linux/net/sunrpc/svc.c

1316 lines
31 KiB
C
Raw Normal View History

/*
* linux/net/sunrpc/svc.c
*
* High-level RPC service routines
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*
* Multiple threads pools and NUMAisation
* Copyright (c) 2006 Silicon Graphics, Inc.
* by Greg Banks <gnb@melbourne.sgi.com>
*/
#include <linux/linkage.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/kthread.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/bc_xprt.h>
#define RPCDBG_FACILITY RPCDBG_SVCDSP
static void svc_unregister(const struct svc_serv *serv);
#define svc_serv_is_pooled(serv) ((serv)->sv_function)
/*
* Mode for mapping cpus to pools.
*/
enum {
SVC_POOL_AUTO = -1, /* choose one of the others */
SVC_POOL_GLOBAL, /* no mapping, just a single global pool
* (legacy & UP mode) */
SVC_POOL_PERCPU, /* one pool per cpu */
SVC_POOL_PERNODE /* one pool per numa node */
};
#define SVC_POOL_DEFAULT SVC_POOL_GLOBAL
/*
* Structure for mapping cpus to pools and vice versa.
* Setup once during sunrpc initialisation.
*/
static struct svc_pool_map {
int count; /* How many svc_servs use us */
int mode; /* Note: int not enum to avoid
* warnings about "enumeration value
* not handled in switch" */
unsigned int npools;
unsigned int *pool_to; /* maps pool id to cpu or node */
unsigned int *to_pool; /* maps cpu or node to pool id */
} svc_pool_map = {
.count = 0,
.mode = SVC_POOL_DEFAULT
};
static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
static int
param_set_pool_mode(const char *val, struct kernel_param *kp)
{
int *ip = (int *)kp->arg;
struct svc_pool_map *m = &svc_pool_map;
int err;
mutex_lock(&svc_pool_map_mutex);
err = -EBUSY;
if (m->count)
goto out;
err = 0;
if (!strncmp(val, "auto", 4))
*ip = SVC_POOL_AUTO;
else if (!strncmp(val, "global", 6))
*ip = SVC_POOL_GLOBAL;
else if (!strncmp(val, "percpu", 6))
*ip = SVC_POOL_PERCPU;
else if (!strncmp(val, "pernode", 7))
*ip = SVC_POOL_PERNODE;
else
err = -EINVAL;
out:
mutex_unlock(&svc_pool_map_mutex);
return err;
}
static int
param_get_pool_mode(char *buf, struct kernel_param *kp)
{
int *ip = (int *)kp->arg;
switch (*ip)
{
case SVC_POOL_AUTO:
return strlcpy(buf, "auto", 20);
case SVC_POOL_GLOBAL:
return strlcpy(buf, "global", 20);
case SVC_POOL_PERCPU:
return strlcpy(buf, "percpu", 20);
case SVC_POOL_PERNODE:
return strlcpy(buf, "pernode", 20);
default:
return sprintf(buf, "%d", *ip);
}
}
module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode,
&svc_pool_map.mode, 0644);
/*
* Detect best pool mapping mode heuristically,
* according to the machine's topology.
*/
static int
svc_pool_map_choose_mode(void)
{
unsigned int node;
if (nr_online_nodes > 1) {
/*
* Actually have multiple NUMA nodes,
* so split pools on NUMA node boundaries
*/
return SVC_POOL_PERNODE;
}
node = first_online_node;
if (nr_cpus_node(node) > 2) {
/*
* Non-trivial SMP, or CONFIG_NUMA on
* non-NUMA hardware, e.g. with a generic
* x86_64 kernel on Xeons. In this case we
* want to divide the pools on cpu boundaries.
*/
return SVC_POOL_PERCPU;
}
/* default: one global pool */
return SVC_POOL_GLOBAL;
}
/*
* Allocate the to_pool[] and pool_to[] arrays.
* Returns 0 on success or an errno.
*/
static int
svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools)
{
m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL);
if (!m->to_pool)
goto fail;
m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL);
if (!m->pool_to)
goto fail_free;
return 0;
fail_free:
kfree(m->to_pool);
fail:
return -ENOMEM;
}
/*
* Initialise the pool map for SVC_POOL_PERCPU mode.
* Returns number of pools or <0 on error.
*/
static int
svc_pool_map_init_percpu(struct svc_pool_map *m)
{
unsigned int maxpools = nr_cpu_ids;
unsigned int pidx = 0;
unsigned int cpu;
int err;
err = svc_pool_map_alloc_arrays(m, maxpools);
if (err)
return err;
for_each_online_cpu(cpu) {
BUG_ON(pidx > maxpools);
m->to_pool[cpu] = pidx;
m->pool_to[pidx] = cpu;
pidx++;
}
/* cpus brought online later all get mapped to pool0, sorry */
return pidx;
};
/*
* Initialise the pool map for SVC_POOL_PERNODE mode.
* Returns number of pools or <0 on error.
*/
static int
svc_pool_map_init_pernode(struct svc_pool_map *m)
{
unsigned int maxpools = nr_node_ids;
unsigned int pidx = 0;
unsigned int node;
int err;
err = svc_pool_map_alloc_arrays(m, maxpools);
if (err)
return err;
for_each_node_with_cpus(node) {
/* some architectures (e.g. SN2) have cpuless nodes */
BUG_ON(pidx > maxpools);
m->to_pool[node] = pidx;
m->pool_to[pidx] = node;
pidx++;
}
/* nodes brought online later all get mapped to pool0, sorry */
return pidx;
}
/*
* Add a reference to the global map of cpus to pools (and
* vice versa). Initialise the map if we're the first user.
* Returns the number of pools.
*/
static unsigned int
svc_pool_map_get(void)
{
struct svc_pool_map *m = &svc_pool_map;
int npools = -1;
mutex_lock(&svc_pool_map_mutex);
if (m->count++) {
mutex_unlock(&svc_pool_map_mutex);
return m->npools;
}
if (m->mode == SVC_POOL_AUTO)
m->mode = svc_pool_map_choose_mode();
switch (m->mode) {
case SVC_POOL_PERCPU:
npools = svc_pool_map_init_percpu(m);
break;
case SVC_POOL_PERNODE:
npools = svc_pool_map_init_pernode(m);
break;
}
if (npools < 0) {
/* default, or memory allocation failure */
npools = 1;
m->mode = SVC_POOL_GLOBAL;
}
m->npools = npools;
mutex_unlock(&svc_pool_map_mutex);
return m->npools;
}
/*
* Drop a reference to the global map of cpus to pools.
* When the last reference is dropped, the map data is
* freed; this allows the sysadmin to change the pool
* mode using the pool_mode module option without
* rebooting or re-loading sunrpc.ko.
*/
static void
svc_pool_map_put(void)
{
struct svc_pool_map *m = &svc_pool_map;
mutex_lock(&svc_pool_map_mutex);
if (!--m->count) {
m->mode = SVC_POOL_DEFAULT;
kfree(m->to_pool);
kfree(m->pool_to);
m->npools = 0;
}
mutex_unlock(&svc_pool_map_mutex);
}
/*
* Set the given thread's cpus_allowed mask so that it
* will only run on cpus in the given pool.
*/
static inline void
svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
{
struct svc_pool_map *m = &svc_pool_map;
unsigned int node = m->pool_to[pidx];
/*
* The caller checks for sv_nrpools > 1, which
* implies that we've been initialized.
*/
BUG_ON(m->count == 0);
switch (m->mode) {
case SVC_POOL_PERCPU:
{
set_cpus_allowed_ptr(task, cpumask_of(node));
break;
}
case SVC_POOL_PERNODE:
{
set_cpus_allowed_ptr(task, cpumask_of_node(node));
break;
}
}
}
/*
* Use the mapping mode to choose a pool for a given CPU.
* Used when enqueueing an incoming RPC. Always returns
* a non-NULL pool pointer.
*/
struct svc_pool *
svc_pool_for_cpu(struct svc_serv *serv, int cpu)
{
struct svc_pool_map *m = &svc_pool_map;
unsigned int pidx = 0;
/*
* An uninitialised map happens in a pure client when
* lockd is brought up, so silently treat it the
* same as SVC_POOL_GLOBAL.
*/
if (svc_serv_is_pooled(serv)) {
switch (m->mode) {
case SVC_POOL_PERCPU:
pidx = m->to_pool[cpu];
break;
case SVC_POOL_PERNODE:
pidx = m->to_pool[cpu_to_node(cpu)];
break;
}
}
return &serv->sv_pools[pidx % serv->sv_nrpools];
}
/*
* Create an RPC service
*/
static struct svc_serv *
__svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
void (*shutdown)(struct svc_serv *serv))
{
struct svc_serv *serv;
unsigned int vers;
unsigned int xdrsize;
unsigned int i;
if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL)))
return NULL;
serv->sv_name = prog->pg_name;
serv->sv_program = prog;
serv->sv_nrthreads = 1;
serv->sv_stats = prog->pg_stats;
if (bufsize > RPCSVC_MAXPAYLOAD)
bufsize = RPCSVC_MAXPAYLOAD;
serv->sv_max_payload = bufsize? bufsize : 4096;
serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE);
serv->sv_shutdown = shutdown;
xdrsize = 0;
while (prog) {
prog->pg_lovers = prog->pg_nvers-1;
for (vers=0; vers<prog->pg_nvers ; vers++)
if (prog->pg_vers[vers]) {
prog->pg_hivers = vers;
if (prog->pg_lovers > vers)
prog->pg_lovers = vers;
if (prog->pg_vers[vers]->vs_xdrsize > xdrsize)
xdrsize = prog->pg_vers[vers]->vs_xdrsize;
}
prog = prog->pg_next;
}
serv->sv_xdrsize = xdrsize;
INIT_LIST_HEAD(&serv->sv_tempsocks);
INIT_LIST_HEAD(&serv->sv_permsocks);
init_timer(&serv->sv_temptimer);
spin_lock_init(&serv->sv_lock);
serv->sv_nrpools = npools;
serv->sv_pools =
kcalloc(serv->sv_nrpools, sizeof(struct svc_pool),
GFP_KERNEL);
if (!serv->sv_pools) {
kfree(serv);
return NULL;
}
for (i = 0; i < serv->sv_nrpools; i++) {
struct svc_pool *pool = &serv->sv_pools[i];
dprintk("svc: initialising pool %u for %s\n",
i, serv->sv_name);
pool->sp_id = i;
INIT_LIST_HEAD(&pool->sp_threads);
INIT_LIST_HEAD(&pool->sp_sockets);
INIT_LIST_HEAD(&pool->sp_all_threads);
spin_lock_init(&pool->sp_lock);
}
/* Remove any stale portmap registrations */
svc_unregister(serv);
return serv;
}
struct svc_serv *
svc_create(struct svc_program *prog, unsigned int bufsize,
void (*shutdown)(struct svc_serv *serv))
{
return __svc_create(prog, bufsize, /*npools*/1, shutdown);
}
EXPORT_SYMBOL_GPL(svc_create);
struct svc_serv *
svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
void (*shutdown)(struct svc_serv *serv),
svc_thread_fn func, struct module *mod)
{
struct svc_serv *serv;
unsigned int npools = svc_pool_map_get();
serv = __svc_create(prog, bufsize, npools, shutdown);
if (serv != NULL) {
serv->sv_function = func;
serv->sv_module = mod;
}
return serv;
}
EXPORT_SYMBOL_GPL(svc_create_pooled);
/*
* Destroy an RPC service. Should be called with appropriate locking to
* protect the sv_nrthreads, sv_permsocks and sv_tempsocks.
*/
void
svc_destroy(struct svc_serv *serv)
{
dprintk("svc: svc_destroy(%s, %d)\n",
serv->sv_program->pg_name,
serv->sv_nrthreads);
if (serv->sv_nrthreads) {
if (--(serv->sv_nrthreads) != 0) {
svc_sock_update_bufs(serv);
return;
}
} else
printk("svc_destroy: no threads for serv=%p!\n", serv);
del_timer_sync(&serv->sv_temptimer);
svc_close_all(&serv->sv_tempsocks);
if (serv->sv_shutdown)
serv->sv_shutdown(serv);
svc_close_all(&serv->sv_permsocks);
BUG_ON(!list_empty(&serv->sv_permsocks));
BUG_ON(!list_empty(&serv->sv_tempsocks));
cache_clean_deferred(serv);
if (svc_serv_is_pooled(serv))
svc_pool_map_put();
svc_unregister(serv);
kfree(serv->sv_pools);
kfree(serv);
}
EXPORT_SYMBOL_GPL(svc_destroy);
/*
* Allocate an RPC server's buffer space.
* We allocate pages and place them in rq_argpages.
*/
static int
svc_init_buffer(struct svc_rqst *rqstp, unsigned int size)
{
unsigned int pages, arghi;
/* bc_xprt uses fore channel allocated buffers */
if (svc_is_backchannel(rqstp))
return 1;
pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply.
* We assume one is at most one page
*/
arghi = 0;
BUG_ON(pages > RPCSVC_MAXPAGES);
while (pages) {
struct page *p = alloc_page(GFP_KERNEL);
if (!p)
break;
rqstp->rq_pages[arghi++] = p;
pages--;
}
return pages == 0;
}
/*
* Release an RPC server buffer
*/
static void
svc_release_buffer(struct svc_rqst *rqstp)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(rqstp->rq_pages); i++)
if (rqstp->rq_pages[i])
put_page(rqstp->rq_pages[i]);
}
struct svc_rqst *
svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool)
{
struct svc_rqst *rqstp;
rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
if (!rqstp)
goto out_enomem;
init_waitqueue_head(&rqstp->rq_wait);
serv->sv_nrthreads++;
spin_lock_bh(&pool->sp_lock);
pool->sp_nrthreads++;
list_add(&rqstp->rq_all, &pool->sp_all_threads);
spin_unlock_bh(&pool->sp_lock);
rqstp->rq_server = serv;
rqstp->rq_pool = pool;
rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
if (!rqstp->rq_argp)
goto out_thread;
rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
if (!rqstp->rq_resp)
goto out_thread;
if (!svc_init_buffer(rqstp, serv->sv_max_mesg))
goto out_thread;
return rqstp;
out_thread:
svc_exit_thread(rqstp);
out_enomem:
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(svc_prepare_thread);
/*
* Choose a pool in which to create a new thread, for svc_set_num_threads
*/
static inline struct svc_pool *
choose_pool(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
{
if (pool != NULL)
return pool;
return &serv->sv_pools[(*state)++ % serv->sv_nrpools];
}
/*
* Choose a thread to kill, for svc_set_num_threads
*/
static inline struct task_struct *
choose_victim(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state)
{
unsigned int i;
struct task_struct *task = NULL;
if (pool != NULL) {
spin_lock_bh(&pool->sp_lock);
} else {
/* choose a pool in round-robin fashion */
for (i = 0; i < serv->sv_nrpools; i++) {
pool = &serv->sv_pools[--(*state) % serv->sv_nrpools];
spin_lock_bh(&pool->sp_lock);
if (!list_empty(&pool->sp_all_threads))
goto found_pool;
spin_unlock_bh(&pool->sp_lock);
}
return NULL;
}
found_pool:
if (!list_empty(&pool->sp_all_threads)) {
struct svc_rqst *rqstp;
/*
* Remove from the pool->sp_all_threads list
* so we don't try to kill it again.
*/
rqstp = list_entry(pool->sp_all_threads.next, struct svc_rqst, rq_all);
list_del_init(&rqstp->rq_all);
task = rqstp->rq_task;
}
spin_unlock_bh(&pool->sp_lock);
return task;
}
/*
* Create or destroy enough new threads to make the number
* of threads the given number. If `pool' is non-NULL, applies
* only to threads in that pool, otherwise round-robins between
* all pools. Must be called with a svc_get() reference and
* the BKL or another lock to protect access to svc_serv fields.
*
* Destroying threads relies on the service threads filling in
* rqstp->rq_task, which only the nfs ones do. Assumes the serv
* has been created using svc_create_pooled().
*
* Based on code that used to be in nfsd_svc() but tweaked
* to be pool-aware.
*/
int
svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
struct svc_rqst *rqstp;
struct task_struct *task;
struct svc_pool *chosen_pool;
int error = 0;
unsigned int state = serv->sv_nrthreads-1;
if (pool == NULL) {
/* The -1 assumes caller has done a svc_get() */
nrservs -= (serv->sv_nrthreads-1);
} else {
spin_lock_bh(&pool->sp_lock);
nrservs -= pool->sp_nrthreads;
spin_unlock_bh(&pool->sp_lock);
}
/* create new threads */
while (nrservs > 0) {
nrservs--;
chosen_pool = choose_pool(serv, pool, &state);
rqstp = svc_prepare_thread(serv, chosen_pool);
if (IS_ERR(rqstp)) {
error = PTR_ERR(rqstp);
break;
}
__module_get(serv->sv_module);
task = kthread_create(serv->sv_function, rqstp, serv->sv_name);
if (IS_ERR(task)) {
error = PTR_ERR(task);
module_put(serv->sv_module);
svc_exit_thread(rqstp);
break;
}
rqstp->rq_task = task;
if (serv->sv_nrpools > 1)
svc_pool_map_set_cpumask(task, chosen_pool->sp_id);
svc_sock_update_bufs(serv);
wake_up_process(task);
}
/* destroy old threads */
while (nrservs < 0 &&
(task = choose_victim(serv, pool, &state)) != NULL) {
send_sig(SIGINT, task, 1);
nrservs++;
}
return error;
}
EXPORT_SYMBOL_GPL(svc_set_num_threads);
/*
* Called from a server thread as it's exiting. Caller must hold the BKL or
* the "service mutex", whichever is appropriate for the service.
*/
void
svc_exit_thread(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
struct svc_pool *pool = rqstp->rq_pool;
svc_release_buffer(rqstp);
kfree(rqstp->rq_resp);
kfree(rqstp->rq_argp);
kfree(rqstp->rq_auth_data);
spin_lock_bh(&pool->sp_lock);
pool->sp_nrthreads--;
list_del(&rqstp->rq_all);
spin_unlock_bh(&pool->sp_lock);
kfree(rqstp);
/* Release the server */
if (serv)
svc_destroy(serv);
}
EXPORT_SYMBOL_GPL(svc_exit_thread);
/*
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
* Register an "inet" protocol family netid with the local
* rpcbind daemon via an rpcbind v4 SET request.
*
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
* No netconfig infrastructure is available in the kernel, so
* we map IP_ protocol numbers to netids by hand.
*
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
static int __svc_rpcb_register4(const u32 program, const u32 version,
const unsigned short protocol,
const unsigned short port)
{
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
const struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
const char *netid;
int error;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
switch (protocol) {
case IPPROTO_UDP:
netid = RPCBIND_NETID_UDP;
break;
case IPPROTO_TCP:
netid = RPCBIND_NETID_TCP;
break;
default:
return -ENOPROTOOPT;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
}
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
error = rpcb_v4_register(program, version,
(const struct sockaddr *)&sin, netid);
/*
* User space didn't support rpcbind v4, so retry this
* registration request with the legacy rpcbind v2 protocol.
*/
if (error == -EPROTONOSUPPORT)
error = rpcb_register(program, version, protocol, port);
return error;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
}
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
/*
* Register an "inet6" protocol family netid with the local
* rpcbind daemon via an rpcbind v4 SET request.
*
* No netconfig infrastructure is available in the kernel, so
* we map IP_ protocol numbers to netids by hand.
*
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
static int __svc_rpcb_register6(const u32 program, const u32 version,
const unsigned short protocol,
const unsigned short port)
{
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
const struct sockaddr_in6 sin6 = {
.sin6_family = AF_INET6,
.sin6_addr = IN6ADDR_ANY_INIT,
.sin6_port = htons(port),
};
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
const char *netid;
int error;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
switch (protocol) {
case IPPROTO_UDP:
netid = RPCBIND_NETID_UDP6;
break;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
case IPPROTO_TCP:
netid = RPCBIND_NETID_TCP6;
break;
default:
return -ENOPROTOOPT;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
}
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
error = rpcb_v4_register(program, version,
(const struct sockaddr *)&sin6, netid);
/*
* User space didn't support rpcbind version 4, so we won't
* use a PF_INET6 listener.
*/
if (error == -EPROTONOSUPPORT)
error = -EAFNOSUPPORT;
return error;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
}
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
/*
* Register a kernel RPC service via rpcbind version 4.
*
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
static int __svc_register(const char *progname,
const u32 program, const u32 version,
const int family,
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
const unsigned short protocol,
const unsigned short port)
{
int error = -EAFNOSUPPORT;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
switch (family) {
case PF_INET:
error = __svc_rpcb_register4(program, version,
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
protocol, port);
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
break;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
case PF_INET6:
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
error = __svc_rpcb_register6(program, version,
protocol, port);
SUNRPC: Simplify kernel RPC service registration The kernel registers RPC services with the local portmapper with an rpcbind SET upcall to the local portmapper. Traditionally, this used rpcbind v2 (PMAP), but registering RPC services that support IPv6 requires rpcbind v3 or v4. Since we now want separate PF_INET and PF_INET6 listeners for each kernel RPC service, svc_register() will do only one of those registrations at a time. For PF_INET, it tries an rpcb v4 SET upcall first; if that fails, it does a legacy portmap SET. This makes it entirely backwards compatible with legacy user space, but allows a proper v4 SET to be used if rpcbind is available. For PF_INET6, it does an rpcb v4 SET upcall. If that fails, it fails the registration, and thus the transport creation. This let's the kernel detect if user space is able to support IPv6 RPC services, and thus whether it should maintain a PF_INET6 listener for each service at all. This provides complete backwards compatibilty with legacy user space that only supports rpcbind v2. The only down-side is that registering a new kernel RPC service may take an extra exchange with the local portmapper on legacy systems, but this is an infrequent operation and is done over UDP (no lingering sockets in TIMEWAIT), so it shouldn't be consequential. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256 Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-03-19 00:47:36 +00:00
#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
}
if (error < 0)
printk(KERN_WARNING "svc: failed to register %sv%u RPC "
"service (errno %d).\n", progname, version, -error);
return error;
}
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
/**
* svc_register - register an RPC service with the local portmapper
* @serv: svc_serv struct for the service to register
* @family: protocol family of service's listener socket
* @proto: transport protocol number to advertise
* @port: port to advertise
*
* Service is registered for any address in the passed-in protocol family
*/
int svc_register(const struct svc_serv *serv, const int family,
const unsigned short proto, const unsigned short port)
{
struct svc_program *progp;
unsigned int i;
int error = 0;
BUG_ON(proto == 0 && port == 0);
for (progp = serv->sv_program; progp; progp = progp->pg_next) {
for (i = 0; i < progp->pg_nvers; i++) {
if (progp->pg_vers[i] == NULL)
continue;
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
dprintk("svc: svc_register(%sv%d, %s, %u, %u)%s\n",
progp->pg_name,
SUNRPC: Register both netids for AF_INET6 servers TI-RPC is a user-space library of RPC functions that replaces ONC RPC and allows RPC to operate in the new world of IPv6. TI-RPC combines the concept of a transport protocol (UDP and TCP) and a protocol family (PF_INET and PF_INET6) into a single identifier called a "netid." For example, "udp" means UDP over IPv4, and "udp6" means UDP over IPv6. For rpcbind, then, the RPC service tuple that is registered and advertised is: [RPC program, RPC version, service address and port, netid] instead of [RPC program, RPC version, port, protocol] Service address is typically ANYADDR, but can be a specific address of one of the interfaces on a multi-homed host. The third item in the new tuple is expressed as a universal address. The current Linux rpcbind implementation registers a netid for both protocol families when RPCB_SET is done for just the PF_INET6 version of the netid (ie udp6 or tcp6). So registering "udp6" causes a registration for "udp" to appear automatically as well. We've recently determined that this is incorrect behavior. In the TI-RPC world, "udp6" is not meant to imply that the registered RPC service handles requests from AF_INET as well, even if the listener socket does address mapping. "udp" and "udp6" are entirely separate capabilities, and must be registered separately. The Linux kernel, unlike TI-RPC, leverages address mapping to allow a single listener socket to handle requests for both AF_INET and AF_INET6. This is still OK, but the kernel currently assumes registering "udp6" will cover "udp" as well. It registers only "udp6" for it's AF_INET6 services, even though they handle both AF_INET and AF_INET6 on the same port. So svc_register() actually needs to register both "udp" and "udp6" explicitly (and likewise for TCP). Until rpcbind is fixed, the kernel can ignore the return code for the second RPCB_SET call. Please merge this with commit 15231312: SUNRPC: Support IPv6 when registering kernel RPC services Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Cc: Olaf Kirch <okir@suse.de> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2008-09-15 21:27:23 +00:00
i,
proto == IPPROTO_UDP? "udp" : "tcp",
port,
family,
progp->pg_vers[i]->vs_hidden?
" (but not telling portmap)" : "");
if (progp->pg_vers[i]->vs_hidden)
continue;
error = __svc_register(progp->pg_name, progp->pg_prog,
i, family, proto, port);
if (error < 0)
break;
}
}
return error;
}
/*
* If user space is running rpcbind, it should take the v4 UNSET
* and clear everything for this [program, version]. If user space
* is running portmap, it will reject the v4 UNSET, but won't have
* any "inet6" entries anyway. So a PMAP_UNSET should be sufficient
* in this case to clear all existing entries for [program, version].
*/
static void __svc_unregister(const u32 program, const u32 version,
const char *progname)
{
int error;
error = rpcb_v4_register(program, version, NULL, "");
/*
* User space didn't support rpcbind v4, so retry this
* request with the legacy rpcbind v2 protocol.
*/
if (error == -EPROTONOSUPPORT)
error = rpcb_register(program, version, 0, 0);
dprintk("svc: %s(%sv%u), error %d\n",
__func__, progname, version, error);
}
/*
* All netids, bind addresses and ports registered for [program, version]
* are removed from the local rpcbind database (if the service is not
* hidden) to make way for a new instance of the service.
*
* The result of unregistration is reported via dprintk for those who want
* verification of the result, but is otherwise not important.
*/
static void svc_unregister(const struct svc_serv *serv)
{
struct svc_program *progp;
unsigned long flags;
unsigned int i;
clear_thread_flag(TIF_SIGPENDING);
for (progp = serv->sv_program; progp; progp = progp->pg_next) {
for (i = 0; i < progp->pg_nvers; i++) {
if (progp->pg_vers[i] == NULL)
continue;
if (progp->pg_vers[i]->vs_hidden)
continue;
__svc_unregister(progp->pg_prog, i, progp->pg_name);
}
}
spin_lock_irqsave(&current->sighand->siglock, flags);
recalc_sigpending();
spin_unlock_irqrestore(&current->sighand->siglock, flags);
}
/*
* Printk the given error with the address of the client that caused it.
*/
static int
__attribute__ ((format (printf, 2, 3)))
svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
{
va_list args;
int r;
char buf[RPC_MAX_ADDRBUFLEN];
if (!net_ratelimit())
return 0;
printk(KERN_WARNING "svc: %s: ",
svc_print_addr(rqstp, buf, sizeof(buf)));
va_start(args, fmt);
r = vprintk(fmt, args);
va_end(args);
return r;
}
/*
* Common routine for processing the RPC request.
*/
static int
svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
{
struct svc_program *progp;
struct svc_version *versp = NULL; /* compiler food */
struct svc_procedure *procp = NULL;
struct svc_serv *serv = rqstp->rq_server;
kxdrproc_t xdr;
__be32 *statp;
u32 prog, vers, proc;
__be32 auth_stat, rpc_stat;
int auth_res;
__be32 *reply_statp;
rpc_stat = rpc_success;
if (argv->iov_len < 6*4)
goto err_short_len;
/* Will be turned off only in gss privacy case: */
rqstp->rq_splice_ok = 1;
/* Will be turned off only when NFSv4 Sessions are used */
rqstp->rq_usedeferral = 1;
rqstp->rq_dropme = false;
/* Setup reply header */
rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
svc_putu32(resv, rqstp->rq_xid);
vers = svc_getnl(argv);
/* First words of reply: */
svc_putnl(resv, 1); /* REPLY */
if (vers != 2) /* RPC version number */
goto err_bad_rpc;
/* Save position in case we later decide to reject: */
reply_statp = resv->iov_base + resv->iov_len;
svc_putnl(resv, 0); /* ACCEPT */
rqstp->rq_prog = prog = svc_getnl(argv); /* program number */
rqstp->rq_vers = vers = svc_getnl(argv); /* version number */
rqstp->rq_proc = proc = svc_getnl(argv); /* procedure number */
progp = serv->sv_program;
for (progp = serv->sv_program; progp; progp = progp->pg_next)
if (prog == progp->pg_prog)
break;
/*
* Decode auth data, and add verifier to reply buffer.
* We do this before anything else in order to get a decent
* auth verifier.
*/
auth_res = svc_authenticate(rqstp, &auth_stat);
/* Also give the program a chance to reject this call: */
if (auth_res == SVC_OK && progp) {
auth_stat = rpc_autherr_badcred;
auth_res = progp->pg_authenticate(rqstp);
}
switch (auth_res) {
case SVC_OK:
break;
case SVC_GARBAGE:
goto err_garbage;
case SVC_SYSERR:
rpc_stat = rpc_system_err;
goto err_bad;
case SVC_DENIED:
goto err_bad_auth;
case SVC_CLOSE:
if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
svc_close_xprt(rqstp->rq_xprt);
case SVC_DROP:
goto dropit;
case SVC_COMPLETE:
goto sendit;
}
if (progp == NULL)
goto err_bad_prog;
if (vers >= progp->pg_nvers ||
!(versp = progp->pg_vers[vers]))
goto err_bad_vers;
procp = versp->vs_proc + proc;
if (proc >= versp->vs_nproc || !procp->pc_func)
goto err_bad_proc;
rqstp->rq_procinfo = procp;
/* Syntactic check complete */
serv->sv_stats->rpccnt++;
/* Build the reply header. */
statp = resv->iov_base +resv->iov_len;
svc_putnl(resv, RPC_SUCCESS);
/* Bump per-procedure stats counter */
procp->pc_count++;
/* Initialize storage for argp and resp */
memset(rqstp->rq_argp, 0, procp->pc_argsize);
memset(rqstp->rq_resp, 0, procp->pc_ressize);
/* un-reserve some of the out-queue now that we have a
* better idea of reply size
*/
if (procp->pc_xdrressize)
RPC: add wrapper for svc_reserve to account for checksum When the kernel calls svc_reserve to downsize the expected size of an RPC reply, it fails to account for the possibility of a checksum at the end of the packet. If a client mounts a NFSv2/3 with sec=krb5i/p, and does I/O then you'll generally see messages similar to this in the server's ring buffer: RPC request reserved 164 but used 208 While I was never able to verify it, I suspect that this problem is also the root cause of some oopses I've seen under these conditions: https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=227726 This is probably also a problem for other sec= types and for NFSv4. The large reserved size for NFSv4 compound packets seems to generally paper over the problem, however. This patch adds a wrapper for svc_reserve that accounts for the possibility of a checksum. It also fixes up the appropriate callers of svc_reserve to call the wrapper. For now, it just uses a hardcoded value that I determined via testing. That value may need to be revised upward as things change, or we may want to eventually add a new auth_op that attempts to calculate this somehow. Unfortunately, there doesn't seem to be a good way to reliably determine the expected checksum length prior to actually calculating it, particularly with schemes like spkm3. Signed-off-by: Jeff Layton <jlayton@redhat.com> Acked-by: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Acked-by: J. Bruce Fields <bfields@citi.umich.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 09:34:50 +00:00
svc_reserve_auth(rqstp, procp->pc_xdrressize<<2);
/* Call the function that processes the request. */
if (!versp->vs_dispatch) {
/* Decode arguments */
xdr = procp->pc_decode;
if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp))
goto err_garbage;
*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
/* Encode reply */
if (rqstp->rq_dropme) {
if (procp->pc_release)
procp->pc_release(rqstp, NULL, rqstp->rq_resp);
goto dropit;
}
if (*statp == rpc_success &&
(xdr = procp->pc_encode) &&
!xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
dprintk("svc: failed to encode reply\n");
/* serv->sv_stats->rpcsystemerr++; */
*statp = rpc_system_err;
}
} else {
dprintk("svc: calling dispatcher\n");
if (!versp->vs_dispatch(rqstp, statp)) {
/* Release reply info */
if (procp->pc_release)
procp->pc_release(rqstp, NULL, rqstp->rq_resp);
goto dropit;
}
}
/* Check RPC status result */
if (*statp != rpc_success)
resv->iov_len = ((void*)statp) - resv->iov_base + 4;
/* Release reply info */
if (procp->pc_release)
procp->pc_release(rqstp, NULL, rqstp->rq_resp);
if (procp->pc_encode == NULL)
goto dropit;
sendit:
if (svc_authorise(rqstp))
goto dropit;
return 1; /* Caller can now send it */
dropit:
svc_authorise(rqstp); /* doesn't hurt to call this twice */
dprintk("svc: svc_process dropit\n");
return 0;
err_short_len:
svc_printk(rqstp, "short len %Zd, dropping request\n",
argv->iov_len);
goto dropit; /* drop request */
err_bad_rpc:
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, 1); /* REJECT */
svc_putnl(resv, 0); /* RPC_MISMATCH */
svc_putnl(resv, 2); /* Only RPCv2 supported */
svc_putnl(resv, 2);
goto sendit;
err_bad_auth:
dprintk("svc: authentication failed (%d)\n", ntohl(auth_stat));
serv->sv_stats->rpcbadauth++;
/* Restore write pointer to location of accept status: */
xdr_ressize_check(rqstp, reply_statp);
svc_putnl(resv, 1); /* REJECT */
svc_putnl(resv, 1); /* AUTH_ERROR */
svc_putnl(resv, ntohl(auth_stat)); /* status */
goto sendit;
err_bad_prog:
dprintk("svc: unknown program %d\n", prog);
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, RPC_PROG_UNAVAIL);
goto sendit;
err_bad_vers:
svc_printk(rqstp, "unknown version (%d for prog %d, %s)\n",
vers, prog, progp->pg_name);
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, RPC_PROG_MISMATCH);
svc_putnl(resv, progp->pg_lovers);
svc_putnl(resv, progp->pg_hivers);
goto sendit;
err_bad_proc:
svc_printk(rqstp, "unknown procedure (%d)\n", proc);
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, RPC_PROC_UNAVAIL);
goto sendit;
err_garbage:
svc_printk(rqstp, "failed to decode args\n");
rpc_stat = rpc_garbage_args;
err_bad:
serv->sv_stats->rpcbadfmt++;
svc_putnl(resv, ntohl(rpc_stat));
goto sendit;
}
EXPORT_SYMBOL_GPL(svc_process);
/*
* Process the RPC request.
*/
int
svc_process(struct svc_rqst *rqstp)
{
struct kvec *argv = &rqstp->rq_arg.head[0];
struct kvec *resv = &rqstp->rq_res.head[0];
struct svc_serv *serv = rqstp->rq_server;
u32 dir;
/*
* Setup response xdr_buf.
* Initially it has just one page
*/
rqstp->rq_resused = 1;
resv->iov_base = page_address(rqstp->rq_respages[0]);
resv->iov_len = 0;
rqstp->rq_res.pages = rqstp->rq_respages + 1;
rqstp->rq_res.len = 0;
rqstp->rq_res.page_base = 0;
rqstp->rq_res.page_len = 0;
rqstp->rq_res.buflen = PAGE_SIZE;
rqstp->rq_res.tail[0].iov_base = NULL;
rqstp->rq_res.tail[0].iov_len = 0;
rqstp->rq_xid = svc_getu32(argv);
dir = svc_getnl(argv);
if (dir != 0) {
/* direction != CALL */
svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
serv->sv_stats->rpcbadfmt++;
svc_drop(rqstp);
return 0;
}
/* Returns 1 for send, 0 for drop */
if (svc_process_common(rqstp, argv, resv))
return svc_send(rqstp);
else {
svc_drop(rqstp);
return 0;
}
}
#if defined(CONFIG_NFS_V4_1)
/*
* Process a backchannel RPC request that arrived over an existing
* outbound connection
*/
int
bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
struct svc_rqst *rqstp)
{
struct kvec *argv = &rqstp->rq_arg.head[0];
struct kvec *resv = &rqstp->rq_res.head[0];
/* Build the svc_rqst used by the common processing routine */
rqstp->rq_xprt = serv->sv_bc_xprt;
rqstp->rq_xid = req->rq_xid;
rqstp->rq_prot = req->rq_xprt->prot;
rqstp->rq_server = serv;
rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg));
memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res));
/* reset result send buffer "put" position */
resv->iov_len = 0;
if (rqstp->rq_prot != IPPROTO_TCP) {
printk(KERN_ERR "No support for Non-TCP transports!\n");
BUG();
}
/*
* Skip the next two words because they've already been
* processed in the trasport
*/
svc_getu32(argv); /* XID */
svc_getnl(argv); /* CALLDIR */
/* Returns 1 for send, 0 for drop */
if (svc_process_common(rqstp, argv, resv)) {
memcpy(&req->rq_snd_buf, &rqstp->rq_res,
sizeof(req->rq_snd_buf));
return bc_send(req);
} else {
/* Nothing to do to drop request */
return 0;
}
}
EXPORT_SYMBOL(bc_svc_process);
#endif /* CONFIG_NFS_V4_1 */
/*
* Return (transport-specific) limit on the rpc payload.
*/
u32 svc_max_payload(const struct svc_rqst *rqstp)
{
u32 max = rqstp->rq_xprt->xpt_class->xcl_max_payload;
if (rqstp->rq_server->sv_max_payload < max)
max = rqstp->rq_server->sv_max_payload;
return max;
}
EXPORT_SYMBOL_GPL(svc_max_payload);