forked from luck/tmp_suning_uos_patched
f044c8847b
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>
324 lines
7.8 KiB
C
324 lines
7.8 KiB
C
/* AFS server record management
|
|
*
|
|
* Copyright (C) 2002, 2007 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/sched.h>
|
|
#include <linux/slab.h>
|
|
#include "internal.h"
|
|
|
|
static unsigned afs_server_timeout = 10; /* server timeout in seconds */
|
|
|
|
/*
|
|
* install a server record in the master tree
|
|
*/
|
|
static int afs_install_server(struct afs_server *server)
|
|
{
|
|
struct afs_server *xserver;
|
|
struct afs_net *net = server->cell->net;
|
|
struct rb_node **pp, *p;
|
|
int ret;
|
|
|
|
_enter("%p", server);
|
|
|
|
write_lock(&net->servers_lock);
|
|
|
|
ret = -EEXIST;
|
|
pp = &net->servers.rb_node;
|
|
p = NULL;
|
|
while (*pp) {
|
|
p = *pp;
|
|
_debug("- consider %p", p);
|
|
xserver = rb_entry(p, struct afs_server, master_rb);
|
|
if (server->addr.s_addr < xserver->addr.s_addr)
|
|
pp = &(*pp)->rb_left;
|
|
else if (server->addr.s_addr > xserver->addr.s_addr)
|
|
pp = &(*pp)->rb_right;
|
|
else
|
|
goto error;
|
|
}
|
|
|
|
rb_link_node(&server->master_rb, p, pp);
|
|
rb_insert_color(&server->master_rb, &net->servers);
|
|
ret = 0;
|
|
|
|
error:
|
|
write_unlock(&net->servers_lock);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* allocate a new server record
|
|
*/
|
|
static struct afs_server *afs_alloc_server(struct afs_cell *cell,
|
|
const struct in_addr *addr)
|
|
{
|
|
struct afs_server *server;
|
|
|
|
_enter("");
|
|
|
|
server = kzalloc(sizeof(struct afs_server), GFP_KERNEL);
|
|
if (server) {
|
|
atomic_set(&server->usage, 1);
|
|
server->cell = cell;
|
|
|
|
INIT_LIST_HEAD(&server->link);
|
|
INIT_LIST_HEAD(&server->grave);
|
|
init_rwsem(&server->sem);
|
|
spin_lock_init(&server->fs_lock);
|
|
server->fs_vnodes = RB_ROOT;
|
|
server->cb_promises = RB_ROOT;
|
|
spin_lock_init(&server->cb_lock);
|
|
init_waitqueue_head(&server->cb_break_waitq);
|
|
INIT_DELAYED_WORK(&server->cb_break_work,
|
|
afs_dispatch_give_up_callbacks);
|
|
|
|
memcpy(&server->addr, addr, sizeof(struct in_addr));
|
|
server->addr.s_addr = addr->s_addr;
|
|
_leave(" = %p{%d}", server, atomic_read(&server->usage));
|
|
} else {
|
|
_leave(" = NULL [nomem]");
|
|
}
|
|
return server;
|
|
}
|
|
|
|
/*
|
|
* get an FS-server record for a cell
|
|
*/
|
|
struct afs_server *afs_lookup_server(struct afs_cell *cell,
|
|
const struct in_addr *addr)
|
|
{
|
|
struct afs_server *server, *candidate;
|
|
|
|
_enter("%p,%pI4", cell, &addr->s_addr);
|
|
|
|
/* quick scan of the list to see if we already have the server */
|
|
read_lock(&cell->servers_lock);
|
|
|
|
list_for_each_entry(server, &cell->servers, link) {
|
|
if (server->addr.s_addr == addr->s_addr)
|
|
goto found_server_quickly;
|
|
}
|
|
read_unlock(&cell->servers_lock);
|
|
|
|
candidate = afs_alloc_server(cell, addr);
|
|
if (!candidate) {
|
|
_leave(" = -ENOMEM");
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
write_lock(&cell->servers_lock);
|
|
|
|
/* check the cell's server list again */
|
|
list_for_each_entry(server, &cell->servers, link) {
|
|
if (server->addr.s_addr == addr->s_addr)
|
|
goto found_server;
|
|
}
|
|
|
|
_debug("new");
|
|
server = candidate;
|
|
if (afs_install_server(server) < 0)
|
|
goto server_in_two_cells;
|
|
|
|
afs_get_cell(cell);
|
|
list_add_tail(&server->link, &cell->servers);
|
|
|
|
write_unlock(&cell->servers_lock);
|
|
_leave(" = %p{%d}", server, atomic_read(&server->usage));
|
|
return server;
|
|
|
|
/* found a matching server quickly */
|
|
found_server_quickly:
|
|
_debug("found quickly");
|
|
afs_get_server(server);
|
|
read_unlock(&cell->servers_lock);
|
|
no_longer_unused:
|
|
if (!list_empty(&server->grave)) {
|
|
spin_lock(&cell->net->server_graveyard_lock);
|
|
list_del_init(&server->grave);
|
|
spin_unlock(&cell->net->server_graveyard_lock);
|
|
}
|
|
_leave(" = %p{%d}", server, atomic_read(&server->usage));
|
|
return server;
|
|
|
|
/* found a matching server on the second pass */
|
|
found_server:
|
|
_debug("found");
|
|
afs_get_server(server);
|
|
write_unlock(&cell->servers_lock);
|
|
kfree(candidate);
|
|
goto no_longer_unused;
|
|
|
|
/* found a server that seems to be in two cells */
|
|
server_in_two_cells:
|
|
write_unlock(&cell->servers_lock);
|
|
kfree(candidate);
|
|
printk(KERN_NOTICE "kAFS: Server %pI4 appears to be in two cells\n",
|
|
addr);
|
|
_leave(" = -EEXIST");
|
|
return ERR_PTR(-EEXIST);
|
|
}
|
|
|
|
/*
|
|
* look up a server by its IP address
|
|
*/
|
|
struct afs_server *afs_find_server(struct afs_net *net,
|
|
const struct sockaddr_rxrpc *srx)
|
|
{
|
|
struct afs_server *server = NULL;
|
|
struct rb_node *p;
|
|
struct in_addr addr = srx->transport.sin.sin_addr;
|
|
|
|
_enter("{%d,%pI4}", srx->transport.family, &addr.s_addr);
|
|
|
|
if (srx->transport.family != AF_INET) {
|
|
WARN(true, "AFS does not yes support non-IPv4 addresses\n");
|
|
return NULL;
|
|
}
|
|
|
|
read_lock(&net->servers_lock);
|
|
|
|
p = net->servers.rb_node;
|
|
while (p) {
|
|
server = rb_entry(p, struct afs_server, master_rb);
|
|
|
|
_debug("- consider %p", p);
|
|
|
|
if (addr.s_addr < server->addr.s_addr) {
|
|
p = p->rb_left;
|
|
} else if (addr.s_addr > server->addr.s_addr) {
|
|
p = p->rb_right;
|
|
} else {
|
|
afs_get_server(server);
|
|
goto found;
|
|
}
|
|
}
|
|
|
|
server = NULL;
|
|
found:
|
|
read_unlock(&net->servers_lock);
|
|
ASSERTIFCMP(server, server->addr.s_addr, ==, addr.s_addr);
|
|
_leave(" = %p", server);
|
|
return server;
|
|
}
|
|
|
|
/*
|
|
* destroy a server record
|
|
* - removes from the cell list
|
|
*/
|
|
void afs_put_server(struct afs_server *server)
|
|
{
|
|
struct afs_net *net = server->cell->net;
|
|
|
|
if (!server)
|
|
return;
|
|
|
|
_enter("%p{%d}", server, atomic_read(&server->usage));
|
|
|
|
_debug("PUT SERVER %d", atomic_read(&server->usage));
|
|
|
|
ASSERTCMP(atomic_read(&server->usage), >, 0);
|
|
|
|
if (likely(!atomic_dec_and_test(&server->usage))) {
|
|
_leave("");
|
|
return;
|
|
}
|
|
|
|
afs_flush_callback_breaks(server);
|
|
|
|
spin_lock(&net->server_graveyard_lock);
|
|
if (atomic_read(&server->usage) == 0) {
|
|
list_move_tail(&server->grave, &net->server_graveyard);
|
|
server->time_of_death = ktime_get_real_seconds();
|
|
queue_delayed_work(afs_wq, &net->server_reaper,
|
|
net->live ? afs_server_timeout * HZ : 0);
|
|
}
|
|
spin_unlock(&net->server_graveyard_lock);
|
|
_leave(" [dead]");
|
|
}
|
|
|
|
/*
|
|
* destroy a dead server
|
|
*/
|
|
static void afs_destroy_server(struct afs_server *server)
|
|
{
|
|
_enter("%p", server);
|
|
|
|
ASSERTIF(server->cb_break_head != server->cb_break_tail,
|
|
delayed_work_pending(&server->cb_break_work));
|
|
|
|
ASSERTCMP(server->fs_vnodes.rb_node, ==, NULL);
|
|
ASSERTCMP(server->cb_promises.rb_node, ==, NULL);
|
|
ASSERTCMP(server->cb_break_head, ==, server->cb_break_tail);
|
|
ASSERTCMP(atomic_read(&server->cb_break_n), ==, 0);
|
|
|
|
afs_put_cell(server->cell);
|
|
kfree(server);
|
|
}
|
|
|
|
/*
|
|
* reap dead server records
|
|
*/
|
|
void afs_reap_server(struct work_struct *work)
|
|
{
|
|
LIST_HEAD(corpses);
|
|
struct afs_server *server;
|
|
struct afs_net *net = container_of(work, struct afs_net, server_reaper.work);
|
|
unsigned long delay, expiry;
|
|
time64_t now;
|
|
|
|
now = ktime_get_real_seconds();
|
|
spin_lock(&net->server_graveyard_lock);
|
|
|
|
while (!list_empty(&net->server_graveyard)) {
|
|
server = list_entry(net->server_graveyard.next,
|
|
struct afs_server, grave);
|
|
|
|
/* the queue is ordered most dead first */
|
|
if (net->live) {
|
|
expiry = server->time_of_death + afs_server_timeout;
|
|
if (expiry > now) {
|
|
delay = (expiry - now) * HZ;
|
|
mod_delayed_work(afs_wq, &net->server_reaper, delay);
|
|
break;
|
|
}
|
|
}
|
|
|
|
write_lock(&server->cell->servers_lock);
|
|
write_lock(&net->servers_lock);
|
|
if (atomic_read(&server->usage) > 0) {
|
|
list_del_init(&server->grave);
|
|
} else {
|
|
list_move_tail(&server->grave, &corpses);
|
|
list_del_init(&server->link);
|
|
rb_erase(&server->master_rb, &net->servers);
|
|
}
|
|
write_unlock(&net->servers_lock);
|
|
write_unlock(&server->cell->servers_lock);
|
|
}
|
|
|
|
spin_unlock(&net->server_graveyard_lock);
|
|
|
|
/* now reap the corpses we've extracted */
|
|
while (!list_empty(&corpses)) {
|
|
server = list_entry(corpses.next, struct afs_server, grave);
|
|
list_del(&server->grave);
|
|
afs_destroy_server(server);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Discard all the server records from a net namespace when it is destroyed or
|
|
* the afs module is removed.
|
|
*/
|
|
void __net_exit afs_purge_servers(struct afs_net *net)
|
|
{
|
|
mod_delayed_work(afs_wq, &net->server_reaper, 0);
|
|
}
|