linux-stable/fs/afs/fs_operation.c
David Howells 453924de62 afs: Overhaul invalidation handling to better support RO volumes
Overhaul the third party-induced invalidation handling, making use of the
previously added volume-level event counters (cb_scrub and cb_ro_snapshot)
that are now being parsed out of the VolSync record returned by the
fileserver in many of its replies.

This allows better handling of RO (and Backup) volumes.  Since these are
snapshot of a RW volume that are updated atomically simultantanously across
all servers that host them, they only require a single callback promise for
the entire volume.  The currently upstream code assumes that RO volumes
operate in the same manner as RW volumes, and that each file has its own
individual callback - which means that it does a status fetch for *every*
file in a RO volume, whether or not the volume got "released" (volume
callback breaks can occur for other reasons too, such as the volumeserver
taking ownership of a volume from a fileserver).

To this end, make the following changes:

 (1) Change the meaning of the volume's cb_v_break counter so that it is
     now a hint that we need to issue a status fetch to work out the state
     of a volume.  cb_v_break is incremented by volume break callbacks and
     by server initialisation callbacks.

 (2) Add a second counter, cb_v_check, to the afs_volume struct such that
     if this differs from cb_v_break, we need to do a check.  When the
     check is complete, cb_v_check is advanced to what cb_v_break was at
     the start of the status fetch.

 (3) Move the list of mmap'd vnodes to the volume and trigger removal of
     PTEs that map to files on a volume break rather than on a server
     break.

 (4) When a server reinitialisation callback comes in, use the
     server-to-volume reverse mapping added in a preceding patch to iterate
     over all the volumes using that server and clear the volume callback
     promises for that server and the general volume promise as a whole to
     trigger reanalysis.

 (5) Replace the AFS_VNODE_CB_PROMISED flag with an AFS_NO_CB_PROMISE
     (TIME64_MIN) value in the cb_expires_at field, reducing the number of
     checks we need to make.

 (6) Change afs_check_validity() to quickly see if various event counters
     have been incremented or if the vnode or volume callback promise is
     due to expire/has expired without making any changes to the state.
     That is now left to afs_validate() as this may get more complicated in
     future as we may have to examine server records too.

 (7) Overhaul afs_validate() so that it does a single status fetch if we
     need to check the state of either the vnode or the volume - and do so
     under appropriate locking.  The function does the following steps:

     (A) If the vnode/volume is no longer seen as valid, then we take the
     vnode validation lock and, if the volume promise has expired, the
     volume check lock also.  The latter prevents redundant checks being
     made to find out if a new version of the volume got released.

     (B) If a previous RPC call found that the volsync changed unexpectedly
     or that a RO volume was updated, then we unmap all PTEs pointing to
     the file to stop mmap being used for access.

     (C) If the vnode is still seen to be of uncertain validity, then we
     perform an FS.FetchStatus RPC op to jointly update the volume status
     and the vnode status.  This assessment is done as part of parsing the
     reply:

	If the RO volume creation timestamp advances, cb_ro_snapshot is
	incremented; if either the creation or update timestamps changes in
	an unexpected way, the cb_scrub counter is incremented

	If the Data Version returned doesn't match the copy we have
	locally, then we ask for the pagecache to be zapped.  This takes
	care of handling RO update.

     (D) If cb_scrub differs between volume and vnode, the vnode's
     pagecache is zapped and the vnode's cb_scrub is updated unless the
     file is marked as having been deleted.

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

281 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;
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);
}