linux-sg2042/net/sctp/chunk.c

373 lines
10 KiB
C
Raw Normal View History

/* SCTP kernel implementation
* (C) Copyright IBM Corp. 2003, 2004
*
* This file is part of the SCTP kernel implementation
*
* This file contains the code relating the chunk abstraction.
*
* This SCTP implementation 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, or (at your option)
* any later version.
*
* This SCTP implementation is distributed in the hope that it
* will be useful, but WITHOUT ANY WARRANTY; without even the implied
* ************************
* warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
* See the GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with GNU CC; see the file COPYING. If not, see
* <http://www.gnu.org/licenses/>.
*
* Please send any bug reports or fixes you make to the
* email address(es):
* lksctp developers <linux-sctp@vger.kernel.org>
*
* Written or modified by:
* Jon Grimm <jgrimm@us.ibm.com>
* Sridhar Samudrala <sri@us.ibm.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/net.h>
#include <linux/inet.h>
#include <linux/skbuff.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 16:04:11 +08:00
#include <linux/slab.h>
#include <net/sock.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
/* This file is mostly in anticipation of future work, but initially
* populate with fragment tracking for an outbound message.
*/
/* Initialize datamsg from memory. */
static void sctp_datamsg_init(struct sctp_datamsg *msg)
{
refcount_set(&msg->refcnt, 1);
msg->send_failed = 0;
msg->send_error = 0;
msg->can_delay = 1;
msg->abandoned = 0;
msg->expires_at = 0;
INIT_LIST_HEAD(&msg->chunks);
}
/* Allocate and initialize datamsg. */
static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp)
{
struct sctp_datamsg *msg;
msg = kmalloc(sizeof(struct sctp_datamsg), gfp);
if (msg) {
sctp_datamsg_init(msg);
SCTP_DBG_OBJCNT_INC(datamsg);
}
return msg;
}
void sctp_datamsg_free(struct sctp_datamsg *msg)
{
struct sctp_chunk *chunk;
/* This doesn't have to be a _safe vairant because
* sctp_chunk_free() only drops the refs.
*/
list_for_each_entry(chunk, &msg->chunks, frag_list)
sctp_chunk_free(chunk);
sctp_datamsg_put(msg);
}
/* Final destructruction of datamsg memory. */
static void sctp_datamsg_destroy(struct sctp_datamsg *msg)
{
struct list_head *pos, *temp;
struct sctp_chunk *chunk;
struct sctp_sock *sp;
struct sctp_ulpevent *ev;
struct sctp_association *asoc = NULL;
int error = 0, notify;
/* If we failed, we may need to notify. */
notify = msg->send_failed ? -1 : 0;
/* Release all references. */
list_for_each_safe(pos, temp, &msg->chunks) {
list_del_init(pos);
chunk = list_entry(pos, struct sctp_chunk, frag_list);
/* Check whether we _really_ need to notify. */
if (notify < 0) {
asoc = chunk->asoc;
if (msg->send_error)
error = msg->send_error;
else
error = asoc->outqueue.error;
sp = sctp_sk(asoc->base.sk);
notify = sctp_ulpevent_type_enabled(SCTP_SEND_FAILED,
&sp->subscribe);
}
/* Generate a SEND FAILED event only if enabled. */
if (notify > 0) {
int sent;
if (chunk->has_tsn)
sent = SCTP_DATA_SENT;
else
sent = SCTP_DATA_UNSENT;
ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent,
error, GFP_ATOMIC);
if (ev)
asoc->stream.si->enqueue_event(&asoc->ulpq, ev);
}
sctp_chunk_put(chunk);
}
SCTP_DBG_OBJCNT_DEC(datamsg);
kfree(msg);
}
/* Hold a reference. */
static void sctp_datamsg_hold(struct sctp_datamsg *msg)
{
refcount_inc(&msg->refcnt);
}
/* Release a reference. */
void sctp_datamsg_put(struct sctp_datamsg *msg)
{
if (refcount_dec_and_test(&msg->refcnt))
sctp_datamsg_destroy(msg);
}
/* Assign a chunk to this datamsg. */
static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chunk)
{
sctp_datamsg_hold(msg);
chunk->msg = msg;
}
/* A data chunk can have a maximum payload of (2^16 - 20). Break
* down any such message into smaller chunks. Opportunistically, fragment
* the chunks down to the current MTU constraints. We may get refragmented
* later if the PMTU changes, but it is _much better_ to fragment immediately
* with a reasonable guess than always doing our fragmentation on the
* soft-interrupt.
*/
struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
struct sctp_sndrcvinfo *sinfo,
struct iov_iter *from)
{
size_t len, first_len, max_data, remaining;
size_t msg_len = iov_iter_count(from);
struct sctp_shared_key *shkey = NULL;
struct list_head *pos, *temp;
struct sctp_chunk *chunk;
struct sctp_datamsg *msg;
struct sctp_sock *sp;
struct sctp_af *af;
int err;
msg = sctp_datamsg_new(GFP_KERNEL);
if (!msg)
return ERR_PTR(-ENOMEM);
/* Note: Calculate this outside of the loop, so that all fragments
* have the same expiration.
*/
if (asoc->peer.prsctp_capable && sinfo->sinfo_timetolive &&
(SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags) ||
!SCTP_PR_POLICY(sinfo->sinfo_flags)))
msg->expires_at = jiffies +
msecs_to_jiffies(sinfo->sinfo_timetolive);
/* This is the biggest possible DATA chunk that can fit into
* the packet
*/
sp = sctp_sk(asoc->base.sk);
af = sp->pf->af;
max_data = asoc->pathmtu - af->net_header_len -
sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream) -
af->ip_options_len(asoc->base.sk);
max_data = SCTP_TRUNC4(max_data);
/* If the the peer requested that we authenticate DATA chunks
* we need to account for bundling of the AUTH chunks along with
* DATA.
*/
if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) {
struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc);
if (hmac_desc)
max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) +
hmac_desc->hmac_len);
if (sinfo->sinfo_tsn &&
sinfo->sinfo_ssn != asoc->active_key_id) {
shkey = sctp_auth_get_shkey(asoc, sinfo->sinfo_ssn);
if (!shkey) {
err = -EINVAL;
goto errout;
}
} else {
shkey = asoc->shkey;
}
}
/* Check what's our max considering the above */
max_data = min_t(size_t, max_data, asoc->frag_point);
/* Set first_len and then account for possible bundles on first frag */
first_len = max_data;
/* Check to see if we have a pending SACK and try to let it be bundled
* with this message. Do this if we don't have any data queued already.
* To check that, look at out_qlen and retransmit list.
* NOTE: we will not reduce to account for SACK, if the message would
* not have been fragmented.
*/
if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) &&
asoc->outqueue.out_qlen == 0 &&
list_empty(&asoc->outqueue.retransmit) &&
msg_len > max_data)
first_len -= SCTP_PAD4(sizeof(struct sctp_sack_chunk));
/* Encourage Cookie-ECHO bundling. */
if (asoc->state < SCTP_STATE_COOKIE_ECHOED)
first_len -= SCTP_ARBITRARY_COOKIE_ECHO_LEN;
/* Account for a different sized first fragment */
if (msg_len >= first_len) {
msg->can_delay = 0;
SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS);
} else {
/* Which may be the only one... */
first_len = msg_len;
}
/* Create chunks for all DATA chunks. */
for (remaining = msg_len; remaining; remaining -= len) {
u8 frag = SCTP_DATA_MIDDLE_FRAG;
if (remaining == msg_len) {
/* First frag, which may also be the last */
frag |= SCTP_DATA_FIRST_FRAG;
len = first_len;
} else {
/* Middle frags */
len = max_data;
}
if (len >= remaining) {
/* Last frag, which may also be the first */
len = remaining;
frag |= SCTP_DATA_LAST_FRAG;
/* The application requests to set the I-bit of the
* last DATA chunk of a user message when providing
* the user message to the SCTP implementation.
*/
if ((sinfo->sinfo_flags & SCTP_EOF) ||
(sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY))
frag |= SCTP_DATA_SACK_IMM;
}
chunk = asoc->stream.si->make_datafrag(asoc, sinfo, len, frag,
GFP_KERNEL);
if (!chunk) {
err = -ENOMEM;
goto errout;
}
err = sctp_user_addto_chunk(chunk, len, from);
if (err < 0)
goto errout_chunk_free;
chunk->shkey = shkey;
/* Put the chunk->skb back into the form expected by send. */
__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr -
chunk->skb->data);
sctp_datamsg_assign(msg, chunk);
list_add_tail(&chunk->frag_list, &msg->chunks);
}
return msg;
errout_chunk_free:
sctp_chunk_free(chunk);
errout:
list_for_each_safe(pos, temp, &msg->chunks) {
list_del_init(pos);
chunk = list_entry(pos, struct sctp_chunk, frag_list);
sctp_chunk_free(chunk);
}
sctp_datamsg_put(msg);
return ERR_PTR(err);
}
/* Check whether this message has expired. */
int sctp_chunk_abandoned(struct sctp_chunk *chunk)
{
if (!chunk->asoc->peer.prsctp_capable)
return 0;
if (chunk->msg->abandoned)
return 1;
if (!chunk->has_tsn &&
!(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG))
return 0;
if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
time_after(jiffies, chunk->msg->expires_at)) {
struct sctp_stream_out *streamout =
&chunk->asoc->stream.out[chunk->sinfo.sinfo_stream];
if (chunk->sent_count) {
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
} else {
chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
}
chunk->msg->abandoned = 1;
return 1;
} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
struct sctp_stream_out *streamout =
&chunk->asoc->stream.out[chunk->sinfo.sinfo_stream];
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
chunk->msg->abandoned = 1;
return 1;
} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
chunk->msg->expires_at &&
time_after(jiffies, chunk->msg->expires_at)) {
chunk->msg->abandoned = 1;
return 1;
}
/* PRIO policy is processed by sendmsg, not here */
return 0;
}
/* This chunk (and consequently entire message) has failed in its sending. */
void sctp_chunk_fail(struct sctp_chunk *chunk, int error)
{
chunk->msg->send_failed = 1;
chunk->msg->send_error = error;
}