linux/fs/afs/cell.c

814 lines
20 KiB
C
Raw Normal View History

/* AFS cell and server record management
*
* Copyright (C) 2002, 2017 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/slab.h>
#include <linux/key.h>
#include <linux/ctype.h>
#include <linux/dns_resolver.h>
#include <linux/sched.h>
#include <linux/inet.h>
#include <linux/namei.h>
#include <keys/rxrpc-type.h>
#include "internal.h"
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-09 23:12:31 +03:00
static unsigned __read_mostly afs_cell_gc_delay = 10;
static unsigned __read_mostly afs_cell_min_ttl = 10 * 60;
static unsigned __read_mostly afs_cell_max_ttl = 24 * 60 * 60;
static void afs_manage_cell(struct work_struct *);
static void afs_dec_cells_outstanding(struct afs_net *net)
{
if (atomic_dec_and_test(&net->cells_outstanding))
wake_up_var(&net->cells_outstanding);
}
/*
* Set the cell timer to fire after a given delay, assuming it's not already
* set for an earlier time.
*/
static void afs_set_cell_timer(struct afs_net *net, time64_t delay)
{
if (net->live) {
atomic_inc(&net->cells_outstanding);
if (timer_reduce(&net->cells_timer, jiffies + delay * HZ))
afs_dec_cells_outstanding(net);
}
}
/*
* Look up and get an activation reference on a cell record under RCU
* conditions. The caller must hold the RCU read lock.
*/
struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
const char *name, unsigned int namesz)
{
struct afs_cell *cell = NULL;
struct rb_node *p;
int n, seq = 0, ret = 0;
_enter("%*.*s", namesz, namesz, name);
if (name && namesz == 0)
return ERR_PTR(-EINVAL);
if (namesz > AFS_MAXCELLNAME)
return ERR_PTR(-ENAMETOOLONG);
do {
/* Unfortunately, rbtree walking doesn't give reliable results
* under just the RCU read lock, so we have to check for
* changes.
*/
if (cell)
afs_put_cell(net, cell);
cell = NULL;
ret = -ENOENT;
read_seqbegin_or_lock(&net->cells_lock, &seq);
if (!name) {
cell = rcu_dereference_raw(net->ws_cell);
if (cell) {
afs_get_cell(cell);
afs: Fix checker warnings Fix warnings raised by checker, including: (*) Warnings raised by unequal comparison for the purposes of sorting, where the endianness doesn't matter: fs/afs/addr_list.c:246:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:246:30: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:248:21: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:248:49: warning: restricted __be32 degrades to integer fs/afs/addr_list.c:283:21: warning: restricted __be16 degrades to integer fs/afs/addr_list.c:283:30: warning: restricted __be16 degrades to integer (*) afs_set_cb_interest() is not actually used and can be removed. (*) afs_cell_gc_delay() should be provided with a sysctl. (*) afs_cell_destroy() needs to use rcu_access_pointer() to read cell->vl_addrs. (*) afs_init_fs_cursor() should be static. (*) struct afs_vnode::permit_cache needs to be marked __rcu. (*) afs_server_rcu() needs to use rcu_access_pointer(). (*) afs_destroy_server() should use rcu_access_pointer() on server->addresses as the server object is no longer accessible. (*) afs_find_server() casts __be16/__be32 values to int in order to directly compare them for the purpose of finding a match in a list, but is should also annotate the cast with __force to avoid checker warnings. (*) afs_check_permit() accesses vnode->permit_cache outside of the RCU readlock, though it doesn't then access the value; the extraneous access is deleted. False positives: (*) Conditional locking around the code in xdr_decode_AFSFetchStatus. This can be dealt with in a separate patch. fs/afs/fsclient.c:148:9: warning: context imbalance in 'xdr_decode_AFSFetchStatus' - different lock contexts for basic block (*) Incorrect handling of seq-retry lock context balance: fs/afs/inode.c:455:38: warning: context imbalance in 'afs_getattr' - different lock contexts for basic block fs/afs/server.c:52:17: warning: context imbalance in 'afs_find_server' - different lock contexts for basic block fs/afs/server.c:128:17: warning: context imbalance in 'afs_find_server_by_uuid' - different lock contexts for basic block Errors: (*) afs_lookup_cell_rcu() needs to break out of the seq-retry loop, not go round again if it successfully found the workstation cell. (*) Fix UUID decode in afs_deliver_cb_probe_uuid(). (*) afs_cache_permit() has a missing rcu_read_unlock() before one of the jumps to the someone_else_changed_it label. Move the unlock to after the label. (*) afs_vl_get_addrs_u() is using ntohl() rather than htonl() when encoding to XDR. (*) afs_deliver_yfsvl_get_endpoints() is using htonl() rather than ntohl() when decoding from XDR. Signed-off-by: David Howells <dhowells@redhat.com>
2018-04-09 23:12:31 +03:00
break;
}
ret = -EDESTADDRREQ;
continue;
}
p = rcu_dereference_raw(net->cells.rb_node);
while (p) {
cell = rb_entry(p, struct afs_cell, net_node);
n = strncasecmp(cell->name, name,
min_t(size_t, cell->name_len, namesz));
if (n == 0)
n = cell->name_len - namesz;
if (n < 0) {
p = rcu_dereference_raw(p->rb_left);
} else if (n > 0) {
p = rcu_dereference_raw(p->rb_right);
} else {
if (atomic_inc_not_zero(&cell->usage)) {
ret = 0;
break;
}
/* We want to repeat the search, this time with
* the lock properly locked.
*/
}
cell = NULL;
}
} while (need_seqretry(&net->cells_lock, seq));
done_seqretry(&net->cells_lock, seq);
return ret == 0 ? cell : ERR_PTR(ret);
}
/*
* Set up a cell record and fill in its name, VL server address list and
* allocate an anonymous key
*/
static struct afs_cell *afs_alloc_cell(struct afs_net *net,
const char *name, unsigned int namelen,
const char *addresses)
{
struct afs_vlserver_list *vllist;
struct afs_cell *cell;
int i, ret;
ASSERT(name);
if (namelen == 0)
return ERR_PTR(-EINVAL);
if (namelen > AFS_MAXCELLNAME) {
_leave(" = -ENAMETOOLONG");
return ERR_PTR(-ENAMETOOLONG);
}
if (namelen == 5 && memcmp(name, "@cell", 5) == 0)
return ERR_PTR(-EINVAL);
_enter("%*.*s,%s", namelen, namelen, name, addresses);
cell = kzalloc(sizeof(struct afs_cell), GFP_KERNEL);
if (!cell) {
_leave(" = -ENOMEM");
return ERR_PTR(-ENOMEM);
}
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 18:27:45 +03:00
cell->net = net;
cell->name_len = namelen;
for (i = 0; i < namelen; i++)
cell->name[i] = tolower(name[i]);
atomic_set(&cell->usage, 2);
INIT_WORK(&cell->manager, afs_manage_cell);
cell->flags = ((1 << AFS_CELL_FL_NOT_READY) |
(1 << AFS_CELL_FL_NO_LOOKUP_YET));
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 18:27:50 +03:00
INIT_LIST_HEAD(&cell->proc_volumes);
rwlock_init(&cell->proc_lock);
rwlock_init(&cell->vl_servers_lock);
/* Provide a VL server list, filling it in if we were given a list of
* addresses to use.
*/
if (addresses) {
vllist = afs_parse_text_addrs(net,
addresses, strlen(addresses), ':',
VL_SERVICE, AFS_VL_PORT);
if (IS_ERR(vllist)) {
ret = PTR_ERR(vllist);
goto parse_failed;
}
cell->dns_expiry = TIME64_MAX;
} else {
ret = -ENOMEM;
vllist = afs_alloc_vlserver_list(0);
if (!vllist)
goto error;
cell->dns_expiry = ktime_get_real_seconds();
}
rcu_assign_pointer(cell->vl_servers, vllist);
_leave(" = %p", cell);
return cell;
parse_failed:
if (ret == -EINVAL)
printk(KERN_ERR "kAFS: bad VL server IP address\n");
error:
kfree(cell);
_leave(" = %d", ret);
return ERR_PTR(ret);
}
/*
* afs_lookup_cell - Look up or create a cell record.
afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells <dhowells@redhat.com>
2017-11-02 18:27:45 +03:00
* @net: The network namespace
* @name: The name of the cell.
* @namesz: The strlen of the cell name.
* @vllist: A colon/comma separated list of numeric IP addresses or NULL.
* @excl: T if an error should be given if the cell name already exists.
*
* Look up a cell record by name and query the DNS for VL server addresses if
* needed. Note that that actual DNS query is punted off to the manager thread
* so that this function can return immediately if interrupted whilst allowing
* cell records to be shared even if not yet fully constructed.
*/
struct afs_cell *afs_lookup_cell(struct afs_net *net,
const char *name, unsigned int namesz,
const char *vllist, bool excl)
{
struct afs_cell *cell, *candidate, *cursor;
struct rb_node *parent, **pp;
int ret, n;
_enter("%s,%s", name, vllist);
if (!excl) {
rcu_read_lock();
cell = afs_lookup_cell_rcu(net, name, namesz);
rcu_read_unlock();
if (!IS_ERR(cell))
goto wait_for_cell;
}
/* Assume we're probably going to create a cell and preallocate and
* mostly set up a candidate record. We can then use this to stash the
* name, the net namespace and VL server addresses.
*
* We also want to do this before we hold any locks as it may involve
* upcalling to userspace to make DNS queries.
*/
candidate = afs_alloc_cell(net, name, namesz, vllist);
if (IS_ERR(candidate)) {
_leave(" = %ld", PTR_ERR(candidate));
return candidate;
}
/* Find the insertion point and check to see if someone else added a
* cell whilst we were allocating.
*/
write_seqlock(&net->cells_lock);
pp = &net->cells.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
cursor = rb_entry(parent, struct afs_cell, net_node);
n = strncasecmp(cursor->name, name,
min_t(size_t, cursor->name_len, namesz));
if (n == 0)
n = cursor->name_len - namesz;
if (n < 0)
pp = &(*pp)->rb_left;
else if (n > 0)
pp = &(*pp)->rb_right;
else
goto cell_already_exists;
}
cell = candidate;
candidate = NULL;
rb_link_node_rcu(&cell->net_node, parent, pp);
rb_insert_color(&cell->net_node, &net->cells);
atomic_inc(&net->cells_outstanding);
write_sequnlock(&net->cells_lock);
queue_work(afs_wq, &cell->manager);
wait_for_cell:
_debug("wait_for_cell");
ret = wait_on_bit(&cell->flags, AFS_CELL_FL_NOT_READY, TASK_INTERRUPTIBLE);
smp_rmb();
switch (READ_ONCE(cell->state)) {
case AFS_CELL_FAILED:
ret = cell->error;
goto error;
default:
_debug("weird %u %d", cell->state, cell->error);
goto error;
case AFS_CELL_ACTIVE:
break;
}
_leave(" = %p [cell]", cell);
return cell;
cell_already_exists:
_debug("cell exists");
cell = cursor;
if (excl) {
ret = -EEXIST;
} else {
afs_get_cell(cursor);
ret = 0;
}
write_sequnlock(&net->cells_lock);
kfree(candidate);
if (ret == 0)
goto wait_for_cell;
goto error_noput;
error:
afs_put_cell(net, cell);
error_noput:
_leave(" = %d [error]", ret);
return ERR_PTR(ret);
}
/*
* set the root cell information
* - can be called with a module parameter string
* - can be called from a write to /proc/fs/afs/rootcell
*/
int afs_cell_init(struct afs_net *net, const char *rootcell)
{
struct afs_cell *old_root, *new_root;
const char *cp, *vllist;
size_t len;
_enter("");
if (!rootcell) {
/* module is loaded with no parameters, or built statically.
* - in the future we might initialize cell DB here.
*/
_leave(" = 0 [no root]");
return 0;
}
cp = strchr(rootcell, ':');
if (!cp) {
_debug("kAFS: no VL server IP addresses specified");
vllist = NULL;
len = strlen(rootcell);
} else {
vllist = cp + 1;
len = cp - rootcell;
}
/* allocate a cell record for the root cell */
new_root = afs_lookup_cell(net, rootcell, len, vllist, false);
if (IS_ERR(new_root)) {
_leave(" = %ld", PTR_ERR(new_root));
return PTR_ERR(new_root);
}
if (!test_and_set_bit(AFS_CELL_FL_NO_GC, &new_root->flags))
afs_get_cell(new_root);
/* install the new cell */
write_seqlock(&net->cells_lock);
old_root = rcu_access_pointer(net->ws_cell);
rcu_assign_pointer(net->ws_cell, new_root);
write_sequnlock(&net->cells_lock);
afs_put_cell(net, old_root);
_leave(" = 0");
return 0;
}
/*
* Update a cell's VL server address list from the DNS.
*/
static void afs_update_cell(struct afs_cell *cell)
{
struct afs_vlserver_list *vllist, *old;
unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl);
unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl);
time64_t now, expiry = 0;
_enter("%s", cell->name);
vllist = afs_dns_query(cell, &expiry);
now = ktime_get_real_seconds();
if (min_ttl > max_ttl)
max_ttl = min_ttl;
if (expiry < now + min_ttl)
expiry = now + min_ttl;
else if (expiry > now + max_ttl)
expiry = now + max_ttl;
if (IS_ERR(vllist)) {
switch (PTR_ERR(vllist)) {
case -ENODATA:
case -EDESTADDRREQ:
/* The DNS said that the cell does not exist or there
* weren't any addresses to be had.
*/
set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = expiry;
break;
case -EAGAIN:
case -ECONNREFUSED:
default:
set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = now + 10;
break;
}
cell->error = -EDESTADDRREQ;
} else {
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
clear_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
write_lock(&cell->vl_servers_lock);
old = rcu_dereference_protected(cell->vl_servers, true);
rcu_assign_pointer(cell->vl_servers, vllist);
cell->dns_expiry = expiry;
write_unlock(&cell->vl_servers_lock);
afs_put_vlserverlist(cell->net, old);
}
if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags))
wake_up_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET);
now = ktime_get_real_seconds();
afs_set_cell_timer(cell->net, cell->dns_expiry - now);
_leave("");
}
/*
* Destroy a cell record
*/
static void afs_cell_destroy(struct rcu_head *rcu)
{
struct afs_cell *cell = container_of(rcu, struct afs_cell, rcu);
_enter("%p{%s}", cell, cell->name);
ASSERTCMP(atomic_read(&cell->usage), ==, 0);
afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers));
key_put(cell->anonymous_key);
kfree(cell);
_leave(" [destroyed]");
}
/*
* Queue the cell manager.
*/
static void afs_queue_cell_manager(struct afs_net *net)
{
int outstanding = atomic_inc_return(&net->cells_outstanding);
_enter("%d", outstanding);
if (!queue_work(afs_wq, &net->cells_manager))
afs_dec_cells_outstanding(net);
}
/*
* Cell management timer. We have an increment on cells_outstanding that we
* need to pass along to the work item.
*/
void afs_cells_timer(struct timer_list *timer)
{
struct afs_net *net = container_of(timer, struct afs_net, cells_timer);
_enter("");
if (!queue_work(afs_wq, &net->cells_manager))
afs_dec_cells_outstanding(net);
}
/*
* Get a reference on a cell record.
*/
struct afs_cell *afs_get_cell(struct afs_cell *cell)
{
atomic_inc(&cell->usage);
return cell;
}
/*
* Drop a reference on a cell record.
*/
void afs_put_cell(struct afs_net *net, struct afs_cell *cell)
{
time64_t now, expire_delay;
if (!cell)
return;
_enter("%s", cell->name);
now = ktime_get_real_seconds();
cell->last_inactive = now;
expire_delay = 0;
if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) &&
!test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags))
expire_delay = afs_cell_gc_delay;
if (atomic_dec_return(&cell->usage) > 1)
return;
/* 'cell' may now be garbage collected. */
afs_set_cell_timer(net, expire_delay);
}
/*
* Allocate a key to use as a placeholder for anonymous user security.
*/
static int afs_alloc_anon_key(struct afs_cell *cell)
{
struct key *key;
char keyname[4 + AFS_MAXCELLNAME + 1], *cp, *dp;
/* Create a key to represent an anonymous user. */
memcpy(keyname, "afs@", 4);
dp = keyname + 4;
cp = cell->name;
do {
*dp++ = tolower(*cp);
} while (*cp++);
key = rxrpc_get_null_key(keyname);
if (IS_ERR(key))
return PTR_ERR(key);
cell->anonymous_key = key;
_debug("anon key %p{%x}",
cell->anonymous_key, key_serial(cell->anonymous_key));
return 0;
}
/*
* Activate a cell.
*/
static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell)
{
struct hlist_node **p;
struct afs_cell *pcell;
int ret;
if (!cell->anonymous_key) {
ret = afs_alloc_anon_key(cell);
if (ret < 0)
return ret;
}
#ifdef CONFIG_AFS_FSCACHE
cell->cache = fscache_acquire_cookie(afs_cache_netfs.primary_index,
&afs_cell_cache_index_def,
cell->name, strlen(cell->name),
NULL, 0,
cell, 0, true);
#endif
ret = afs_proc_cell_setup(cell);
if (ret < 0)
return ret;
mutex_lock(&net->proc_cells_lock);
for (p = &net->proc_cells.first; *p; p = &(*p)->next) {
pcell = hlist_entry(*p, struct afs_cell, proc_link);
if (strcmp(cell->name, pcell->name) < 0)
break;
}
cell->proc_link.pprev = p;
cell->proc_link.next = *p;
rcu_assign_pointer(*p, &cell->proc_link.next);
if (cell->proc_link.next)
cell->proc_link.next->pprev = &cell->proc_link.next;
afs_dynroot_mkdir(net, cell);
mutex_unlock(&net->proc_cells_lock);
return 0;
}
/*
* Deactivate a cell.
*/
static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell)
{
_enter("%s", cell->name);
afs_proc_cell_remove(cell);
mutex_lock(&net->proc_cells_lock);
hlist_del_rcu(&cell->proc_link);
afs_dynroot_rmdir(net, cell);
mutex_unlock(&net->proc_cells_lock);
#ifdef CONFIG_AFS_FSCACHE
fscache_relinquish_cookie(cell->cache, NULL, false);
cell->cache = NULL;
#endif
_leave("");
}
/*
* Manage a cell record, initialising and destroying it, maintaining its DNS
* records.
*/
static void afs_manage_cell(struct work_struct *work)
{
struct afs_cell *cell = container_of(work, struct afs_cell, manager);
struct afs_net *net = cell->net;
bool deleted;
int ret, usage;
_enter("%s", cell->name);
again:
_debug("state %u", cell->state);
switch (cell->state) {
case AFS_CELL_INACTIVE:
case AFS_CELL_FAILED:
write_seqlock(&net->cells_lock);
usage = 1;
deleted = atomic_try_cmpxchg_relaxed(&cell->usage, &usage, 0);
if (deleted)
rb_erase(&cell->net_node, &net->cells);
write_sequnlock(&net->cells_lock);
if (deleted)
goto final_destruction;
if (cell->state == AFS_CELL_FAILED)
goto done;
cell->state = AFS_CELL_UNSET;
goto again;
case AFS_CELL_UNSET:
cell->state = AFS_CELL_ACTIVATING;
goto again;
case AFS_CELL_ACTIVATING:
ret = afs_activate_cell(net, cell);
if (ret < 0)
goto activation_failed;
cell->state = AFS_CELL_ACTIVE;
smp_wmb();
clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags);
wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY);
goto again;
case AFS_CELL_ACTIVE:
if (atomic_read(&cell->usage) > 1) {
time64_t now = ktime_get_real_seconds();
if (cell->dns_expiry <= now && net->live)
afs_update_cell(cell);
goto done;
}
cell->state = AFS_CELL_DEACTIVATING;
goto again;
case AFS_CELL_DEACTIVATING:
set_bit(AFS_CELL_FL_NOT_READY, &cell->flags);
if (atomic_read(&cell->usage) > 1)
goto reverse_deactivation;
afs_deactivate_cell(net, cell);
cell->state = AFS_CELL_INACTIVE;
goto again;
default:
break;
}
_debug("bad state %u", cell->state);
BUG(); /* Unhandled state */
activation_failed:
cell->error = ret;
afs_deactivate_cell(net, cell);
cell->state = AFS_CELL_FAILED;
smp_wmb();
if (test_and_clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags))
wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY);
goto again;
reverse_deactivation:
cell->state = AFS_CELL_ACTIVE;
smp_wmb();
clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags);
wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY);
_leave(" [deact->act]");
return;
done:
_leave(" [done %u]", cell->state);
return;
final_destruction:
call_rcu(&cell->rcu, afs_cell_destroy);
afs_dec_cells_outstanding(net);
_leave(" [destruct %d]", atomic_read(&net->cells_outstanding));
}
/*
* Manage the records of cells known to a network namespace. This includes
* updating the DNS records and garbage collecting unused cells that were
* automatically added.
*
* Note that constructed cell records may only be removed from net->cells by
* this work item, so it is safe for this work item to stash a cursor pointing
* into the tree and then return to caller (provided it skips cells that are
* still under construction).
*
* Note also that we were given an increment on net->cells_outstanding by
* whoever queued us that we need to deal with before returning.
*/
void afs_manage_cells(struct work_struct *work)
{
struct afs_net *net = container_of(work, struct afs_net, cells_manager);
struct rb_node *cursor;
time64_t now = ktime_get_real_seconds(), next_manage = TIME64_MAX;
bool purging = !net->live;
_enter("");
/* Trawl the cell database looking for cells that have expired from
* lack of use and cells whose DNS results have expired and dispatch
* their managers.
*/
read_seqlock_excl(&net->cells_lock);
for (cursor = rb_first(&net->cells); cursor; cursor = rb_next(cursor)) {
struct afs_cell *cell =
rb_entry(cursor, struct afs_cell, net_node);
unsigned usage;
bool sched_cell = false;
usage = atomic_read(&cell->usage);
_debug("manage %s %u", cell->name, usage);
ASSERTCMP(usage, >=, 1);
if (purging) {
if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags))
usage = atomic_dec_return(&cell->usage);
ASSERTCMP(usage, ==, 1);
}
if (usage == 1) {
time64_t expire_at = cell->last_inactive;
if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) &&
!test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags))
expire_at += afs_cell_gc_delay;
if (purging || expire_at <= now)
sched_cell = true;
else if (expire_at < next_manage)
next_manage = expire_at;
}
if (!purging) {
if (cell->dns_expiry <= now)
sched_cell = true;
else if (cell->dns_expiry <= next_manage)
next_manage = cell->dns_expiry;
}
if (sched_cell)
queue_work(afs_wq, &cell->manager);
}
read_sequnlock_excl(&net->cells_lock);
/* Update the timer on the way out. We have to pass an increment on
* cells_outstanding in the namespace that we are in to the timer or
* the work scheduler.
*/
if (!purging && next_manage < TIME64_MAX) {
now = ktime_get_real_seconds();
if (next_manage - now <= 0) {
if (queue_work(afs_wq, &net->cells_manager))
atomic_inc(&net->cells_outstanding);
} else {
afs_set_cell_timer(net, next_manage - now);
}
}
afs_dec_cells_outstanding(net);
_leave(" [%d]", atomic_read(&net->cells_outstanding));
}
/*
* Purge in-memory cell database.
*/
void afs_cell_purge(struct afs_net *net)
{
struct afs_cell *ws;
_enter("");
write_seqlock(&net->cells_lock);
ws = rcu_access_pointer(net->ws_cell);
RCU_INIT_POINTER(net->ws_cell, NULL);
write_sequnlock(&net->cells_lock);
afs_put_cell(net, ws);
_debug("del timer");
if (del_timer_sync(&net->cells_timer))
atomic_dec(&net->cells_outstanding);
_debug("kick mgr");
afs_queue_cell_manager(net);
_debug("wait");
wait_var_event(&net->cells_outstanding,
!atomic_read(&net->cells_outstanding));
_leave("");
}