#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/errno.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svc_xprt.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/xprt.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <trace/events/sunrpc.h>
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
static unsigned int svc_rpc_per_connection_limit __read_mostly;
module_param(svc_rpc_per_connection_limit, uint, 0644);
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
static void svc_age_temp_xprts(struct timer_list *t);
static void svc_delete_xprt(struct svc_xprt *xprt);
static int svc_conn_age_period = 6*60;
static DEFINE_SPINLOCK(svc_xprt_class_lock);
static LIST_HEAD(svc_xprt_class_list);
int svc_reg_xprt_class(struct svc_xprt_class *xcl)
{
struct svc_xprt_class *cl;
int res = -EEXIST;
INIT_LIST_HEAD(&xcl->xcl_list);
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(cl, &svc_xprt_class_list, xcl_list) {
if (strcmp(xcl->xcl_name, cl->xcl_name) == 0)
goto out;
}
list_add_tail(&xcl->xcl_list, &svc_xprt_class_list);
res = 0;
out:
spin_unlock(&svc_xprt_class_lock);
return res;
}
EXPORT_SYMBOL_GPL(svc_reg_xprt_class);
void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
{
spin_lock(&svc_xprt_class_lock);
list_del_init(&xcl->xcl_list);
spin_unlock(&svc_xprt_class_lock);
}
EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
int svc_print_xprts(char *buf, int maxlen)
{
struct svc_xprt_class *xcl;
char tmpstr[80];
int len = 0;
buf[0] = '\0';
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
int slen;
slen = snprintf(tmpstr, sizeof(tmpstr), "%s %d\n",
xcl->xcl_name, xcl->xcl_max_payload);
if (slen >= sizeof(tmpstr) || len + slen >= maxlen)
break;
len += slen;
strcat(buf, tmpstr);
}
spin_unlock(&svc_xprt_class_lock);
return len;
}
void svc_xprt_deferred_close(struct svc_xprt *xprt)
{
if (!test_and_set_bit(XPT_CLOSE, &xprt->xpt_flags))
svc_xprt_enqueue(xprt);
}
EXPORT_SYMBOL_GPL(svc_xprt_deferred_close);
static void svc_xprt_free(struct kref *kref)
{
struct svc_xprt *xprt =
container_of(kref, struct svc_xprt, xpt_ref);
struct module *owner = xprt->xpt_class->xcl_owner;
if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags))
svcauth_unix_info_release(xprt);
put_cred(xprt->xpt_cred);
put_net_track(xprt->xpt_net, &xprt->ns_tracker);
if (xprt->xpt_bc_xprt)
xprt_put(xprt->xpt_bc_xprt);
if (xprt->xpt_bc_xps)
xprt_switch_put(xprt->xpt_bc_xps);
trace_svc_xprt_free(xprt);
xprt->xpt_ops->xpo_free(xprt);
module_put(owner);
}
void svc_xprt_put(struct svc_xprt *xprt)
{
kref_put(&xprt->xpt_ref, svc_xprt_free);
}
EXPORT_SYMBOL_GPL(svc_xprt_put);
void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl,
struct svc_xprt *xprt, struct svc_serv *serv)
{
memset(xprt, 0, sizeof(*xprt));
xprt->xpt_class = xcl;
xprt->xpt_ops = xcl->xcl_ops;
kref_init(&xprt->xpt_ref);
xprt->xpt_server = serv;
INIT_LIST_HEAD(&xprt->xpt_list);
INIT_LIST_HEAD(&xprt->xpt_ready);
INIT_LIST_HEAD(&xprt->xpt_deferred);
INIT_LIST_HEAD(&xprt->xpt_users);
mutex_init(&xprt->xpt_mutex);
spin_lock_init(&xprt->xpt_lock);
set_bit(XPT_BUSY, &xprt->xpt_flags);
xprt->xpt_net = get_net_track(net, &xprt->ns_tracker, GFP_ATOMIC);
strcpy(xprt->xpt_remotebuf, "uninitialized");
}
EXPORT_SYMBOL_GPL(svc_xprt_init);
static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
struct svc_serv *serv,
struct net *net,
const int family,
const unsigned short port,
int flags)
{
struct sockaddr_in sin = {
.sin_family = AF_INET,
.sin_addr.s_addr = htonl(INADDR_ANY),
.sin_port = htons(port),
};
#if IS_ENABLED(CONFIG_IPV6)
struct sockaddr_in6 sin6 = {
.sin6_family = AF_INET6,
.sin6_addr = IN6ADDR_ANY_INIT,
.sin6_port = htons(port),
};
#endif
struct svc_xprt *xprt;
struct sockaddr *sap;
size_t len;
switch (family) {
case PF_INET:
sap = (struct sockaddr *)&sin;
len = sizeof(sin);
break;
#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6:
sap = (struct sockaddr *)&sin6;
len = sizeof(sin6);
break;
#endif
default:
return ERR_PTR(-EAFNOSUPPORT);
}
xprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
if (IS_ERR(xprt))
trace_svc_xprt_create_err(serv->sv_program->pg_name,
xcl->xcl_name, sap, len, xprt);
return xprt;
}
void svc_xprt_received(struct svc_xprt *xprt)
{
if (!test_bit(XPT_BUSY, &xprt->xpt_flags)) {
WARN_ONCE(1, "xprt=0x%p already busy!", xprt);
return;
}
svc_xprt_get(xprt);
smp_mb__before_atomic();
clear_bit(XPT_BUSY, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
svc_xprt_put(xprt);
}
EXPORT_SYMBOL_GPL(svc_xprt_received);
void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new)
{
clear_bit(XPT_TEMP, &new->xpt_flags);
spin_lock_bh(&serv->sv_lock);
list_add(&new->xpt_list, &serv->sv_permsocks);
spin_unlock_bh(&serv->sv_lock);
svc_xprt_received(new);
}
static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
struct net *net, const int family,
const unsigned short port, int flags,
const struct cred *cred)
{
struct svc_xprt_class *xcl;
spin_lock(&svc_xprt_class_lock);
list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
struct svc_xprt *newxprt;
unsigned short newport;
if (strcmp(xprt_name, xcl->xcl_name))
continue;
if (!try_module_get(xcl->xcl_owner))
goto err;
spin_unlock(&svc_xprt_class_lock);
newxprt = __svc_xpo_create(xcl, serv, net, family, port, flags);
if (IS_ERR(newxprt)) {
module_put(xcl->xcl_owner);
return PTR_ERR(newxprt);
}
newxprt->xpt_cred = get_cred(cred);
svc_add_new_perm_xprt(serv, newxprt);
newport = svc_xprt_local_port(newxprt);
return newport;
}
err:
spin_unlock(&svc_xprt_class_lock);
return -EPROTONOSUPPORT;
}
int svc_xprt_create(struct svc_serv *serv, const char *xprt_name,
struct net *net, const int family,
const unsigned short port, int flags,
const struct cred *cred)
{
int err;
err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred);
if (err == -EPROTONOSUPPORT) {
request_module("svc%s", xprt_name);
err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred);
}
return err;
}
EXPORT_SYMBOL_GPL(svc_xprt_create);
void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt)
{
memcpy(&rqstp->rq_addr, &xprt->xpt_remote, xprt->xpt_remotelen);
rqstp->rq_addrlen = xprt->xpt_remotelen;
memcpy(&rqstp->rq_daddr, &xprt->xpt_local, xprt->xpt_locallen);
rqstp->rq_daddrlen = xprt->xpt_locallen;
}
EXPORT_SYMBOL_GPL(svc_xprt_copy_addrs);
char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len)
{
return __svc_print_addr(svc_addr(rqstp), buf, len);
}
EXPORT_SYMBOL_GPL(svc_print_addr);
static bool svc_xprt_slots_in_range(struct svc_xprt *xprt)
{
unsigned int limit = svc_rpc_per_connection_limit;
int nrqsts = atomic_read(&xprt->xpt_nr_rqsts);
return limit == 0 || (nrqsts >= 0 && nrqsts < limit);
}
static bool svc_xprt_reserve_slot(struct svc_rqst *rqstp, struct svc_xprt *xprt)
{
if (!test_bit(RQ_DATA, &rqstp->rq_flags)) {
if (!svc_xprt_slots_in_range(xprt))
return false;
atomic_inc(&xprt->xpt_nr_rqsts);
set_bit(RQ_DATA, &rqstp->rq_flags);
}
return true;
}
static void svc_xprt_release_slot(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
if (test_and_clear_bit(RQ_DATA, &rqstp->rq_flags)) {
atomic_dec(&xprt->xpt_nr_rqsts);
smp_wmb();
svc_xprt_enqueue(xprt);
}
}
static bool svc_xprt_ready(struct svc_xprt *xprt)
{
unsigned long xpt_flags;
smp_rmb();
xpt_flags = READ_ONCE(xprt->xpt_flags);
trace_svc_xprt_enqueue(xprt, xpt_flags);
if (xpt_flags & BIT(XPT_BUSY))
return false;
if (xpt_flags & (BIT(XPT_CONN) | BIT(XPT_CLOSE) | BIT(XPT_HANDSHAKE)))
return true;
if (xpt_flags & (BIT(XPT_DATA) | BIT(XPT_DEFERRED))) {
if (xprt->xpt_ops->xpo_has_wspace(xprt) &&
svc_xprt_slots_in_range(xprt))
return true;
trace_svc_xprt_no_write_space(xprt);
return false;
}
return false;
}
void svc_xprt_enqueue(struct svc_xprt *xprt)
{
struct svc_pool *pool;
if (!svc_xprt_ready(xprt))
return;
if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags))
return;
pool = svc_pool_for_cpu(xprt->xpt_server);
percpu_counter_inc(&pool->sp_sockets_queued);
spin_lock_bh(&pool->sp_lock);
list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
spin_unlock_bh(&pool->sp_lock);
svc_pool_wake_idle_thread(pool);
}
EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
{
struct svc_xprt *xprt = NULL;
if (list_empty(&pool->sp_sockets))
goto out;
spin_lock_bh(&pool->sp_lock);
if (likely(!list_empty(&pool->sp_sockets))) {
xprt = list_first_entry(&pool->sp_sockets,
struct svc_xprt, xpt_ready);
list_del_init(&xprt->xpt_ready);
svc_xprt_get(xprt);
}
spin_unlock_bh(&pool->sp_lock);
out:
return xprt;
}
void svc_reserve(struct svc_rqst *rqstp, int space)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
space += rqstp->rq_res.head[0].iov_len;
if (xprt && space < rqstp->rq_reserved) {
atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved);
rqstp->rq_reserved = space;
smp_wmb();
svc_xprt_enqueue(xprt);
}
}
EXPORT_SYMBOL_GPL(svc_reserve);
static void free_deferred(struct svc_xprt *xprt, struct svc_deferred_req *dr)
{
if (!dr)
return;
xprt->xpt_ops->xpo_release_ctxt(xprt, dr->xprt_ctxt);
kfree(dr);
}
static void svc_xprt_release(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
xprt->xpt_ops->xpo_release_ctxt(xprt, rqstp->rq_xprt_ctxt);
rqstp->rq_xprt_ctxt = NULL;
free_deferred(xprt, rqstp->rq_deferred);
rqstp->rq_deferred = NULL;
svc_rqst_release_pages(rqstp);
rqstp->rq_res.page_len = 0;
rqstp->rq_res.page_base = 0;
if ((rqstp->rq_res.len) > rqstp->rq_reserved)
printk(KERN_ERR "RPC request reserved %d but used %d\n",
rqstp->rq_reserved,
rqstp->rq_res.len);
rqstp->rq_res.head[0].iov_len = 0;
svc_reserve(rqstp, 0);
svc_xprt_release_slot(rqstp);
rqstp->rq_xprt = NULL;
svc_xprt_put(xprt);
}
void svc_wake_up(struct svc_serv *serv)
{
struct svc_pool *pool = &serv->sv_pools[0];
set_bit(SP_TASK_PENDING, &pool->sp_flags);
svc_pool_wake_idle_thread(pool);
}
EXPORT_SYMBOL_GPL(svc_wake_up);
int svc_port_is_privileged(struct sockaddr *sin)
{
switch (sin->sa_family) {
case AF_INET:
return ntohs(((struct sockaddr_in *)sin)->sin_port)
< PROT_SOCK;
case AF_INET6:
return ntohs(((struct sockaddr_in6 *)sin)->sin6_port)
< PROT_SOCK;
default:
return 0;
}
}
static void svc_check_conn_limits(struct svc_serv *serv)
{
unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn :
(serv->sv_nrthreads+3) * 20;
if (serv->sv_tmpcnt > limit) {
struct svc_xprt *xprt = NULL;
spin_lock_bh(&serv->sv_lock);
if (!list_empty(&serv->sv_tempsocks)) {
net_notice_ratelimited("%s: too many open connections, consider increasing the %s\n",
serv->sv_name, serv->sv_maxconn ?
"max number of connections" :
"number of threads");
xprt = list_entry(serv->sv_tempsocks.prev,
struct svc_xprt,
xpt_list);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_get(xprt);
}
spin_unlock_bh(&serv->sv_lock);
if (xprt) {
svc_xprt_enqueue(xprt);
svc_xprt_put(xprt);
}
}
}
static bool svc_alloc_arg(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
struct xdr_buf *arg = &rqstp->rq_arg;
unsigned long pages, filled, ret;
pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
if (pages > RPCSVC_MAXPAGES) {
pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n",
pages, RPCSVC_MAXPAGES);
pages = RPCSVC_MAXPAGES;
}
for (filled = 0; filled < pages; filled = ret) {
ret = alloc_pages_bulk_array_node(GFP_KERNEL,
rqstp->rq_pool->sp_id,
pages, rqstp->rq_pages);
if (ret > filled)
continue;
set_current_state(TASK_IDLE);
if (kthread_should_stop()) {
set_current_state(TASK_RUNNING);
return false;
}
trace_svc_alloc_arg_err(pages, ret);
memalloc_retry_wait(GFP_KERNEL);
}
rqstp->rq_page_end = &rqstp->rq_pages[pages];
rqstp->rq_pages[pages] = NULL;
arg->head[0].iov_base = page_address(rqstp->rq_pages[0]);
arg->head[0].iov_len = PAGE_SIZE;
arg->pages = rqstp->rq_pages + 1;
arg->page_base = 0;
arg->page_len = (pages-2)*PAGE_SIZE;
arg->len = (pages-1)*PAGE_SIZE;
arg->tail[0].iov_len = 0;
rqstp->rq_xid = xdr_zero;
return true;
}
static bool
rqst_should_sleep(struct svc_rqst *rqstp)
{
struct svc_pool *pool = rqstp->rq_pool;
if (test_bit(SP_TASK_PENDING, &pool->sp_flags))
return false;
if (!list_empty(&pool->sp_sockets))
return false;
if (kthread_should_stop())
return false;
if (freezing(current))
return false;
return true;
}
static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp)
{
struct svc_pool *pool = rqstp->rq_pool;
WARN_ON_ONCE(rqstp->rq_xprt);
rqstp->rq_xprt = svc_xprt_dequeue(pool);
if (rqstp->rq_xprt)
goto out_found;
set_current_state(TASK_IDLE);
smp_mb__before_atomic();
clear_bit(SP_CONGESTED, &pool->sp_flags);
clear_bit(RQ_BUSY, &rqstp->rq_flags);
smp_mb__after_atomic();
if (likely(rqst_should_sleep(rqstp)))
schedule();
else
__set_current_state(TASK_RUNNING);
try_to_freeze();
set_bit(RQ_BUSY, &rqstp->rq_flags);
smp_mb__after_atomic();
clear_bit(SP_TASK_PENDING, &pool->sp_flags);
rqstp->rq_xprt = svc_xprt_dequeue(pool);
if (rqstp->rq_xprt)
goto out_found;
if (kthread_should_stop())
return NULL;
return NULL;
out_found:
clear_bit(SP_TASK_PENDING, &pool->sp_flags);
if (!test_bit(SP_CONGESTED, &pool->sp_flags))
rqstp->rq_chandle.thread_wait = 5*HZ;
else
rqstp->rq_chandle.thread_wait = 1*HZ;
trace_svc_xprt_dequeue(rqstp);
return rqstp->rq_xprt;
}
static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
{
spin_lock_bh(&serv->sv_lock);
set_bit(XPT_TEMP, &newxpt->xpt_flags);
list_add(&newxpt->xpt_list, &serv->sv_tempsocks);
serv->sv_tmpcnt++;
if (serv->sv_temptimer.function == NULL) {
serv->sv_temptimer.function = svc_age_temp_xprts;
mod_timer(&serv->sv_temptimer,
jiffies + svc_conn_age_period * HZ);
}
spin_unlock_bh(&serv->sv_lock);
svc_xprt_received(newxpt);
}
static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
{
struct svc_serv *serv = rqstp->rq_server;
int len = 0;
if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
if (test_and_clear_bit(XPT_KILL_TEMP, &xprt->xpt_flags))
xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
svc_delete_xprt(xprt);
goto out;
}
if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
struct svc_xprt *newxpt;
__module_get(xprt->xpt_class->xcl_owner);
svc_check_conn_limits(xprt->xpt_server);
newxpt = xprt->xpt_ops->xpo_accept(xprt);
if (newxpt) {
newxpt->xpt_cred = get_cred(xprt->xpt_cred);
svc_add_new_temp_xprt(serv, newxpt);
trace_svc_xprt_accept(newxpt, serv->sv_name);
} else {
module_put(xprt->xpt_class->xcl_owner);
}
svc_xprt_received(xprt);
} else if (test_bit(XPT_HANDSHAKE, &xprt->xpt_flags)) {
xprt->xpt_ops->xpo_handshake(xprt);
svc_xprt_received(xprt);
} else if (svc_xprt_reserve_slot(rqstp, xprt)) {
rqstp->rq_deferred = svc_deferred_dequeue(xprt);
if (rqstp->rq_deferred)
len = svc_deferred_recv(rqstp);
else
len = xprt->xpt_ops->xpo_recvfrom(rqstp);
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
} else
svc_xprt_received(xprt);
out:
return len;
}
void svc_recv(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = NULL;
struct svc_serv *serv = rqstp->rq_server;
int len;
if (!svc_alloc_arg(rqstp))
goto out;
try_to_freeze();
cond_resched();
if (kthread_should_stop())
goto out;
xprt = svc_get_next_xprt(rqstp);
if (!xprt)
goto out;
len = svc_handle_xprt(rqstp, xprt);
if (len <= 0)
goto out_release;
trace_svc_xdr_recvfrom(&rqstp->rq_arg);
clear_bit(XPT_OLD, &xprt->xpt_flags);
rqstp->rq_chandle.defer = svc_defer;
if (serv->sv_stats)
serv->sv_stats->netcnt++;
percpu_counter_inc(&rqstp->rq_pool->sp_messages_arrived);
rqstp->rq_stime = ktime_get();
svc_process(rqstp);
out:
return;
out_release:
rqstp->rq_res.len = 0;
svc_xprt_release(rqstp);
}
EXPORT_SYMBOL_GPL(svc_recv);
void svc_drop(struct svc_rqst *rqstp)
{
trace_svc_drop(rqstp);
svc_xprt_release(rqstp);
}
EXPORT_SYMBOL_GPL(svc_drop);
void svc_send(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt;
struct xdr_buf *xb;
int status;
xprt = rqstp->rq_xprt;
if (!xprt)
return;
xb = &rqstp->rq_res;
xb->len = xb->head[0].iov_len +
xb->page_len +
xb->tail[0].iov_len;
trace_svc_xdr_sendto(rqstp->rq_xid, xb);
trace_svc_stats_latency(rqstp);
status = xprt->xpt_ops->xpo_sendto(rqstp);
trace_svc_send(rqstp, status);
svc_xprt_release(rqstp);
}
static void svc_age_temp_xprts(struct timer_list *t)
{
struct svc_serv *serv = from_timer(serv, t, sv_temptimer);
struct svc_xprt *xprt;
struct list_head *le, *next;
dprintk("svc_age_temp_xprts\n");
if (!spin_trylock_bh(&serv->sv_lock)) {
dprintk("svc_age_temp_xprts: busy\n");
mod_timer(&serv->sv_temptimer, jiffies + HZ);
return;
}
list_for_each_safe(le, next, &serv->sv_tempsocks) {
xprt = list_entry(le, struct svc_xprt, xpt_list);
if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags))
continue;
if (kref_read(&xprt->xpt_ref) > 1 ||
test_bit(XPT_BUSY, &xprt->xpt_flags))
continue;
list_del_init(le);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
dprintk("queuing xprt %p for closing\n", xprt);
svc_xprt_enqueue(xprt);
}
spin_unlock_bh(&serv->sv_lock);
mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
}
void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr)
{
struct svc_xprt *xprt;
struct list_head *le, *next;
LIST_HEAD(to_be_closed);
spin_lock_bh(&serv->sv_lock);
list_for_each_safe(le, next, &serv->sv_tempsocks) {
xprt = list_entry(le, struct svc_xprt, xpt_list);
if (rpc_cmp_addr(server_addr, (struct sockaddr *)
&xprt->xpt_local)) {
dprintk("svc_age_temp_xprts_now: found %p\n", xprt);
list_move(le, &to_be_closed);
}
}
spin_unlock_bh(&serv->sv_lock);
while (!list_empty(&to_be_closed)) {
le = to_be_closed.next;
list_del_init(le);
xprt = list_entry(le, struct svc_xprt, xpt_list);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
set_bit(XPT_KILL_TEMP, &xprt->xpt_flags);
dprintk("svc_age_temp_xprts_now: queuing xprt %p for closing\n",
xprt);
svc_xprt_enqueue(xprt);
}
}
EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now);
static void call_xpt_users(struct svc_xprt *xprt)
{
struct svc_xpt_user *u;
spin_lock(&xprt->xpt_lock);
while (!list_empty(&xprt->xpt_users)) {
u = list_first_entry(&xprt->xpt_users, struct svc_xpt_user, list);
list_del_init(&u->list);
u->callback(u);
}
spin_unlock(&xprt->xpt_lock);
}
static void svc_delete_xprt(struct svc_xprt *xprt)
{
struct svc_serv *serv = xprt->xpt_server;
struct svc_deferred_req *dr;
if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags))
return;
trace_svc_xprt_detach(xprt);
xprt->xpt_ops->xpo_detach(xprt);
if (xprt->xpt_bc_xprt)
xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt);
spin_lock_bh(&serv->sv_lock);
list_del_init(&xprt->xpt_list);
WARN_ON_ONCE(!list_empty(&xprt->xpt_ready));
if (test_bit(XPT_TEMP, &xprt->xpt_flags))
serv->sv_tmpcnt--;
spin_unlock_bh(&serv->sv_lock);
while ((dr = svc_deferred_dequeue(xprt)) != NULL)
free_deferred(xprt, dr);
call_xpt_users(xprt);
svc_xprt_put(xprt);
}
void svc_xprt_close(struct svc_xprt *xprt)
{
trace_svc_xprt_close(xprt);
set_bit(XPT_CLOSE, &xprt->xpt_flags);
if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags))
return;
svc_delete_xprt(xprt);
}
EXPORT_SYMBOL_GPL(svc_xprt_close);
static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net)
{
struct svc_xprt *xprt;
int ret = 0;
spin_lock_bh(&serv->sv_lock);
list_for_each_entry(xprt, xprt_list, xpt_list) {
if (xprt->xpt_net != net)
continue;
ret++;
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
}
spin_unlock_bh(&serv->sv_lock);
return ret;
}
static struct svc_xprt *svc_dequeue_net(struct svc_serv *serv, struct net *net)
{
struct svc_pool *pool;
struct svc_xprt *xprt;
struct svc_xprt *tmp;
int i;
for (i = 0; i < serv->sv_nrpools; i++) {
pool = &serv->sv_pools[i];
spin_lock_bh(&pool->sp_lock);
list_for_each_entry_safe(xprt, tmp, &pool->sp_sockets, xpt_ready) {
if (xprt->xpt_net != net)
continue;
list_del_init(&xprt->xpt_ready);
spin_unlock_bh(&pool->sp_lock);
return xprt;
}
spin_unlock_bh(&pool->sp_lock);
}
return NULL;
}
static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net)
{
struct svc_xprt *xprt;
while ((xprt = svc_dequeue_net(serv, net))) {
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_delete_xprt(xprt);
}
}
void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net)
{
int delay = 0;
while (svc_close_list(serv, &serv->sv_permsocks, net) +
svc_close_list(serv, &serv->sv_tempsocks, net)) {
svc_clean_up_xprts(serv, net);
msleep(delay++);
}
}
EXPORT_SYMBOL_GPL(svc_xprt_destroy_all);
static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
{
struct svc_deferred_req *dr =
container_of(dreq, struct svc_deferred_req, handle);
struct svc_xprt *xprt = dr->xprt;
spin_lock(&xprt->xpt_lock);
set_bit(XPT_DEFERRED, &xprt->xpt_flags);
if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) {
spin_unlock(&xprt->xpt_lock);
trace_svc_defer_drop(dr);
free_deferred(xprt, dr);
svc_xprt_put(xprt);
return;
}
dr->xprt = NULL;
list_add(&dr->handle.recent, &xprt->xpt_deferred);
spin_unlock(&xprt->xpt_lock);
trace_svc_defer_queue(dr);
svc_xprt_enqueue(xprt);
svc_xprt_put(xprt);
}
static struct cache_deferred_req *svc_defer(struct cache_req *req)
{
struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
struct svc_deferred_req *dr;
if (rqstp->rq_arg.page_len || !test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags))
return NULL;
if (rqstp->rq_deferred) {
dr = rqstp->rq_deferred;
rqstp->rq_deferred = NULL;
} else {
size_t skip;
size_t size;
size = sizeof(struct svc_deferred_req) + rqstp->rq_arg.len;
dr = kmalloc(size, GFP_KERNEL);
if (dr == NULL)
return NULL;
dr->handle.owner = rqstp->rq_server;
dr->prot = rqstp->rq_prot;
memcpy(&dr->addr, &rqstp->rq_addr, rqstp->rq_addrlen);
dr->addrlen = rqstp->rq_addrlen;
dr->daddr = rqstp->rq_daddr;
dr->argslen = rqstp->rq_arg.len >> 2;
skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip,
dr->argslen << 2);
}
dr->xprt_ctxt = rqstp->rq_xprt_ctxt;
rqstp->rq_xprt_ctxt = NULL;
trace_svc_defer(rqstp);
svc_xprt_get(rqstp->rq_xprt);
dr->xprt = rqstp->rq_xprt;
set_bit(RQ_DROPME, &rqstp->rq_flags);
dr->handle.revisit = svc_revisit;
return &dr->handle;
}
static noinline int svc_deferred_recv(struct svc_rqst *rqstp)
{
struct svc_deferred_req *dr = rqstp->rq_deferred;
trace_svc_defer_recv(dr);
rqstp->rq_arg.head[0].iov_base = dr->args;
rqstp->rq_arg.head[0].iov_len = dr->argslen << 2;
rqstp->rq_arg.page_len = 0;
rqstp->rq_arg.len = dr->argslen << 2;
rqstp->rq_prot = dr->prot;
memcpy(&rqstp->rq_addr, &dr->addr, dr->addrlen);
rqstp->rq_addrlen = dr->addrlen;
rqstp->rq_daddr = dr->daddr;
rqstp->rq_respages = rqstp->rq_pages;
rqstp->rq_xprt_ctxt = dr->xprt_ctxt;
dr->xprt_ctxt = NULL;
svc_xprt_received(rqstp->rq_xprt);
return dr->argslen << 2;
}
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt)
{
struct svc_deferred_req *dr = NULL;
if (!test_bit(XPT_DEFERRED, &xprt->xpt_flags))
return NULL;
spin_lock(&xprt->xpt_lock);
if (!list_empty(&xprt->xpt_deferred)) {
dr = list_entry(xprt->xpt_deferred.next,
struct svc_deferred_req,
handle.recent);
list_del_init(&dr->handle.recent);
} else
clear_bit(XPT_DEFERRED, &xprt->xpt_flags);
spin_unlock(&xprt->xpt_lock);
return dr;
}
struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name,
struct net *net, const sa_family_t af,
const unsigned short port)
{
struct svc_xprt *xprt;
struct svc_xprt *found = NULL;
if (serv == NULL || xcl_name == NULL)
return found;
spin_lock_bh(&serv->sv_lock);
list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
if (xprt->xpt_net != net)
continue;
if (strcmp(xprt->xpt_class->xcl_name, xcl_name))
continue;
if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family)
continue;
if (port != 0 && port != svc_xprt_local_port(xprt))
continue;
found = xprt;
svc_xprt_get(xprt);
break;
}
spin_unlock_bh(&serv->sv_lock);
return found;
}
EXPORT_SYMBOL_GPL(svc_find_xprt);
static int svc_one_xprt_name(const struct svc_xprt *xprt,
char *pos, int remaining)
{
int len;
len = snprintf(pos, remaining, "%s %u\n",
xprt->xpt_class->xcl_name,
svc_xprt_local_port(xprt));
if (len >= remaining)
return -ENAMETOOLONG;
return len;
}
int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen)
{
struct svc_xprt *xprt;
int len, totlen;
char *pos;
if (!serv)
return 0;
spin_lock_bh(&serv->sv_lock);
pos = buf;
totlen = 0;
list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
len = svc_one_xprt_name(xprt, pos, buflen - totlen);
if (len < 0) {
*buf = '\0';
totlen = len;
}
if (len <= 0)
break;
pos += len;
totlen += len;
}
spin_unlock_bh(&serv->sv_lock);
return totlen;
}
EXPORT_SYMBOL_GPL(svc_xprt_names);
static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
{
unsigned int pidx = (unsigned int)*pos;
struct svc_serv *serv = m->private;
dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
if (!pidx)
return SEQ_START_TOKEN;
return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
}
static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
{
struct svc_pool *pool = p;
struct svc_serv *serv = m->private;
dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
if (p == SEQ_START_TOKEN) {
pool = &serv->sv_pools[0];
} else {
unsigned int pidx = (pool - &serv->sv_pools[0]);
if (pidx < serv->sv_nrpools-1)
pool = &serv->sv_pools[pidx+1];
else
pool = NULL;
}
++*pos;
return pool;
}
static void svc_pool_stats_stop(struct seq_file *m, void *p)
{
}
static int svc_pool_stats_show(struct seq_file *m, void *p)
{
struct svc_pool *pool = p;
if (p == SEQ_START_TOKEN) {
seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n");
return 0;
}
seq_printf(m, "%u %llu %llu %llu 0\n",
pool->sp_id,
percpu_counter_sum_positive(&pool->sp_messages_arrived),
percpu_counter_sum_positive(&pool->sp_sockets_queued),
percpu_counter_sum_positive(&pool->sp_threads_woken));
return 0;
}
static const struct seq_operations svc_pool_stats_seq_ops = {
.start = svc_pool_stats_start,
.next = svc_pool_stats_next,
.stop = svc_pool_stats_stop,
.show = svc_pool_stats_show,
};
int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
{
int err;
err = seq_open(file, &svc_pool_stats_seq_ops);
if (!err)
((struct seq_file *) file->private_data)->private = serv;
return err;
}
EXPORT_SYMBOL(svc_pool_stats_open);