renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-17 01:34:00 +08:00
Code
00e907127e
linux-next/net/rxrpc/call_accept.c
David Howells 00e907127e rxrpc: Preallocate peers, conns and calls for incoming service requests 
Make it possible for the data_ready handler called from the UDP transport
socket to completely instantiate an rxrpc_call structure and make it
immediately live by preallocating all the memory it might need.  The idea
is to cut out the background thread usage as much as possible.

[Note that the preallocated structs are not actually used in this patch -
 that will be done in a future patch.]

If insufficient resources are available in the preallocation buffers, it
will be possible to discard the DATA packet in the data_ready handler or
schedule a BUSY packet without the need to schedule an attempt at
allocation in a background thread.

To this end:

 (1) Preallocate rxrpc_peer, rxrpc_connection and rxrpc_call structs to a
     maximum number each of the listen backlog size.  The backlog size is
     limited to a maxmimum of 32.  Only this many of each can be in the
     preallocation buffer.

 (2) For userspace sockets, the preallocation is charged initially by
     listen() and will be recharged by accepting or rejecting pending
     new incoming calls.

 (3) For kernel services {,re,dis}charging of the preallocation buffers is
     handled manually.  Two notifier callbacks have to be provided before
     kernel_listen() is invoked:

     (a) An indication that a new call has been instantiated.  This can be
     	 used to trigger background recharging.

     (b) An indication that a call is being discarded.  This is used when
     	 the socket is being released.

     A function, rxrpc_kernel_charge_accept() is called by the kernel
     service to preallocate a single call.  It should be passed the user ID
     to be used for that call and a callback to associate the rxrpc call
     with the kernel service's side of the ID.

 (4) Discard the preallocation when the socket is closed.

 (5) Temporarily bump the refcount on the call allocated in
     rxrpc_incoming_call() so that rxrpc_release_call() can ditch the
     preallocation ref on service calls unconditionally.  This will no
     longer be necessary once the preallocation is used.

Note that this does not yet control the number of active service calls on a
client - that will come in a later patch.

A future development would be to provide a setsockopt() call that allows a
userspace server to manually charge the preallocation buffer.  This would
allow user call IDs to be provided in advance and the awkward manual accept
stage to be bypassed.

Signed-off-by: David Howells <dhowells@redhat.com>
2016-09-08 11:10:12 +01:00

682 lines
17 KiB
C
Raw Blame History

/* incoming call handling
*
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/errqueue.h>
#include <linux/udp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/icmp.h>
#include <linux/gfp.h>
#include <linux/circ_buf.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include "ar-internal.h"
/*
* Preallocate a single service call, connection and peer and, if possible,
* give them a user ID and attach the user's side of the ID to them.
*/
static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
struct rxrpc_backlog *b,
rxrpc_notify_rx_t notify_rx,
rxrpc_user_attach_call_t user_attach_call,
unsigned long user_call_ID, gfp_t gfp)
{
const void *here = __builtin_return_address(0);
struct rxrpc_call *call;
int max, tmp;
unsigned int size = RXRPC_BACKLOG_MAX;
unsigned int head, tail, call_head, call_tail;
max = rx->sk.sk_max_ack_backlog;
tmp = rx->sk.sk_ack_backlog;
if (tmp >= max) {
_leave(" = -ENOBUFS [full %u]", max);
return -ENOBUFS;
}
max -= tmp;
/* We don't need more conns and peers than we have calls, but on the
* other hand, we shouldn't ever use more peers than conns or conns
* than calls.
*/
call_head = b->call_backlog_head;
call_tail = READ_ONCE(b->call_backlog_tail);
tmp = CIRC_CNT(call_head, call_tail, size);
if (tmp >= max) {
_leave(" = -ENOBUFS [enough %u]", tmp);
return -ENOBUFS;
}
max = tmp + 1;
head = b->peer_backlog_head;
tail = READ_ONCE(b->peer_backlog_tail);
if (CIRC_CNT(head, tail, size) < max) {
struct rxrpc_peer *peer = rxrpc_alloc_peer(rx->local, gfp);
if (!peer)
return -ENOMEM;
b->peer_backlog[head] = peer;
smp_store_release(&b->peer_backlog_head,
(head + 1) & (size - 1));
}
head = b->conn_backlog_head;
tail = READ_ONCE(b->conn_backlog_tail);
if (CIRC_CNT(head, tail, size) < max) {
struct rxrpc_connection *conn;
conn = rxrpc_prealloc_service_connection(gfp);
if (!conn)
return -ENOMEM;
b->conn_backlog[head] = conn;
smp_store_release(&b->conn_backlog_head,
(head + 1) & (size - 1));
}
/* Now it gets complicated, because calls get registered with the
* socket here, particularly if a user ID is preassigned by the user.
*/
call = rxrpc_alloc_call(gfp);
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
call->state = RXRPC_CALL_SERVER_PREALLOC;
trace_rxrpc_call(call, rxrpc_call_new_service,
atomic_read(&call->usage),
here, (const void *)user_call_ID);
write_lock(&rx->call_lock);
if (user_attach_call) {
struct rxrpc_call *xcall;
struct rb_node *parent, **pp;
/* Check the user ID isn't already in use */
pp = &rx->calls.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
xcall = rb_entry(parent, struct rxrpc_call, sock_node);
if (user_call_ID < call->user_call_ID)
pp = &(*pp)->rb_left;
else if (user_call_ID > call->user_call_ID)
pp = &(*pp)->rb_right;
else
goto id_in_use;
}
call->user_call_ID = user_call_ID;
call->notify_rx = notify_rx;
rxrpc_get_call(call, rxrpc_call_got);
user_attach_call(call, user_call_ID);
rxrpc_get_call(call, rxrpc_call_got_userid);
rb_link_node(&call->sock_node, parent, pp);
rb_insert_color(&call->sock_node, &rx->calls);
set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
}
write_unlock(&rx->call_lock);
write_lock(&rxrpc_call_lock);
list_add_tail(&call->link, &rxrpc_calls);
write_unlock(&rxrpc_call_lock);
b->call_backlog[call_head] = call;
smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1));
_leave(" = 0 [%d -> %lx]", call->debug_id, user_call_ID);
return 0;
id_in_use:
write_unlock(&rx->call_lock);
rxrpc_cleanup_call(call);
_leave(" = -EBADSLT");
return -EBADSLT;
}
/*
* Preallocate sufficient service connections, calls and peers to cover the
* entire backlog of a socket. When a new call comes in, if we don't have
* sufficient of each available, the call gets rejected as busy or ignored.
*
* The backlog is replenished when a connection is accepted or rejected.
*/
int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp)
{
struct rxrpc_backlog *b = rx->backlog;
if (!b) {
b = kzalloc(sizeof(struct rxrpc_backlog), gfp);
if (!b)
return -ENOMEM;
rx->backlog = b;
}
if (rx->discard_new_call)
return 0;
while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp) == 0)
;
return 0;
}
/*
* Discard the preallocation on a service.
*/
void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
{
struct rxrpc_backlog *b = rx->backlog;
unsigned int size = RXRPC_BACKLOG_MAX, head, tail;
if (!b)
return;
rx->backlog = NULL;
head = b->peer_backlog_head;
tail = b->peer_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_peer *peer = b->peer_backlog[tail];
kfree(peer);
tail = (tail + 1) & (size - 1);
}
head = b->conn_backlog_head;
tail = b->conn_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_connection *conn = b->conn_backlog[tail];
write_lock(&rxrpc_connection_lock);
list_del(&conn->link);
list_del(&conn->proc_link);
write_unlock(&rxrpc_connection_lock);
kfree(conn);
tail = (tail + 1) & (size - 1);
}
head = b->call_backlog_head;
tail = b->call_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_call *call = b->call_backlog[tail];
if (rx->discard_new_call) {
_debug("discard %lx", call->user_call_ID);
rx->discard_new_call(call, call->user_call_ID);
}
rxrpc_call_completed(call);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put);
tail = (tail + 1) & (size - 1);
}
kfree(b);
}
/*
* generate a connection-level abort
*/
static int rxrpc_busy(struct rxrpc_local *local, struct sockaddr_rxrpc *srx,
struct rxrpc_wire_header *whdr)
{
struct msghdr msg;
struct kvec iov[1];
size_t len;
int ret;
_enter("%d,,", local->debug_id);
whdr->type = RXRPC_PACKET_TYPE_BUSY;
whdr->serial = htonl(1);
msg.msg_name = &srx->transport.sin;
msg.msg_namelen = sizeof(srx->transport.sin);
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
iov[0].iov_base = whdr;
iov[0].iov_len = sizeof(*whdr);
len = iov[0].iov_len;
_proto("Tx BUSY %%1");
ret = kernel_sendmsg(local->socket, &msg, iov, 1, len);
if (ret < 0) {
_leave(" = -EAGAIN [sendmsg failed: %d]", ret);
return -EAGAIN;
}
_leave(" = 0");
return 0;
}
/*
* accept an incoming call that needs peer, transport and/or connection setting
* up
*/
static int rxrpc_accept_incoming_call(struct rxrpc_local *local,
struct rxrpc_sock *rx,
struct sk_buff *skb,
struct sockaddr_rxrpc *srx)
{
struct rxrpc_connection *conn;
struct rxrpc_skb_priv *sp, *nsp;
struct rxrpc_call *call;
struct sk_buff *notification;
int ret;
_enter("");
sp = rxrpc_skb(skb);
/* get a notification message to send to the server app */
notification = alloc_skb(0, GFP_NOFS);
if (!notification) {
_debug("no memory");
ret = -ENOMEM;
goto error_nofree;
}
rxrpc_new_skb(notification);
notification->mark = RXRPC_SKB_MARK_NEW_CALL;
conn = rxrpc_incoming_connection(local, srx, skb);
if (IS_ERR(conn)) {
_debug("no conn");
ret = PTR_ERR(conn);
goto error;
}
call = rxrpc_incoming_call(rx, conn, skb);
rxrpc_put_connection(conn);
if (IS_ERR(call)) {
_debug("no call");
ret = PTR_ERR(call);
goto error;
}
/* attach the call to the socket */
read_lock_bh(&local->services_lock);
if (rx->sk.sk_state == RXRPC_CLOSE)
goto invalid_service;
write_lock(&rx->call_lock);
if (!test_and_set_bit(RXRPC_CALL_INIT_ACCEPT, &call->flags)) {
rxrpc_get_call(call, rxrpc_call_got);
spin_lock(&call->conn->state_lock);
if (sp->hdr.securityIndex > 0 &&
call->conn->state == RXRPC_CONN_SERVICE_UNSECURED) {
_debug("await conn sec");
list_add_tail(&call->accept_link, &rx->secureq);
call->conn->state = RXRPC_CONN_SERVICE_CHALLENGING;
set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events);
rxrpc_queue_conn(call->conn);
} else {
_debug("conn ready");
call->state = RXRPC_CALL_SERVER_ACCEPTING;
list_add_tail(&call->accept_link, &rx->acceptq);
rxrpc_get_call_for_skb(call, notification);
nsp = rxrpc_skb(notification);
nsp->call = call;
ASSERTCMP(atomic_read(&call->usage), >=, 3);
_debug("notify");
spin_lock(&call->lock);
ret = rxrpc_queue_rcv_skb(call, notification, true,
false);
spin_unlock(&call->lock);
notification = NULL;
BUG_ON(ret < 0);
}
spin_unlock(&call->conn->state_lock);
_debug("queued");
}
write_unlock(&rx->call_lock);
_debug("process");
rxrpc_fast_process_packet(call, skb);
_debug("done");
read_unlock_bh(&local->services_lock);
rxrpc_free_skb(notification);
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = 0");
return 0;
invalid_service:
_debug("invalid");
read_unlock_bh(&local->services_lock);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put);
ret = -ECONNREFUSED;
error:
rxrpc_free_skb(notification);
error_nofree:
_leave(" = %d", ret);
return ret;
}
/*
* accept incoming calls that need peer, transport and/or connection setting up
* - the packets we get are all incoming client DATA packets that have seq == 1
*/
void rxrpc_accept_incoming_calls(struct rxrpc_local *local)
{
struct rxrpc_skb_priv *sp;
struct sockaddr_rxrpc srx;
struct rxrpc_sock *rx;
struct rxrpc_wire_header whdr;
struct sk_buff *skb;
int ret;
_enter("%d", local->debug_id);
skb = skb_dequeue(&local->accept_queue);
if (!skb) {
_leave("\n");
return;
}
_net("incoming call skb %p", skb);
rxrpc_see_skb(skb);
sp = rxrpc_skb(skb);
/* Set up a response packet header in case we need it */
whdr.epoch = htonl(sp->hdr.epoch);
whdr.cid = htonl(sp->hdr.cid);
whdr.callNumber = htonl(sp->hdr.callNumber);
whdr.seq = htonl(sp->hdr.seq);
whdr.serial = 0;
whdr.flags = 0;
whdr.type = 0;
whdr.userStatus = 0;
whdr.securityIndex = sp->hdr.securityIndex;
whdr._rsvd = 0;
whdr.serviceId = htons(sp->hdr.serviceId);
if (rxrpc_extract_addr_from_skb(&srx, skb) < 0)
goto drop;
/* get the socket providing the service */
read_lock_bh(&local->services_lock);
hlist_for_each_entry(rx, &local->services, listen_link) {
if (rx->srx.srx_service == sp->hdr.serviceId &&
rx->sk.sk_state != RXRPC_CLOSE)
goto found_service;
}
read_unlock_bh(&local->services_lock);
goto invalid_service;
found_service:
_debug("found service %hd", rx->srx.srx_service);
if (sk_acceptq_is_full(&rx->sk))
goto backlog_full;
sk_acceptq_added(&rx->sk);
read_unlock_bh(&local->services_lock);
ret = rxrpc_accept_incoming_call(local, rx, skb, &srx);
if (ret < 0)
sk_acceptq_removed(&rx->sk);
switch (ret) {
case -ECONNRESET: /* old calls are ignored */
case -ECONNABORTED: /* aborted calls are reaborted or ignored */
case 0:
return;
case -ECONNREFUSED:
goto invalid_service;
case -EBUSY:
goto busy;
case -EKEYREJECTED:
goto security_mismatch;
default:
BUG();
}
backlog_full:
read_unlock_bh(&local->services_lock);
busy:
rxrpc_busy(local, &srx, &whdr);
rxrpc_free_skb(skb);
return;
drop:
rxrpc_free_skb(skb);
return;
invalid_service:
skb->priority = RX_INVALID_OPERATION;
rxrpc_reject_packet(local, skb);
return;
/* can't change connection security type mid-flow */
security_mismatch:
skb->priority = RX_PROTOCOL_ERROR;
rxrpc_reject_packet(local, skb);
return;
}
/*
* handle acceptance of a call by userspace
* - assign the user call ID to the call at the front of the queue
*/
struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
unsigned long user_call_ID,
rxrpc_notify_rx_t notify_rx)
{
struct rxrpc_call *call;
struct rb_node *parent, **pp;
int ret;
_enter(",%lx", user_call_ID);
ASSERT(!irqs_disabled());
write_lock(&rx->call_lock);
ret = -ENODATA;
if (list_empty(&rx->acceptq))
goto out;
/* check the user ID isn't already in use */
ret = -EBADSLT;
pp = &rx->calls.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
call = rb_entry(parent, struct rxrpc_call, sock_node);
if (user_call_ID < call->user_call_ID)
pp = &(*pp)->rb_left;
else if (user_call_ID > call->user_call_ID)
pp = &(*pp)->rb_right;
else
goto out;
}
/* dequeue the first call and check it's still valid */
call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link);
list_del_init(&call->accept_link);
sk_acceptq_removed(&rx->sk);
rxrpc_see_call(call);
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_SERVER_ACCEPTING:
call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
break;
case RXRPC_CALL_COMPLETE:
ret = call->error;
goto out_release;
default:
BUG();
}
/* formalise the acceptance */
rxrpc_get_call(call, rxrpc_call_got_userid);
call->notify_rx = notify_rx;
call->user_call_ID = user_call_ID;
rb_link_node(&call->sock_node, parent, pp);
rb_insert_color(&call->sock_node, &rx->calls);
if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags))
BUG();
if (test_and_set_bit(RXRPC_CALL_EV_ACCEPTED, &call->events))
BUG();
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
rxrpc_queue_call(call);
_leave(" = %p{%d}", call, call->debug_id);
return call;
out_release:
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
_debug("release %p", call);
rxrpc_release_call(rx, call);
_leave(" = %d", ret);
return ERR_PTR(ret);
out:
write_unlock(&rx->call_lock);
_leave(" = %d", ret);
return ERR_PTR(ret);
}
/*
* Handle rejection of a call by userspace
* - reject the call at the front of the queue
*/
int rxrpc_reject_call(struct rxrpc_sock *rx)
{
struct rxrpc_call *call;
int ret;
_enter("");
ASSERT(!irqs_disabled());
write_lock(&rx->call_lock);
ret = -ENODATA;
if (list_empty(&rx->acceptq)) {
write_unlock(&rx->call_lock);
_leave(" = -ENODATA");
return -ENODATA;
}
/* dequeue the first call and check it's still valid */
call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link);
list_del_init(&call->accept_link);
sk_acceptq_removed(&rx->sk);
rxrpc_see_call(call);
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_SERVER_ACCEPTING:
__rxrpc_set_call_completion(call, RXRPC_CALL_SERVER_BUSY,
0, ECONNABORTED);
if (test_and_set_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events))
rxrpc_queue_call(call);
ret = 0;
break;
case RXRPC_CALL_COMPLETE:
ret = call->error;
break;
default:
BUG();
}
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
rxrpc_release_call(rx, call);
_leave(" = %d", ret);
return ret;
}
/**
* rxrpc_kernel_accept_call - Allow a kernel service to accept an incoming call
* @sock: The socket on which the impending call is waiting
* @user_call_ID: The tag to attach to the call
* @notify_rx: Where to send notifications instead of socket queue
*
* Allow a kernel service to accept an incoming call, assuming the incoming
* call is still valid. The caller should immediately trigger their own
* notification as there must be data waiting.
*/
struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *sock,
unsigned long user_call_ID,
rxrpc_notify_rx_t notify_rx)
{
struct rxrpc_call *call;
_enter(",%lx", user_call_ID);
call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID, notify_rx);
_leave(" = %p", call);
return call;
}
EXPORT_SYMBOL(rxrpc_kernel_accept_call);
/**
* rxrpc_kernel_reject_call - Allow a kernel service to reject an incoming call
* @sock: The socket on which the impending call is waiting
*
* Allow a kernel service to reject an incoming call with a BUSY message,
* assuming the incoming call is still valid.
*/
int rxrpc_kernel_reject_call(struct socket *sock)
{
int ret;
_enter("");
ret = rxrpc_reject_call(rxrpc_sk(sock->sk));
_leave(" = %d", ret);
return ret;
}
EXPORT_SYMBOL(rxrpc_kernel_reject_call);
/*
* rxrpc_kernel_charge_accept - Charge up socket with preallocated calls
* @sock: The socket on which to preallocate
* @notify_rx: Event notification function for the call
* @user_attach_call: Func to attach call to user_call_ID
* @user_call_ID: The tag to attach to the preallocated call
* @gfp: The allocation conditions.
*
* Charge up the socket with preallocated calls, each with a user ID. A
* function should be provided to effect the attachment from the user's side.
* The user is given a ref to hold on the call.
*
* Note that the call may be come connected before this function returns.
*/
int rxrpc_kernel_charge_accept(struct socket *sock,
rxrpc_notify_rx_t notify_rx,
rxrpc_user_attach_call_t user_attach_call,
unsigned long user_call_ID, gfp_t gfp)
{
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct rxrpc_backlog *b = rx->backlog;
if (sock->sk->sk_state == RXRPC_CLOSE)
return -ESHUTDOWN;
return rxrpc_service_prealloc_one(rx, b, notify_rx,
user_attach_call, user_call_ID,
gfp);
}
EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
View Git Blame Copy Permalink