OpenCloudOS-Kernel/fs/afs/cell.c

832 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/module.h>
#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 <keys/rxrpc-type.h>
#include "internal.h"
unsigned __read_mostly afs_cell_gc_delay = 10;
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_atomic_t(&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);
continue;
}
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 *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);
}
_enter("%*.*s,%s", namelen, namelen, name, vllist);
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 23:27:45 +08:00
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);
rwlock_init(&cell->servers_lock);
INIT_LIST_HEAD(&cell->servers);
init_rwsem(&cell->vl_sem);
INIT_LIST_HEAD(&cell->vl_list);
spin_lock_init(&cell->vl_lock);
seqlock_init(&cell->vl_addrs_lock);
cell->flags = (1 << AFS_CELL_FL_NOT_READY);
for (i = 0; i < AFS_CELL_MAX_ADDRS; i++) {
struct sockaddr_rxrpc *srx = &cell->vl_addrs[i];
srx->srx_family = AF_RXRPC;
srx->srx_service = VL_SERVICE;
srx->transport_type = SOCK_DGRAM;
srx->transport.sin6.sin6_family = AF_INET6;
srx->transport.sin6.sin6_port = htons(AFS_VL_PORT);
}
/* Fill in the VL server list if we were given a list of addresses to
* use.
*/
if (vllist) {
char delim = ':';
if (strchr(vllist, ',') || !strchr(vllist, '.'))
delim = ',';
do {
struct sockaddr_rxrpc *srx = &cell->vl_addrs[cell->vl_naddrs];
if (in4_pton(vllist, -1,
(u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],
delim, &vllist)) {
srx->transport_len = sizeof(struct sockaddr_in6);
srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
} else if (in6_pton(vllist, -1,
srx->transport.sin6.sin6_addr.s6_addr,
delim, &vllist)) {
srx->transport_len = sizeof(struct sockaddr_in6);
srx->transport.sin6.sin6_family = AF_INET6;
} else {
goto bad_address;
}
cell->vl_naddrs++;
if (!*vllist)
break;
vllist++;
} while (cell->vl_naddrs < AFS_CELL_MAX_ADDRS && vllist);
/* Disable DNS refresh for manually-specified cells */
cell->dns_expiry = TIME64_MAX;
} else {
/* We're going to need to 'refresh' this cell's VL server list
* from the DNS before we can use it.
*/
cell->dns_expiry = S64_MIN;
}
_leave(" = %p", cell);
return cell;
bad_address:
printk(KERN_ERR "kAFS: bad VL server IP address\n");
ret = -EINVAL;
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 23:27:45 +08:00
* @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)) {
if (excl) {
afs_put_cell(net, cell);
return ERR_PTR(-EEXIST);
}
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 {
ASSERTCMP(atomic_read(&cursor->usage), >=, 1);
afs_get_cell(cursor);
ret = 0;
}
write_sequnlock(&net->cells_lock);
kfree(candidate);
if (ret == 0)
goto wait_for_cell;
error:
afs_put_cell(net, cell);
_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);
}
set_bit(AFS_CELL_FL_NO_GC, &new_root->flags);
afs_get_cell(new_root);
/* install the new cell */
write_seqlock(&net->cells_lock);
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 23:27:45 +08:00
old_root = net->ws_cell;
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)
{
time64_t now, expiry;
char *vllist = NULL;
int ret;
_enter("%s", cell->name);
ret = dns_query("afsdb", cell->name, cell->name_len,
"ipv4", &vllist, &expiry);
_debug("query %d", ret);
switch (ret) {
case 0 ... INT_MAX:
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
clear_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
goto parse_dns_data;
case -ENODATA:
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
cell->dns_expiry = ktime_get_real_seconds() + 61;
cell->error = -EDESTADDRREQ;
goto out;
case -EAGAIN:
case -ECONNREFUSED:
default:
/* Unable to query DNS. */
set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = ktime_get_real_seconds() + 10;
cell->error = -EDESTADDRREQ;
goto out;
}
parse_dns_data:
write_seqlock(&cell->vl_addrs_lock);
ret = -EINVAL;
do {
struct sockaddr_rxrpc *srx = &cell->vl_addrs[cell->vl_naddrs];
if (in4_pton(vllist, -1,
(u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],
',', (const char **)&vllist)) {
srx->transport_len = sizeof(struct sockaddr_in6);
srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
} else if (in6_pton(vllist, -1,
srx->transport.sin6.sin6_addr.s6_addr,
',', (const char **)&vllist)) {
srx->transport_len = sizeof(struct sockaddr_in6);
srx->transport.sin6.sin6_family = AF_INET6;
} else {
goto bad_address;
}
cell->vl_naddrs++;
if (!*vllist)
break;
vllist++;
} while (cell->vl_naddrs < AFS_CELL_MAX_ADDRS);
if (cell->vl_naddrs < AFS_CELL_MAX_ADDRS)
memset(cell->vl_addrs + cell->vl_naddrs, 0,
(AFS_CELL_MAX_ADDRS - cell->vl_naddrs) * sizeof(cell->vl_addrs[0]));
now = ktime_get_real_seconds();
cell->dns_expiry = expiry;
afs_set_cell_timer(cell->net, expiry - now);
bad_address:
write_sequnlock(&cell->vl_addrs_lock);
out:
_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);
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);
}
/*
* 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)
{
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, true);
#endif
ret = afs_proc_cell_setup(net, cell);
if (ret < 0)
return ret;
spin_lock(&net->proc_cells_lock);
list_add_tail(&cell->proc_link, &net->proc_cells);
spin_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: 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 23:27:45 +08:00
afs_proc_cell_remove(net, cell);
spin_lock(&net->proc_cells_lock);
list_del_init(&cell->proc_link);
spin_unlock(&net->proc_cells_lock);
#ifdef CONFIG_AFS_FSCACHE
fscache_relinquish_cookie(cell->cache, 0);
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 = net->ws_cell;
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_on_atomic_t(&net->cells_outstanding, atomic_t_wait,
TASK_UNINTERRUPTIBLE);
_leave("");
}