android_kernel_samsung_msm8976/net/phonet/pep.c

1578 lines
35 KiB
C
Raw Normal View History

/*
* File: pep.c
*
* Phonet pipe protocol end point socket
*
* Copyright (C) 2008 Nokia Corporation.
*
* Author: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*
* This program 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 this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
* 02110-1301 USA
*/
#include <linux/kernel.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/socket.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <asm/ioctls.h>
#include <linux/phonet.h>
#include <net/phonet/phonet.h>
#include <net/phonet/pep.h>
#include <net/phonet/gprs.h>
/* sk_state values:
* TCP_CLOSE sock not in use yet
* TCP_CLOSE_WAIT disconnected pipe
* TCP_LISTEN listening pipe endpoint
* TCP_SYN_RECV connected pipe in disabled state
* TCP_ESTABLISHED connected pipe in enabled state
*
* pep_sock locking:
* - sk_state, ackq, hlist: sock lock needed
* - listener: read only
* - pipe_handle: read only
*/
#define CREDITS_MAX 10
#define CREDITS_THR 7
static const struct sockaddr_pn pipe_srv = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9, /* pipe service */
};
#define pep_sb_size(s) (((s) + 5) & ~3) /* 2-bytes head, 32-bits aligned */
/* Get the next TLV sub-block. */
static unsigned char *pep_get_sb(struct sk_buff *skb, u8 *ptype, u8 *plen,
void *buf)
{
void *data = NULL;
struct {
u8 sb_type;
u8 sb_len;
} *ph, h;
int buflen = *plen;
ph = skb_header_pointer(skb, 0, 2, &h);
if (ph == NULL || ph->sb_len < 2 || !pskb_may_pull(skb, ph->sb_len))
return NULL;
ph->sb_len -= 2;
*ptype = ph->sb_type;
*plen = ph->sb_len;
if (buflen > ph->sb_len)
buflen = ph->sb_len;
data = skb_header_pointer(skb, 2, buflen, buf);
__skb_pull(skb, 2 + ph->sb_len);
return data;
}
static int pep_reply(struct sock *sk, struct sk_buff *oskb,
u8 code, const void *data, int len, gfp_t priority)
{
const struct pnpipehdr *oph = pnp_hdr(oskb);
struct pnpipehdr *ph;
struct sk_buff *skb;
#ifdef CONFIG_PHONET_PIPECTRLR
const struct phonethdr *hdr = pn_hdr(oskb);
struct sockaddr_pn spn = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9,
.spn_dev = hdr->pn_sdev,
.spn_obj = hdr->pn_sobj,
};
#endif
skb = alloc_skb(MAX_PNPIPE_HEADER + len, priority);
if (!skb)
return -ENOMEM;
skb_set_owner_w(skb, sk);
skb_reserve(skb, MAX_PNPIPE_HEADER);
__skb_put(skb, len);
skb_copy_to_linear_data(skb, data, len);
__skb_push(skb, sizeof(*ph));
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = oph->utid;
ph->message_id = oph->message_id + 1; /* REQ -> RESP */
ph->pipe_handle = oph->pipe_handle;
ph->error_code = code;
#ifdef CONFIG_PHONET_PIPECTRLR
return pn_skb_send(sk, skb, &spn);
#else
return pn_skb_send(sk, skb, &pipe_srv);
#endif
}
#define PAD 0x00
#ifdef CONFIG_PHONET_PIPECTRLR
static u8 pipe_negotiate_fc(u8 *host_fc, u8 *remote_fc, int len)
{
int i, j;
u8 base_fc, final_fc;
for (i = 0; i < len; i++) {
base_fc = host_fc[i];
for (j = 0; j < len; j++) {
if (remote_fc[j] == base_fc) {
final_fc = base_fc;
goto done;
}
}
}
return -EINVAL;
done:
return final_fc;
}
static int pipe_get_flow_info(struct sock *sk, struct sk_buff *skb,
u8 *pref_rx_fc, u8 *req_tx_fc)
{
struct pnpipehdr *hdr;
u8 n_sb;
if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
return -EINVAL;
hdr = pnp_hdr(skb);
n_sb = hdr->data[4];
__skb_pull(skb, sizeof(*hdr) + 4);
while (n_sb > 0) {
u8 type, buf[3], len = sizeof(buf);
u8 *data = pep_get_sb(skb, &type, &len, buf);
if (data == NULL)
return -EINVAL;
switch (type) {
case PN_PIPE_SB_REQUIRED_FC_TX:
if (len < 3 || (data[2] | data[3] | data[4]) > 3)
break;
req_tx_fc[0] = data[2];
req_tx_fc[1] = data[3];
req_tx_fc[2] = data[4];
break;
case PN_PIPE_SB_PREFERRED_FC_RX:
if (len < 3 || (data[2] | data[3] | data[4]) > 3)
break;
pref_rx_fc[0] = data[2];
pref_rx_fc[1] = data[3];
pref_rx_fc[2] = data[4];
break;
}
n_sb--;
}
return 0;
}
static int pipe_handler_send_req(struct sock *sk, u16 dobj, u8 utid,
u8 msg_id, u8 p_handle, gfp_t priority)
{
int len;
struct pnpipehdr *ph;
struct sk_buff *skb;
struct sockaddr_pn spn = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9,
.spn_dev = pn_dev(dobj),
.spn_obj = pn_obj(dobj),
};
static const u8 data[4] = {
PAD, PAD, PAD, PAD,
};
switch (msg_id) {
case PNS_PEP_CONNECT_REQ:
len = sizeof(data);
break;
case PNS_PEP_DISCONNECT_REQ:
case PNS_PEP_ENABLE_REQ:
case PNS_PEP_DISABLE_REQ:
len = 0;
break;
default:
return -EINVAL;
}
skb = alloc_skb(MAX_PNPIPE_HEADER + len, priority);
if (!skb)
return -ENOMEM;
skb_set_owner_w(skb, sk);
skb_reserve(skb, MAX_PNPIPE_HEADER);
if (len) {
__skb_put(skb, len);
skb_copy_to_linear_data(skb, data, len);
}
__skb_push(skb, sizeof(*ph));
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = utid;
ph->message_id = msg_id;
ph->pipe_handle = p_handle;
ph->error_code = PN_PIPE_NO_ERROR;
return pn_skb_send(sk, skb, &spn);
}
static int pipe_handler_send_created_ind(struct sock *sk, u16 dobj,
u8 utid, u8 p_handle, u8 msg_id, u8 tx_fc, u8 rx_fc)
{
int err_code;
struct pnpipehdr *ph;
struct sk_buff *skb;
struct sockaddr_pn spn = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9,
.spn_dev = pn_dev(dobj),
.spn_obj = pn_obj(dobj),
};
static u8 data[4] = {
0x03, 0x04,
};
data[2] = tx_fc;
data[3] = rx_fc;
/*
* actually, below is number of sub-blocks and not error code.
* Pipe_created_ind message format does not have any
* error code field. However, the Phonet stack will always send
* an error code as part of pnpipehdr. So, use that err_code to
* specify the number of sub-blocks.
*/
err_code = 0x01;
skb = alloc_skb(MAX_PNPIPE_HEADER + sizeof(data), GFP_ATOMIC);
if (!skb)
return -ENOMEM;
skb_set_owner_w(skb, sk);
skb_reserve(skb, MAX_PNPIPE_HEADER);
__skb_put(skb, sizeof(data));
skb_copy_to_linear_data(skb, data, sizeof(data));
__skb_push(skb, sizeof(*ph));
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = utid;
ph->message_id = msg_id;
ph->pipe_handle = p_handle;
ph->error_code = err_code;
return pn_skb_send(sk, skb, &spn);
}
static int pipe_handler_send_ind(struct sock *sk, u16 dobj, u8 utid,
u8 p_handle, u8 msg_id)
{
int err_code;
struct pnpipehdr *ph;
struct sk_buff *skb;
struct sockaddr_pn spn = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9,
.spn_dev = pn_dev(dobj),
.spn_obj = pn_obj(dobj),
};
/*
* actually, below is a filler.
* Pipe_enabled/disabled_ind message format does not have any
* error code field. However, the Phonet stack will always send
* an error code as part of pnpipehdr. So, use that err_code to
* specify the filler value.
*/
err_code = 0x0;
skb = alloc_skb(MAX_PNPIPE_HEADER, GFP_ATOMIC);
if (!skb)
return -ENOMEM;
skb_set_owner_w(skb, sk);
skb_reserve(skb, MAX_PNPIPE_HEADER);
__skb_push(skb, sizeof(*ph));
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = utid;
ph->message_id = msg_id;
ph->pipe_handle = p_handle;
ph->error_code = err_code;
return pn_skb_send(sk, skb, &spn);
}
static int pipe_handler_enable_pipe(struct sock *sk, int cmd)
{
int ret;
struct pep_sock *pn = pep_sk(sk);
switch (cmd) {
case PNPIPE_ENABLE:
ret = pipe_handler_send_req(sk, pn->pn_sk.sobject,
PNS_PIPE_ENABLE_UTID, PNS_PEP_ENABLE_REQ,
pn->pipe_handle, GFP_ATOMIC);
break;
case PNPIPE_DISABLE:
ret = pipe_handler_send_req(sk, pn->pn_sk.sobject,
PNS_PIPE_DISABLE_UTID, PNS_PEP_DISABLE_REQ,
pn->pipe_handle, GFP_ATOMIC);
break;
default:
ret = -EINVAL;
}
return ret;
}
static int pipe_handler_create_pipe(struct sock *sk, int pipe_handle, int cmd)
{
int ret;
struct pep_sock *pn = pep_sk(sk);
switch (cmd) {
case PNPIPE_CREATE:
ret = pipe_handler_send_req(sk, pn->pn_sk.sobject,
PNS_PEP_CONNECT_UTID, PNS_PEP_CONNECT_REQ,
pipe_handle, GFP_ATOMIC);
break;
case PNPIPE_DESTROY:
ret = pipe_handler_send_req(sk, pn->remote_pep,
PNS_PEP_DISCONNECT_UTID,
PNS_PEP_DISCONNECT_REQ,
pn->pipe_handle, GFP_ATOMIC);
break;
default:
ret = -EINVAL;
}
return ret;
}
#endif
static int pep_accept_conn(struct sock *sk, struct sk_buff *skb)
{
static const u8 data[20] = {
PAD, PAD, PAD, 2 /* sub-blocks */,
PN_PIPE_SB_REQUIRED_FC_TX, pep_sb_size(5), 3, PAD,
PN_MULTI_CREDIT_FLOW_CONTROL,
PN_ONE_CREDIT_FLOW_CONTROL,
PN_LEGACY_FLOW_CONTROL,
PAD,
PN_PIPE_SB_PREFERRED_FC_RX, pep_sb_size(5), 3, PAD,
PN_MULTI_CREDIT_FLOW_CONTROL,
PN_ONE_CREDIT_FLOW_CONTROL,
PN_LEGACY_FLOW_CONTROL,
PAD,
};
might_sleep();
return pep_reply(sk, skb, PN_PIPE_NO_ERROR, data, sizeof(data),
GFP_KERNEL);
}
static int pep_reject_conn(struct sock *sk, struct sk_buff *skb, u8 code)
{
static const u8 data[4] = { PAD, PAD, PAD, 0 /* sub-blocks */ };
WARN_ON(code == PN_PIPE_NO_ERROR);
return pep_reply(sk, skb, code, data, sizeof(data), GFP_ATOMIC);
}
/* Control requests are not sent by the pipe service and have a specific
* message format. */
static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code,
gfp_t priority)
{
const struct pnpipehdr *oph = pnp_hdr(oskb);
struct sk_buff *skb;
struct pnpipehdr *ph;
struct sockaddr_pn dst;
skb = alloc_skb(MAX_PNPIPE_HEADER + 4, priority);
if (!skb)
return -ENOMEM;
skb_set_owner_w(skb, sk);
skb_reserve(skb, MAX_PHONET_HEADER);
ph = (struct pnpipehdr *)skb_put(skb, sizeof(*ph) + 4);
ph->utid = oph->utid;
ph->message_id = PNS_PEP_CTRL_RESP;
ph->pipe_handle = oph->pipe_handle;
ph->data[0] = oph->data[1]; /* CTRL id */
ph->data[1] = oph->data[0]; /* PEP type */
ph->data[2] = code; /* error code, at an usual offset */
ph->data[3] = PAD;
ph->data[4] = PAD;
pn_skb_get_src_sockaddr(oskb, &dst);
return pn_skb_send(sk, skb, &dst);
}
static int pipe_snd_status(struct sock *sk, u8 type, u8 status, gfp_t priority)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *ph;
struct sk_buff *skb;
#ifdef CONFIG_PHONET_PIPECTRLR
struct sockaddr_pn spn = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9,
.spn_dev = pn_dev(pn->remote_pep),
.spn_obj = pn_obj(pn->remote_pep),
};
#endif
skb = alloc_skb(MAX_PNPIPE_HEADER + 4, priority);
if (!skb)
return -ENOMEM;
skb_set_owner_w(skb, sk);
skb_reserve(skb, MAX_PNPIPE_HEADER + 4);
__skb_push(skb, sizeof(*ph) + 4);
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = 0;
ph->message_id = PNS_PEP_STATUS_IND;
ph->pipe_handle = pn->pipe_handle;
ph->pep_type = PN_PEP_TYPE_COMMON;
ph->data[1] = type;
ph->data[2] = PAD;
ph->data[3] = PAD;
ph->data[4] = status;
#ifdef CONFIG_PHONET_PIPECTRLR
return pn_skb_send(sk, skb, &spn);
#else
return pn_skb_send(sk, skb, &pipe_srv);
#endif
}
/* Send our RX flow control information to the sender.
* Socket must be locked. */
static void pipe_grant_credits(struct sock *sk)
{
struct pep_sock *pn = pep_sk(sk);
BUG_ON(sk->sk_state != TCP_ESTABLISHED);
switch (pn->rx_fc) {
case PN_LEGACY_FLOW_CONTROL: /* TODO */
break;
case PN_ONE_CREDIT_FLOW_CONTROL:
pipe_snd_status(sk, PN_PEP_IND_FLOW_CONTROL,
PEP_IND_READY, GFP_ATOMIC);
pn->rx_credits = 1;
break;
case PN_MULTI_CREDIT_FLOW_CONTROL:
if ((pn->rx_credits + CREDITS_THR) > CREDITS_MAX)
break;
if (pipe_snd_status(sk, PN_PEP_IND_ID_MCFC_GRANT_CREDITS,
CREDITS_MAX - pn->rx_credits,
GFP_ATOMIC) == 0)
pn->rx_credits = CREDITS_MAX;
break;
}
}
static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *hdr;
int wake = 0;
if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
return -EINVAL;
hdr = pnp_hdr(skb);
if (hdr->data[0] != PN_PEP_TYPE_COMMON) {
LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n",
(unsigned)hdr->data[0]);
return -EOPNOTSUPP;
}
switch (hdr->data[1]) {
case PN_PEP_IND_FLOW_CONTROL:
switch (pn->tx_fc) {
case PN_LEGACY_FLOW_CONTROL:
switch (hdr->data[4]) {
case PEP_IND_BUSY:
atomic_set(&pn->tx_credits, 0);
break;
case PEP_IND_READY:
atomic_set(&pn->tx_credits, wake = 1);
break;
}
break;
case PN_ONE_CREDIT_FLOW_CONTROL:
if (hdr->data[4] == PEP_IND_READY)
atomic_set(&pn->tx_credits, wake = 1);
break;
}
break;
case PN_PEP_IND_ID_MCFC_GRANT_CREDITS:
if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL)
break;
atomic_add(wake = hdr->data[4], &pn->tx_credits);
break;
default:
LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP indication: %u\n",
(unsigned)hdr->data[1]);
return -EOPNOTSUPP;
}
if (wake)
sk->sk_write_space(sk);
return 0;
}
static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *hdr = pnp_hdr(skb);
u8 n_sb = hdr->data[0];
pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL;
__skb_pull(skb, sizeof(*hdr));
while (n_sb > 0) {
u8 type, buf[2], len = sizeof(buf);
u8 *data = pep_get_sb(skb, &type, &len, buf);
if (data == NULL)
return -EINVAL;
switch (type) {
case PN_PIPE_SB_NEGOTIATED_FC:
if (len < 2 || (data[0] | data[1]) > 3)
break;
pn->tx_fc = data[0] & 3;
pn->rx_fc = data[1] & 3;
break;
}
n_sb--;
}
return 0;
}
/* Queue an skb to a connected sock.
* Socket lock must be held. */
static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *hdr = pnp_hdr(skb);
struct sk_buff_head *queue;
int err = 0;
#ifdef CONFIG_PHONET_PIPECTRLR
struct phonethdr *ph = pn_hdr(skb);
static u8 host_pref_rx_fc[3], host_req_tx_fc[3];
u8 remote_pref_rx_fc[3], remote_req_tx_fc[3];
u8 negotiated_rx_fc, negotiated_tx_fc;
#endif
BUG_ON(sk->sk_state == TCP_CLOSE_WAIT);
switch (hdr->message_id) {
case PNS_PEP_CONNECT_REQ:
pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE);
break;
#ifdef CONFIG_PHONET_PIPECTRLR
case PNS_PEP_CONNECT_RESP:
if ((ph->pn_sdev == pn_dev(pn->remote_pep)) &&
(ph->pn_sobj == pn_obj(pn->remote_pep))) {
pipe_get_flow_info(sk, skb, remote_pref_rx_fc,
remote_req_tx_fc);
negotiated_tx_fc = pipe_negotiate_fc(remote_req_tx_fc,
host_pref_rx_fc,
sizeof(host_pref_rx_fc));
negotiated_rx_fc = pipe_negotiate_fc(host_req_tx_fc,
remote_pref_rx_fc,
sizeof(host_pref_rx_fc));
pn->pipe_state = PIPE_DISABLED;
pipe_handler_send_created_ind(sk, pn->remote_pep,
PNS_PIPE_CREATED_IND_UTID,
pn->pipe_handle, PNS_PIPE_CREATED_IND,
negotiated_tx_fc, negotiated_rx_fc);
pipe_handler_send_created_ind(sk, pn->pn_sk.sobject,
PNS_PIPE_CREATED_IND_UTID,
pn->pipe_handle, PNS_PIPE_CREATED_IND,
negotiated_tx_fc, negotiated_rx_fc);
} else {
pipe_handler_send_req(sk, pn->remote_pep,
PNS_PEP_CONNECT_UTID,
PNS_PEP_CONNECT_REQ, pn->pipe_handle,
GFP_ATOMIC);
pipe_get_flow_info(sk, skb, host_pref_rx_fc,
host_req_tx_fc);
}
break;
#endif
case PNS_PEP_DISCONNECT_REQ:
pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC);
sk->sk_state = TCP_CLOSE_WAIT;
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
break;
#ifdef CONFIG_PHONET_PIPECTRLR
case PNS_PEP_DISCONNECT_RESP:
pn->pipe_state = PIPE_IDLE;
pipe_handler_send_req(sk, pn->pn_sk.sobject,
PNS_PEP_DISCONNECT_UTID,
PNS_PEP_DISCONNECT_REQ, pn->pipe_handle,
GFP_KERNEL);
break;
#endif
case PNS_PEP_ENABLE_REQ:
/* Wait for PNS_PIPE_(ENABLED|REDIRECTED)_IND */
pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC);
break;
#ifdef CONFIG_PHONET_PIPECTRLR
case PNS_PEP_ENABLE_RESP:
if ((ph->pn_sdev == pn_dev(pn->remote_pep)) &&
(ph->pn_sobj == pn_obj(pn->remote_pep))) {
pn->pipe_state = PIPE_ENABLED;
pipe_handler_send_ind(sk, pn->remote_pep,
PNS_PIPE_ENABLED_IND_UTID,
pn->pipe_handle, PNS_PIPE_ENABLED_IND);
pipe_handler_send_ind(sk, pn->pn_sk.sobject,
PNS_PIPE_ENABLED_IND_UTID,
pn->pipe_handle, PNS_PIPE_ENABLED_IND);
} else
pipe_handler_send_req(sk, pn->remote_pep,
PNS_PIPE_ENABLE_UTID,
PNS_PEP_ENABLE_REQ, pn->pipe_handle,
GFP_KERNEL);
break;
#endif
case PNS_PEP_RESET_REQ:
switch (hdr->state_after_reset) {
case PN_PIPE_DISABLE:
pn->init_enable = 0;
break;
case PN_PIPE_ENABLE:
pn->init_enable = 1;
break;
default: /* not allowed to send an error here!? */
err = -EINVAL;
goto out;
}
/* fall through */
case PNS_PEP_DISABLE_REQ:
atomic_set(&pn->tx_credits, 0);
pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC);
break;
#ifdef CONFIG_PHONET_PIPECTRLR
case PNS_PEP_DISABLE_RESP:
if ((ph->pn_sdev == pn_dev(pn->remote_pep)) &&
(ph->pn_sobj == pn_obj(pn->remote_pep))) {
pn->pipe_state = PIPE_DISABLED;
pipe_handler_send_ind(sk, pn->remote_pep,
PNS_PIPE_DISABLED_IND_UTID,
pn->pipe_handle,
PNS_PIPE_DISABLED_IND);
pipe_handler_send_ind(sk, pn->pn_sk.sobject,
PNS_PIPE_DISABLED_IND_UTID,
pn->pipe_handle,
PNS_PIPE_DISABLED_IND);
} else
pipe_handler_send_req(sk, pn->remote_pep,
PNS_PIPE_DISABLE_UTID,
PNS_PEP_DISABLE_REQ, pn->pipe_handle,
GFP_KERNEL);
break;
#endif
case PNS_PEP_CTRL_REQ:
if (skb_queue_len(&pn->ctrlreq_queue) >= PNPIPE_CTRLREQ_MAX) {
atomic_inc(&sk->sk_drops);
break;
}
__skb_pull(skb, 4);
queue = &pn->ctrlreq_queue;
goto queue;
case PNS_PIPE_ALIGNED_DATA:
__skb_pull(skb, 1);
/* fall through */
case PNS_PIPE_DATA:
__skb_pull(skb, 3); /* Pipe data header */
if (!pn_flow_safe(pn->rx_fc)) {
err = sock_queue_rcv_skb(sk, skb);
if (!err)
return 0;
break;
}
if (pn->rx_credits == 0) {
atomic_inc(&sk->sk_drops);
err = -ENOBUFS;
break;
}
pn->rx_credits--;
queue = &sk->sk_receive_queue;
goto queue;
case PNS_PEP_STATUS_IND:
pipe_rcv_status(sk, skb);
break;
case PNS_PIPE_REDIRECTED_IND:
err = pipe_rcv_created(sk, skb);
break;
case PNS_PIPE_CREATED_IND:
err = pipe_rcv_created(sk, skb);
if (err)
break;
/* fall through */
case PNS_PIPE_RESET_IND:
if (!pn->init_enable)
break;
/* fall through */
case PNS_PIPE_ENABLED_IND:
if (!pn_flow_safe(pn->tx_fc)) {
atomic_set(&pn->tx_credits, 1);
sk->sk_write_space(sk);
}
if (sk->sk_state == TCP_ESTABLISHED)
break; /* Nothing to do */
sk->sk_state = TCP_ESTABLISHED;
pipe_grant_credits(sk);
break;
case PNS_PIPE_DISABLED_IND:
sk->sk_state = TCP_SYN_RECV;
pn->rx_credits = 0;
break;
default:
LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP message: %u\n",
hdr->message_id);
err = -EINVAL;
}
out:
kfree_skb(skb);
return err;
queue:
skb->dev = NULL;
skb_set_owner_r(skb, sk);
err = skb->len;
skb_queue_tail(queue, skb);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk, err);
return 0;
}
/* Destroy connected sock. */
static void pipe_destruct(struct sock *sk)
{
struct pep_sock *pn = pep_sk(sk);
skb_queue_purge(&sk->sk_receive_queue);
skb_queue_purge(&pn->ctrlreq_queue);
}
static int pep_connreq_rcv(struct sock *sk, struct sk_buff *skb)
{
struct sock *newsk;
struct pep_sock *newpn, *pn = pep_sk(sk);
struct pnpipehdr *hdr;
struct sockaddr_pn dst;
u16 peer_type;
u8 pipe_handle, enabled, n_sb;
u8 aligned = 0;
if (!pskb_pull(skb, sizeof(*hdr) + 4))
return -EINVAL;
hdr = pnp_hdr(skb);
pipe_handle = hdr->pipe_handle;
switch (hdr->state_after_connect) {
case PN_PIPE_DISABLE:
enabled = 0;
break;
case PN_PIPE_ENABLE:
enabled = 1;
break;
default:
pep_reject_conn(sk, skb, PN_PIPE_ERR_INVALID_PARAM);
return -EINVAL;
}
peer_type = hdr->other_pep_type << 8;
if (unlikely(sk->sk_state != TCP_LISTEN) || sk_acceptq_is_full(sk)) {
pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE);
return -ENOBUFS;
}
/* Parse sub-blocks (options) */
n_sb = hdr->data[4];
while (n_sb > 0) {
u8 type, buf[1], len = sizeof(buf);
const u8 *data = pep_get_sb(skb, &type, &len, buf);
if (data == NULL)
return -EINVAL;
switch (type) {
case PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE:
if (len < 1)
return -EINVAL;
peer_type = (peer_type & 0xff00) | data[0];
break;
case PN_PIPE_SB_ALIGNED_DATA:
aligned = data[0] != 0;
break;
}
n_sb--;
}
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb)
return -ENOMEM;
/* Create a new to-be-accepted sock */
newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_ATOMIC, sk->sk_prot);
if (!newsk) {
kfree_skb(skb);
return -ENOMEM;
}
sock_init_data(NULL, newsk);
newsk->sk_state = TCP_SYN_RECV;
newsk->sk_backlog_rcv = pipe_do_rcv;
newsk->sk_protocol = sk->sk_protocol;
newsk->sk_destruct = pipe_destruct;
newpn = pep_sk(newsk);
pn_skb_get_dst_sockaddr(skb, &dst);
newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst);
newpn->pn_sk.resource = pn->pn_sk.resource;
skb_queue_head_init(&newpn->ctrlreq_queue);
newpn->pipe_handle = pipe_handle;
atomic_set(&newpn->tx_credits, 0);
newpn->peer_type = peer_type;
newpn->rx_credits = 0;
newpn->rx_fc = newpn->tx_fc = PN_LEGACY_FLOW_CONTROL;
newpn->init_enable = enabled;
newpn->aligned = aligned;
#ifdef CONFIG_PHONET_PIPECTRLR
newpn->remote_pep = pn->remote_pep;
#endif
BUG_ON(!skb_queue_empty(&newsk->sk_receive_queue));
skb_queue_head(&newsk->sk_receive_queue, skb);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk, 0);
sk_acceptq_added(sk);
sk_add_node(newsk, &pn->ackq);
return 0;
}
/* Listening sock must be locked */
static struct sock *pep_find_pipe(const struct hlist_head *hlist,
const struct sockaddr_pn *dst,
u8 pipe_handle)
{
struct hlist_node *node;
struct sock *sknode;
u16 dobj = pn_sockaddr_get_object(dst);
sk_for_each(sknode, node, hlist) {
struct pep_sock *pnnode = pep_sk(sknode);
/* Ports match, but addresses might not: */
if (pnnode->pn_sk.sobject != dobj)
continue;
if (pnnode->pipe_handle != pipe_handle)
continue;
if (sknode->sk_state == TCP_CLOSE_WAIT)
continue;
sock_hold(sknode);
return sknode;
}
return NULL;
}
/*
* Deliver an skb to a listening sock.
* Socket lock must be held.
* We then queue the skb to the right connected sock (if any).
*/
static int pep_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
struct sock *sknode;
struct pnpipehdr *hdr;
struct sockaddr_pn dst;
int err = NET_RX_SUCCESS;
u8 pipe_handle;
if (!pskb_may_pull(skb, sizeof(*hdr)))
goto drop;
hdr = pnp_hdr(skb);
pipe_handle = hdr->pipe_handle;
if (pipe_handle == PN_PIPE_INVALID_HANDLE)
goto drop;
pn_skb_get_dst_sockaddr(skb, &dst);
/* Look for an existing pipe handle */
sknode = pep_find_pipe(&pn->hlist, &dst, pipe_handle);
if (sknode)
return sk_receive_skb(sknode, skb, 1);
/* Look for a pipe handle pending accept */
sknode = pep_find_pipe(&pn->ackq, &dst, pipe_handle);
if (sknode) {
sock_put(sknode);
if (net_ratelimit())
printk(KERN_WARNING"Phonet unconnected PEP ignored");
err = NET_RX_DROP;
goto drop;
}
switch (hdr->message_id) {
case PNS_PEP_CONNECT_REQ:
err = pep_connreq_rcv(sk, skb);
break;
case PNS_PEP_DISCONNECT_REQ:
pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC);
break;
case PNS_PEP_CTRL_REQ:
pep_ctrlreq_error(sk, skb, PN_PIPE_INVALID_HANDLE, GFP_ATOMIC);
break;
case PNS_PEP_RESET_REQ:
case PNS_PEP_ENABLE_REQ:
case PNS_PEP_DISABLE_REQ:
/* invalid handle is not even allowed here! */
default:
err = NET_RX_DROP;
}
drop:
kfree_skb(skb);
return err;
}
static int pipe_do_remove(struct sock *sk)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *ph;
struct sk_buff *skb;
skb = alloc_skb(MAX_PNPIPE_HEADER, GFP_KERNEL);
if (!skb)
return -ENOMEM;
skb_reserve(skb, MAX_PNPIPE_HEADER);
__skb_push(skb, sizeof(*ph));
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = 0;
ph->message_id = PNS_PIPE_REMOVE_REQ;
ph->pipe_handle = pn->pipe_handle;
ph->data[0] = PAD;
return pn_skb_send(sk, skb, &pipe_srv);
}
/* associated socket ceases to exist */
static void pep_sock_close(struct sock *sk, long timeout)
{
struct pep_sock *pn = pep_sk(sk);
int ifindex = 0;
sock_hold(sk); /* keep a reference after sk_common_release() */
sk_common_release(sk);
lock_sock(sk);
if (sk->sk_state == TCP_LISTEN) {
/* Destroy the listen queue */
struct sock *sknode;
struct hlist_node *p, *n;
sk_for_each_safe(sknode, p, n, &pn->ackq)
sk_del_node_init(sknode);
sk->sk_state = TCP_CLOSE;
} else if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED))
/* Forcefully remove dangling Phonet pipe */
pipe_do_remove(sk);
ifindex = pn->ifindex;
pn->ifindex = 0;
release_sock(sk);
if (ifindex)
gprs_detach(sk);
sock_put(sk);
}
static int pep_wait_connreq(struct sock *sk, int noblock)
{
struct task_struct *tsk = current;
struct pep_sock *pn = pep_sk(sk);
long timeo = sock_rcvtimeo(sk, noblock);
for (;;) {
DEFINE_WAIT(wait);
if (sk->sk_state != TCP_LISTEN)
return -EINVAL;
if (!hlist_empty(&pn->ackq))
break;
if (!timeo)
return -EWOULDBLOCK;
if (signal_pending(tsk))
return sock_intr_errno(timeo);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
finish_wait(sk_sleep(sk), &wait);
}
return 0;
}
static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
{
struct pep_sock *pn = pep_sk(sk);
struct sock *newsk = NULL;
struct sk_buff *oskb;
int err;
lock_sock(sk);
err = pep_wait_connreq(sk, flags & O_NONBLOCK);
if (err)
goto out;
newsk = __sk_head(&pn->ackq);
oskb = skb_dequeue(&newsk->sk_receive_queue);
err = pep_accept_conn(newsk, oskb);
if (err) {
skb_queue_head(&newsk->sk_receive_queue, oskb);
newsk = NULL;
goto out;
}
kfree_skb(oskb);
sock_hold(sk);
pep_sk(newsk)->listener = sk;
sock_hold(newsk);
sk_del_node_init(newsk);
sk_acceptq_removed(sk);
sk_add_node(newsk, &pn->hlist);
__sock_put(newsk);
out:
release_sock(sk);
*errp = err;
return newsk;
}
static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
struct pep_sock *pn = pep_sk(sk);
int answ;
switch (cmd) {
case SIOCINQ:
if (sk->sk_state == TCP_LISTEN)
return -EINVAL;
lock_sock(sk);
if (sock_flag(sk, SOCK_URGINLINE) &&
!skb_queue_empty(&pn->ctrlreq_queue))
answ = skb_peek(&pn->ctrlreq_queue)->len;
else if (!skb_queue_empty(&sk->sk_receive_queue))
answ = skb_peek(&sk->sk_receive_queue)->len;
else
answ = 0;
release_sock(sk);
return put_user(answ, (int __user *)arg);
}
return -ENOIOCTLCMD;
}
static int pep_init(struct sock *sk)
{
struct pep_sock *pn = pep_sk(sk);
INIT_HLIST_HEAD(&pn->ackq);
INIT_HLIST_HEAD(&pn->hlist);
skb_queue_head_init(&pn->ctrlreq_queue);
pn->pipe_handle = PN_PIPE_INVALID_HANDLE;
return 0;
}
static int pep_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct pep_sock *pn = pep_sk(sk);
int val = 0, err = 0;
#ifdef CONFIG_PHONET_PIPECTRLR
int remote_pep;
int pipe_handle;
#endif
if (level != SOL_PNPIPE)
return -ENOPROTOOPT;
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
}
lock_sock(sk);
switch (optname) {
#ifdef CONFIG_PHONET_PIPECTRLR
case PNPIPE_CREATE:
if (val) {
if (pn->pipe_state > PIPE_IDLE) {
err = -EFAULT;
break;
}
remote_pep = val & 0xFFFF;
pipe_handle = (val >> 16) & 0xFF;
pn->remote_pep = remote_pep;
err = pipe_handler_create_pipe(sk, pipe_handle,
PNPIPE_CREATE);
break;
}
case PNPIPE_ENABLE:
if (pn->pipe_state != PIPE_DISABLED) {
err = -EFAULT;
break;
}
err = pipe_handler_enable_pipe(sk, PNPIPE_ENABLE);
break;
case PNPIPE_DISABLE:
if (pn->pipe_state != PIPE_ENABLED) {
err = -EFAULT;
break;
}
err = pipe_handler_enable_pipe(sk, PNPIPE_DISABLE);
break;
case PNPIPE_DESTROY:
if (pn->pipe_state < PIPE_DISABLED) {
err = -EFAULT;
break;
}
err = pipe_handler_create_pipe(sk, 0x0, PNPIPE_DESTROY);
break;
#endif
case PNPIPE_ENCAP:
if (val && val != PNPIPE_ENCAP_IP) {
err = -EINVAL;
break;
}
if (!pn->ifindex == !val)
break; /* Nothing to do! */
if (!capable(CAP_NET_ADMIN)) {
err = -EPERM;
break;
}
if (val) {
release_sock(sk);
err = gprs_attach(sk);
if (err > 0) {
pn->ifindex = err;
err = 0;
}
} else {
pn->ifindex = 0;
release_sock(sk);
gprs_detach(sk);
err = 0;
}
goto out_norel;
default:
err = -ENOPROTOOPT;
}
release_sock(sk);
out_norel:
return err;
}
static int pep_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct pep_sock *pn = pep_sk(sk);
int len, val;
if (level != SOL_PNPIPE)
return -ENOPROTOOPT;
if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
case PNPIPE_ENCAP:
val = pn->ifindex ? PNPIPE_ENCAP_IP : PNPIPE_ENCAP_NONE;
break;
#ifdef CONFIG_PHONET_PIPECTRLR
case PNPIPE_INQ:
val = pn->pipe_state;
break;
#endif
case PNPIPE_IFINDEX:
val = pn->ifindex;
break;
default:
return -ENOPROTOOPT;
}
len = min_t(unsigned int, sizeof(int), len);
if (put_user(len, optlen))
return -EFAULT;
if (put_user(val, (int __user *) optval))
return -EFAULT;
return 0;
}
static int pipe_skb_send(struct sock *sk, struct sk_buff *skb)
{
struct pep_sock *pn = pep_sk(sk);
struct pnpipehdr *ph;
int err;
#ifdef CONFIG_PHONET_PIPECTRLR
struct sockaddr_pn spn = {
.spn_family = AF_PHONET,
.spn_resource = 0xD9,
.spn_dev = pn_dev(pn->remote_pep),
.spn_obj = pn_obj(pn->remote_pep),
};
#endif
if (pn_flow_safe(pn->tx_fc) &&
!atomic_add_unless(&pn->tx_credits, -1, 0)) {
kfree_skb(skb);
return -ENOBUFS;
}
skb_push(skb, 3 + pn->aligned);
skb_reset_transport_header(skb);
ph = pnp_hdr(skb);
ph->utid = 0;
if (pn->aligned) {
ph->message_id = PNS_PIPE_ALIGNED_DATA;
ph->data[0] = 0; /* padding */
} else
ph->message_id = PNS_PIPE_DATA;
ph->pipe_handle = pn->pipe_handle;
#ifdef CONFIG_PHONET_PIPECTRLR
err = pn_skb_send(sk, skb, &spn);
#else
err = pn_skb_send(sk, skb, &pipe_srv);
#endif
if (err && pn_flow_safe(pn->tx_fc))
atomic_inc(&pn->tx_credits);
return err;
}
static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len)
{
struct pep_sock *pn = pep_sk(sk);
struct sk_buff *skb;
long timeo;
int flags = msg->msg_flags;
int err, done;
if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL|
MSG_CMSG_COMPAT)) ||
!(msg->msg_flags & MSG_EOR))
return -EOPNOTSUPP;
skb = sock_alloc_send_skb(sk, MAX_PNPIPE_HEADER + len,
flags & MSG_DONTWAIT, &err);
if (!skb)
return err;
skb_reserve(skb, MAX_PHONET_HEADER + 3);
err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
if (err < 0)
goto outfree;
lock_sock(sk);
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
if ((1 << sk->sk_state) & (TCPF_LISTEN|TCPF_CLOSE)) {
err = -ENOTCONN;
goto out;
}
if (sk->sk_state != TCP_ESTABLISHED) {
/* Wait until the pipe gets to enabled state */
disabled:
err = sk_stream_wait_connect(sk, &timeo);
if (err)
goto out;
if (sk->sk_state == TCP_CLOSE_WAIT) {
err = -ECONNRESET;
goto out;
}
}
BUG_ON(sk->sk_state != TCP_ESTABLISHED);
/* Wait until flow control allows TX */
done = atomic_read(&pn->tx_credits);
while (!done) {
DEFINE_WAIT(wait);
if (!timeo) {
err = -EAGAIN;
goto out;
}
if (signal_pending(current)) {
err = sock_intr_errno(timeo);
goto out;
}
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits));
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
finish_wait(sk_sleep(sk), &wait);
if (sk->sk_state != TCP_ESTABLISHED)
goto disabled;
}
err = pipe_skb_send(sk, skb);
if (err >= 0)
err = len; /* success! */
skb = NULL;
out:
release_sock(sk);
outfree:
kfree_skb(skb);
return err;
}
int pep_writeable(struct sock *sk)
{
struct pep_sock *pn = pep_sk(sk);
return atomic_read(&pn->tx_credits);
}
int pep_write(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *rskb, *fs;
int flen = 0;
if (pep_sk(sk)->aligned)
return pipe_skb_send(sk, skb);
rskb = alloc_skb(MAX_PNPIPE_HEADER, GFP_ATOMIC);
if (!rskb) {
kfree_skb(skb);
return -ENOMEM;
}
skb_shinfo(rskb)->frag_list = skb;
rskb->len += skb->len;
rskb->data_len += rskb->len;
rskb->truesize += rskb->len;
/* Avoid nested fragments */
skb_walk_frags(skb, fs)
flen += fs->len;
skb->next = skb_shinfo(skb)->frag_list;
skb_frag_list_init(skb);
skb->len -= flen;
skb->data_len -= flen;
skb->truesize -= flen;
skb_reserve(rskb, MAX_PHONET_HEADER + 3);
return pipe_skb_send(sk, rskb);
}
struct sk_buff *pep_read(struct sock *sk)
{
struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
if (sk->sk_state == TCP_ESTABLISHED)
pipe_grant_credits(sk);
return skb;
}
static int pep_recvmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len, int noblock,
int flags, int *addr_len)
{
struct sk_buff *skb;
int err;
if (flags & ~(MSG_OOB|MSG_PEEK|MSG_TRUNC|MSG_DONTWAIT|MSG_WAITALL|
MSG_NOSIGNAL|MSG_CMSG_COMPAT))
return -EOPNOTSUPP;
if (unlikely(1 << sk->sk_state & (TCPF_LISTEN | TCPF_CLOSE)))
return -ENOTCONN;
if ((flags & MSG_OOB) || sock_flag(sk, SOCK_URGINLINE)) {
/* Dequeue and acknowledge control request */
struct pep_sock *pn = pep_sk(sk);
if (flags & MSG_PEEK)
return -EOPNOTSUPP;
skb = skb_dequeue(&pn->ctrlreq_queue);
if (skb) {
pep_ctrlreq_error(sk, skb, PN_PIPE_NO_ERROR,
GFP_KERNEL);
msg->msg_flags |= MSG_OOB;
goto copy;
}
if (flags & MSG_OOB)
return -EINVAL;
}
skb = skb_recv_datagram(sk, flags, noblock, &err);
lock_sock(sk);
if (skb == NULL) {
if (err == -ENOTCONN && sk->sk_state == TCP_CLOSE_WAIT)
err = -ECONNRESET;
release_sock(sk);
return err;
}
if (sk->sk_state == TCP_ESTABLISHED)
pipe_grant_credits(sk);
release_sock(sk);
copy:
msg->msg_flags |= MSG_EOR;
if (skb->len > len)
msg->msg_flags |= MSG_TRUNC;
else
len = skb->len;
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
if (!err)
err = (flags & MSG_TRUNC) ? skb->len : len;
skb_free_datagram(sk, skb);
return err;
}
static void pep_sock_unhash(struct sock *sk)
{
struct pep_sock *pn = pep_sk(sk);
struct sock *skparent = NULL;
lock_sock(sk);
if ((1 << sk->sk_state) & ~(TCPF_CLOSE|TCPF_LISTEN)) {
skparent = pn->listener;
release_sock(sk);
pn = pep_sk(skparent);
lock_sock(skparent);
sk_del_node_init(sk);
sk = skparent;
}
/* Unhash a listening sock only when it is closed
* and all of its active connected pipes are closed. */
if (hlist_empty(&pn->hlist))
pn_sock_unhash(&pn->pn_sk.sk);
release_sock(sk);
if (skparent)
sock_put(skparent);
}
static struct proto pep_proto = {
.close = pep_sock_close,
.accept = pep_sock_accept,
.ioctl = pep_ioctl,
.init = pep_init,
.setsockopt = pep_setsockopt,
.getsockopt = pep_getsockopt,
.sendmsg = pep_sendmsg,
.recvmsg = pep_recvmsg,
.backlog_rcv = pep_do_rcv,
.hash = pn_sock_hash,
.unhash = pep_sock_unhash,
.get_port = pn_sock_get_port,
.obj_size = sizeof(struct pep_sock),
.owner = THIS_MODULE,
.name = "PNPIPE",
};
static struct phonet_protocol pep_pn_proto = {
.ops = &phonet_stream_ops,
.prot = &pep_proto,
.sock_type = SOCK_SEQPACKET,
};
static int __init pep_register(void)
{
return phonet_proto_register(PN_PROTO_PIPE, &pep_pn_proto);
}
static void __exit pep_unregister(void)
{
phonet_proto_unregister(PN_PROTO_PIPE, &pep_pn_proto);
}
module_init(pep_register);
module_exit(pep_unregister);
MODULE_AUTHOR("Remi Denis-Courmont, Nokia");
MODULE_DESCRIPTION("Phonet pipe protocol");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_PHONET, PN_PROTO_PIPE);