
struct afs_operation *op;
_enter("");
op = kzalloc(sizeof(*op), GFP_KERNEL);
if (!op)
return ERR_PTR(-ENOMEM);
if (!key) {
key = afs_request_key(volume->cell);
if (IS_ERR(key)) {
kfree(op);
return ERR_CAST(key);
}
} else {
key_get(key);
}
op->key = key;
op->volume = afs_get_volume(volume, afs_volume_trace_get_new_op);
op->net = volume->cell->net;
op->cb_v_break = atomic_read(&volume->cb_v_break);
op->pre_volsync.creation = volume->creation_time;
op->pre_volsync.update = volume->update_time;
op->debug_id = atomic_inc_return(&afs_operation_debug_counter);
op->nr_iterations = -1;
afs_op_set_error(op, -EDESTADDRREQ);
_leave(" = [op=%08x]", op->debug_id);
return op;
}
/*
* Lock the vnode(s) being operated upon.
*/
static bool afs_get_io_locks(struct afs_operation *op)
{
struct afs_vnode *vnode = op->file[0].vnode;
struct afs_vnode *vnode2 = op->file[1].vnode;
_enter("");
if (op->flags & AFS_OPERATION_UNINTR) {
mutex_lock(&vnode->io_lock);
op->flags |= AFS_OPERATION_LOCK_0;
_leave(" = t [1]");
return true;
}
if (!vnode2 || !op->file[1].need_io_lock || vnode == vnode2)
vnode2 = NULL;
if (vnode2 > vnode)
swap(vnode, vnode2);
if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
afs_op_set_error(op, -ERESTARTSYS);
op->flags |= AFS_OPERATION_STOP;
_leave(" = f [I 0]");
return false;
}
op->flags |= AFS_OPERATION_LOCK_0;
if (vnode2) {
if (mutex_lock_interruptible_nested(&vnode2->io_lock, 1) < 0) {
afs_op_set_error(op, -ERESTARTSYS);
op->flags |= AFS_OPERATION_STOP;
mutex_unlock(&vnode->io_lock);
op->flags &= ~AFS_OPERATION_LOCK_0;
_leave(" = f [I 1]");
return false;
}
op->flags |= AFS_OPERATION_LOCK_1;
}
_leave(" = t [2]");
return true;
}
static void afs_drop_io_locks(struct afs_operation *op)
{
struct afs_vnode *vnode = op->file[0].vnode;
struct afs_vnode *vnode2 = op->file[1].vnode;
_enter("");
if (op->flags & AFS_OPERATION_LOCK_1)
mutex_unlock(&vnode2->io_lock);
if (op->flags & AFS_OPERATION_LOCK_0)
mutex_unlock(&vnode->io_lock);
}
static void afs_prepare_vnode(struct afs_operation *op, struct afs_vnode_param *vp,
unsigned int index)
{
struct afs_vnode *vnode = vp->vnode;
if (vnode) {
vp->fid = vnode->fid;
vp->dv_before = vnode->status.data_version;
vp->cb_break_before = afs_calc_vnode_cb_break(vnode);
if (vnode->lock_state != AFS_VNODE_LOCK_NONE)
op->flags |= AFS_OPERATION_CUR_ONLY;
if (vp->modification)
set_bit(AFS_VNODE_MODIFYING, &vnode->flags);
}
if (vp->fid.vnode)
_debug("PREP[%u] {%llx:%llu.%u}",
index, vp->fid.vid, vp->fid.vnode, vp->fid.unique);
}
/*
* Begin an operation on the fileserver.
*
* Fileserver operations are serialised on the server by vnode, so we serialise
* them here also using the io_lock.
*/
bool afs_begin_vnode_operation(struct afs_operation *op)
{
struct afs_vnode *vnode = op->file[0].vnode;
ASSERT(vnode);
_enter("");
if (op->file[0].need_io_lock)
if (!afs_get_io_locks(op))
return false;
afs_prepare_vnode(op, &op->file[0], 0);
afs_prepare_vnode(op, &op->file[1], 1);
op->cb_v_break = atomic_read(&op->volume->cb_v_break);
_leave(" = true");
return true;
}
/*
* Tidy up a filesystem cursor and unlock the vnode.
*/
static void afs_end_vnode_operation(struct afs_operation *op)
{
_enter("");
switch (afs_op_error(op)) {
case -EDESTADDRREQ:
case -EADDRNOTAVAIL:
case -ENETUNREACH:
case -EHOSTUNREACH:
afs_dump_edestaddrreq(op);
break;
}
afs_drop_io_locks(op);
}
/*
* Wait for an in-progress operation to complete.
*/
void afs_wait_for_operation(struct afs_operation *op)
{
_enter("");
while (afs_select_fileserver(op)) {
op->call_responded = false;
op->call_error = 0;
op->call_abort_code = 0;
op->cb_s_break = op->server->cb_s_break;
if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) &&
op->ops->issue_yfs_rpc)
op->ops->issue_yfs_rpc(op);
else if (op->ops->issue_afs_rpc)
op->ops->issue_afs_rpc(op);
else
op->call_error = -ENOTSUPP;
if (op->call) {
afs_wait_for_call_to_complete(op->call);
op->call_abort_code = op->call->abort_code;
op->call_error = op->call->error;
op->call_responded = op->call->responded;
afs_put_call(op->call);
}
}
if (op->call_responded)
set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags);
if (!afs_op_error(op)) {
_debug("success");
op->ops->success(op);
} else if (op->cumul_error.aborted) {
if (op->ops->aborted)
op->ops->aborted(op);
} else {
if (op->ops->failed)
op->ops->failed(op);
}
afs_end_vnode_operation(op);
if (!afs_op_error(op) && op->ops->edit_dir) {
_debug("edit_dir");
op->ops->edit_dir(op);
}
_leave("");
}
/*
* Dispose of an operation.
*/
int afs_put_operation(struct afs_operation *op)
{
struct afs_endpoint_state *estate = op->estate;
struct afs_addr_list *alist;
int i, ret = afs_op_error(op);
_enter("op=%08x,%d", op->debug_id, ret);
if (op->ops && op->ops->put)
op->ops->put(op);
if (op->file[0].modification)
clear_bit(AFS_VNODE_MODIFYING, &op->file[0].vnode->flags);
if (op->file[1].modification && op->file[1].vnode != op->file[0].vnode)
clear_bit(AFS_VNODE_MODIFYING, &op->file[1].vnode->flags);
if (op->file[0].put_vnode)
iput(&op->file[0].vnode->netfs.inode);
if (op->file[1].put_vnode)
iput(&op->file[1].vnode->netfs.inode);
if (op->more_files) {
for (i = 0; i < op->nr_files - 2; i++)
if (op->more_files[i].put_vnode)
iput(&op->more_files[i].vnode->netfs.inode);
kfree(op->more_files);
}
if (estate) {
alist = estate->addresses;
if (alist) {
if (op->call_responded &&
op->addr_index != alist->preferred &&
test_bit(alist->preferred, &op->addr_tried))
WRITE_ONCE(alist->preferred, op->addr_index);
}
afs_put_endpoint_state(estate, afs_estate_trace_put_operation);
op->estate = NULL;
}
afs_put_serverlist(op->net, op->server_list);
afs_put_volume(op->volume, afs_volume_trace_put_put_op);
key_put(op->key);
kfree(op);
return ret;
}
int afs_do_sync_operation(struct afs_operation *op)
{
afs_begin_vnode_operation(op);
afs_wait_for_operation(op);
return afs_put_operation(op);
}