linux/net/9p/trans_fd.c

1140 lines
26 KiB
C
Raw Normal View History

/*
* linux/fs/9p/trans_fd.c
*
* Fd transport layer. Includes deprecated socket layer.
*
* Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
* Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
* Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.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:
* Free Software Foundation
* 51 Franklin Street, Fifth Floor
* Boston, MA 02111-1301 USA
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/ipv6.h>
#include <linux/kthread.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/un.h>
#include <linux/uaccess.h>
#include <linux/inet.h>
#include <linux/idr.h>
#include <linux/file.h>
#include <linux/parser.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 <linux/seq_file.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include <net/9p/transport.h>
#include <linux/syscalls.h> /* killme */
#define P9_PORT 564
#define MAX_SOCK_BUF (64*1024)
#define MAXPOLLWADDR 2
static struct p9_trans_module p9_tcp_trans;
static struct p9_trans_module p9_fd_trans;
/**
* struct p9_fd_opts - per-transport options
* @rfd: file descriptor for reading (trans=fd)
* @wfd: file descriptor for writing (trans=fd)
* @port: port to connect to (trans=tcp)
*
*/
struct p9_fd_opts {
int rfd;
int wfd;
u16 port;
bool privport;
};
/*
* Option Parsing (code inspired by NFS code)
* - a little lazy - parse all fd-transport options
*/
enum {
/* Options that take integer arguments */
Opt_port, Opt_rfdno, Opt_wfdno, Opt_err,
/* Options that take no arguments */
Opt_privport,
};
static const match_table_t tokens = {
{Opt_port, "port=%u"},
{Opt_rfdno, "rfdno=%u"},
{Opt_wfdno, "wfdno=%u"},
{Opt_privport, "privport"},
{Opt_err, NULL},
};
enum {
Rworksched = 1, /* read work scheduled or running */
Rpending = 2, /* can read */
Wworksched = 4, /* write work scheduled or running */
Wpending = 8, /* can write */
};
struct p9_poll_wait {
struct p9_conn *conn;
wait_queue_entry_t wait;
wait_queue_head_t *wait_addr;
};
/**
* struct p9_conn - fd mux connection state information
* @mux_list: list link for mux to manage multiple connections (?)
* @client: reference to client instance for this connection
* @err: error state
* @req_list: accounting for requests which have been sent
* @unsent_req_list: accounting for requests that haven't been sent
* @req: current request being processed (if any)
* @tmp_buf: temporary buffer to read in header
* @rc: temporary fcall for reading current frame
* @wpos: write position for current frame
* @wsize: amount of data to write for current frame
* @wbuf: current write buffer
* @poll_pending_link: pending links to be polled per conn
* @poll_wait: array of wait_q's for various worker threads
* @pt: poll state
* @rq: current read work
* @wq: current write work
* @wsched: ????
*
*/
struct p9_conn {
struct list_head mux_list;
struct p9_client *client;
int err;
struct list_head req_list;
struct list_head unsent_req_list;
struct p9_req_t *req;
char tmp_buf[7];
struct p9_fcall rc;
int wpos;
int wsize;
char *wbuf;
struct list_head poll_pending_link;
struct p9_poll_wait poll_wait[MAXPOLLWADDR];
poll_table pt;
struct work_struct rq;
struct work_struct wq;
unsigned long wsched;
};
/**
* struct p9_trans_fd - transport state
* @rd: reference to file to read from
* @wr: reference of file to write to
* @conn: connection state reference
*
*/
struct p9_trans_fd {
struct file *rd;
struct file *wr;
struct p9_conn conn;
};
static void p9_poll_workfn(struct work_struct *work);
static DEFINE_SPINLOCK(p9_poll_lock);
static LIST_HEAD(p9_poll_pending_list);
static DECLARE_WORK(p9_poll_work, p9_poll_workfn);
static unsigned int p9_ipport_resv_min = P9_DEF_MIN_RESVPORT;
static unsigned int p9_ipport_resv_max = P9_DEF_MAX_RESVPORT;
static void p9_mux_poll_stop(struct p9_conn *m)
{
unsigned long flags;
int i;
for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
struct p9_poll_wait *pwait = &m->poll_wait[i];
if (pwait->wait_addr) {
remove_wait_queue(pwait->wait_addr, &pwait->wait);
pwait->wait_addr = NULL;
}
}
spin_lock_irqsave(&p9_poll_lock, flags);
list_del_init(&m->poll_pending_link);
spin_unlock_irqrestore(&p9_poll_lock, flags);
flush_work(&p9_poll_work);
}
/**
* p9_conn_cancel - cancel all pending requests with error
* @m: mux data
* @err: error code
*
*/
static void p9_conn_cancel(struct p9_conn *m, int err)
{
struct p9_req_t *req, *rtmp;
LIST_HEAD(cancel_list);
p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err);
spin_lock(&m->client->lock);
if (m->err) {
spin_unlock(&m->client->lock);
return;
}
m->err = err;
list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
list_move(&req->req_list, &cancel_list);
}
list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) {
list_move(&req->req_list, &cancel_list);
}
list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req);
list_del(&req->req_list);
if (!req->t_err)
req->t_err = err;
p9_client_cb(m->client, req, REQ_STATUS_ERROR);
}
spin_unlock(&m->client->lock);
}
static __poll_t
p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
{
__poll_t ret;
struct p9_trans_fd *ts = NULL;
if (client && client->status == Connected)
ts = client->trans;
if (!ts) {
if (err)
*err = -EREMOTEIO;
return EPOLLERR;
}
ret = vfs_poll(ts->rd, pt);
if (ts->rd != ts->wr)
ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN);
return ret;
}
/**
* p9_fd_read- read from a fd
* @client: client instance
* @v: buffer to receive data into
* @len: size of receive buffer
*
*/
static int p9_fd_read(struct p9_client *client, void *v, int len)
{
int ret;
struct p9_trans_fd *ts = NULL;
loff_t pos;
if (client && client->status != Disconnected)
ts = client->trans;
if (!ts)
return -EREMOTEIO;
if (!(ts->rd->f_flags & O_NONBLOCK))
p9_debug(P9_DEBUG_ERROR, "blocking read ...\n");
pos = ts->rd->f_pos;
ret = kernel_read(ts->rd, v, len, &pos);
if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
client->status = Disconnected;
return ret;
}
/**
* p9_read_work - called when there is some data to be read from a transport
* @work: container of work to be done
*
*/
static void p9_read_work(struct work_struct *work)
{
__poll_t n;
int err;
struct p9_conn *m;
int status = REQ_STATUS_ERROR;
m = container_of(work, struct p9_conn, rq);
if (m->err < 0)
return;
p9_debug(P9_DEBUG_TRANS, "start mux %p pos %zd\n", m, m->rc.offset);
if (!m->rc.sdata) {
m->rc.sdata = m->tmp_buf;
m->rc.offset = 0;
m->rc.capacity = 7; /* start by reading header */
}
clear_bit(Rpending, &m->wsched);
p9_debug(P9_DEBUG_TRANS, "read mux %p pos %zd size: %zd = %zd\n",
m, m->rc.offset, m->rc.capacity,
m->rc.capacity - m->rc.offset);
err = p9_fd_read(m->client, m->rc.sdata + m->rc.offset,
m->rc.capacity - m->rc.offset);
p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err);
if (err == -EAGAIN)
goto end_clear;
if (err <= 0)
goto error;
m->rc.offset += err;
/* header read in */
if ((!m->req) && (m->rc.offset == m->rc.capacity)) {
p9_debug(P9_DEBUG_TRANS, "got new header\n");
/* Header size */
m->rc.size = 7;
err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0);
if (err) {
p9_debug(P9_DEBUG_ERROR,
"error parsing header: %d\n", err);
goto error;
}
if (m->rc.size >= m->client->msize) {
p9_debug(P9_DEBUG_ERROR,
"requested packet size too big: %d\n",
m->rc.size);
err = -EIO;
goto error;
}
p9_debug(P9_DEBUG_TRANS,
"mux %p pkt: size: %d bytes tag: %d\n",
m, m->rc.size, m->rc.tag);
m->req = p9_tag_lookup(m->client, m->rc.tag);
if (!m->req || (m->req->status != REQ_STATUS_SENT)) {
p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
m->rc.tag);
err = -EIO;
goto error;
}
if (m->req->rc == NULL) {
p9_debug(P9_DEBUG_ERROR,
"No recv fcall for tag %d (req %p), disconnecting!\n",
m->rc.tag, m->req);
m->req = NULL;
err = -EIO;
goto error;
}
m->rc.sdata = (char *)m->req->rc + sizeof(struct p9_fcall);
memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity);
m->rc.capacity = m->rc.size;
}
/* packet is read in
* not an else because some packets (like clunk) have no payload
*/
if ((m->req) && (m->rc.offset == m->rc.capacity)) {
p9_debug(P9_DEBUG_TRANS, "got new packet\n");
m->req->rc->size = m->rc.offset;
spin_lock(&m->client->lock);
if (m->req->status != REQ_STATUS_ERROR)
status = REQ_STATUS_RCVD;
list_del(&m->req->req_list);
/* update req->status while holding client->lock */
p9_client_cb(m->client, m->req, status);
spin_unlock(&m->client->lock);
m->rc.sdata = NULL;
m->rc.offset = 0;
m->rc.capacity = 0;
m->req = NULL;
}
end_clear:
clear_bit(Rworksched, &m->wsched);
if (!list_empty(&m->req_list)) {
if (test_and_clear_bit(Rpending, &m->wsched))
n = EPOLLIN;
else
n = p9_fd_poll(m->client, NULL, NULL);
if ((n & EPOLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) {
p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
schedule_work(&m->rq);
}
}
return;
error:
p9_conn_cancel(m, err);
clear_bit(Rworksched, &m->wsched);
}
/**
* p9_fd_write - write to a socket
* @client: client instance
* @v: buffer to send data from
* @len: size of send buffer
*
*/
static int p9_fd_write(struct p9_client *client, void *v, int len)
{
ssize_t ret;
struct p9_trans_fd *ts = NULL;
if (client && client->status != Disconnected)
ts = client->trans;
if (!ts)
return -EREMOTEIO;
if (!(ts->wr->f_flags & O_NONBLOCK))
p9_debug(P9_DEBUG_ERROR, "blocking write ...\n");
ret = kernel_write(ts->wr, v, len, &ts->wr->f_pos);
if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
client->status = Disconnected;
return ret;
}
/**
* p9_write_work - called when a transport can send some data
* @work: container for work to be done
*
*/
static void p9_write_work(struct work_struct *work)
{
__poll_t n;
int err;
struct p9_conn *m;
struct p9_req_t *req;
m = container_of(work, struct p9_conn, wq);
if (m->err < 0) {
clear_bit(Wworksched, &m->wsched);
return;
}
if (!m->wsize) {
spin_lock(&m->client->lock);
if (list_empty(&m->unsent_req_list)) {
clear_bit(Wworksched, &m->wsched);
spin_unlock(&m->client->lock);
return;
}
req = list_entry(m->unsent_req_list.next, struct p9_req_t,
req_list);
req->status = REQ_STATUS_SENT;
p9_debug(P9_DEBUG_TRANS, "move req %p\n", req);
list_move_tail(&req->req_list, &m->req_list);
m->wbuf = req->tc->sdata;
m->wsize = req->tc->size;
m->wpos = 0;
spin_unlock(&m->client->lock);
}
p9_debug(P9_DEBUG_TRANS, "mux %p pos %d size %d\n",
m, m->wpos, m->wsize);
clear_bit(Wpending, &m->wsched);
err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos);
p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err);
if (err == -EAGAIN)
goto end_clear;
if (err < 0)
goto error;
else if (err == 0) {
err = -EREMOTEIO;
goto error;
}
m->wpos += err;
if (m->wpos == m->wsize)
m->wpos = m->wsize = 0;
end_clear:
clear_bit(Wworksched, &m->wsched);
if (m->wsize || !list_empty(&m->unsent_req_list)) {
if (test_and_clear_bit(Wpending, &m->wsched))
n = EPOLLOUT;
else
n = p9_fd_poll(m->client, NULL, NULL);
if ((n & EPOLLOUT) &&
!test_and_set_bit(Wworksched, &m->wsched)) {
p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m);
schedule_work(&m->wq);
}
}
return;
error:
p9_conn_cancel(m, err);
clear_bit(Wworksched, &m->wsched);
}
static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key)
{
struct p9_poll_wait *pwait =
container_of(wait, struct p9_poll_wait, wait);
struct p9_conn *m = pwait->conn;
unsigned long flags;
spin_lock_irqsave(&p9_poll_lock, flags);
if (list_empty(&m->poll_pending_link))
list_add_tail(&m->poll_pending_link, &p9_poll_pending_list);
spin_unlock_irqrestore(&p9_poll_lock, flags);
schedule_work(&p9_poll_work);
return 1;
}
/**
* p9_pollwait - add poll task to the wait queue
* @filp: file pointer being polled
* @wait_address: wait_q to block on
* @p: poll state
*
* called by files poll operation to add v9fs-poll task to files wait queue
*/
static void
p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p)
{
struct p9_conn *m = container_of(p, struct p9_conn, pt);
struct p9_poll_wait *pwait = NULL;
int i;
for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) {
if (m->poll_wait[i].wait_addr == NULL) {
pwait = &m->poll_wait[i];
break;
}
}
if (!pwait) {
p9_debug(P9_DEBUG_ERROR, "not enough wait_address slots\n");
return;
}
pwait->conn = m;
pwait->wait_addr = wait_address;
init_waitqueue_func_entry(&pwait->wait, p9_pollwake);
add_wait_queue(wait_address, &pwait->wait);
}
/**
* p9_conn_create - initialize the per-session mux data
* @client: client instance
*
* Note: Creates the polling task if this is the first session.
*/
static void p9_conn_create(struct p9_client *client)
{
__poll_t n;
struct p9_trans_fd *ts = client->trans;
struct p9_conn *m = &ts->conn;
p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize);
INIT_LIST_HEAD(&m->mux_list);
m->client = client;
INIT_LIST_HEAD(&m->req_list);
INIT_LIST_HEAD(&m->unsent_req_list);
INIT_WORK(&m->rq, p9_read_work);
INIT_WORK(&m->wq, p9_write_work);
INIT_LIST_HEAD(&m->poll_pending_link);
init_poll_funcptr(&m->pt, p9_pollwait);
n = p9_fd_poll(client, &m->pt, NULL);
if (n & EPOLLIN) {
p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
set_bit(Rpending, &m->wsched);
}
if (n & EPOLLOUT) {
p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
set_bit(Wpending, &m->wsched);
}
}
/**
* p9_poll_mux - polls a mux and schedules read or write works if necessary
* @m: connection to poll
*
*/
static void p9_poll_mux(struct p9_conn *m)
{
__poll_t n;
int err = -ECONNRESET;
if (m->err < 0)
return;
n = p9_fd_poll(m->client, NULL, &err);
if (n & (EPOLLERR | EPOLLHUP | EPOLLNVAL)) {
p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n);
p9_conn_cancel(m, err);
}
if (n & EPOLLIN) {
set_bit(Rpending, &m->wsched);
p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
if (!test_and_set_bit(Rworksched, &m->wsched)) {
p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
schedule_work(&m->rq);
}
}
if (n & EPOLLOUT) {
set_bit(Wpending, &m->wsched);
p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
if ((m->wsize || !list_empty(&m->unsent_req_list)) &&
!test_and_set_bit(Wworksched, &m->wsched)) {
p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m);
schedule_work(&m->wq);
}
}
}
/**
* p9_fd_request - send 9P request
* The function can sleep until the request is scheduled for sending.
* The function can be interrupted. Return from the function is not
* a guarantee that the request is sent successfully.
*
* @client: client instance
* @req: request to be sent
*
*/
static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
{
__poll_t n;
struct p9_trans_fd *ts = client->trans;
struct p9_conn *m = &ts->conn;
p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n",
m, current, req->tc, req->tc->id);
if (m->err < 0)
return m->err;
spin_lock(&client->lock);
req->status = REQ_STATUS_UNSENT;
list_add_tail(&req->req_list, &m->unsent_req_list);
spin_unlock(&client->lock);
if (test_and_clear_bit(Wpending, &m->wsched))
n = EPOLLOUT;
else
n = p9_fd_poll(m->client, NULL, NULL);
if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
schedule_work(&m->wq);
return 0;
}
static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
{
int ret = 1;
p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
spin_lock(&client->lock);
if (req->status == REQ_STATUS_UNSENT) {
list_del(&req->req_list);
req->status = REQ_STATUS_FLSHD;
ret = 0;
}
spin_unlock(&client->lock);
return ret;
}
static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
{
p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
/* we haven't received a response for oldreq,
* remove it from the list.
*/
spin_lock(&client->lock);
list_del(&req->req_list);
spin_unlock(&client->lock);
return 0;
}
static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt)
{
if (clnt->trans_mod == &p9_tcp_trans) {
if (clnt->trans_opts.tcp.port != P9_PORT)
seq_printf(m, ",port=%u", clnt->trans_opts.tcp.port);
} else if (clnt->trans_mod == &p9_fd_trans) {
if (clnt->trans_opts.fd.rfd != ~0)
seq_printf(m, ",rfd=%u", clnt->trans_opts.fd.rfd);
if (clnt->trans_opts.fd.wfd != ~0)
seq_printf(m, ",wfd=%u", clnt->trans_opts.fd.wfd);
}
return 0;
}
/**
* parse_opts - parse mount options into p9_fd_opts structure
* @params: options string passed from mount
* @opts: fd transport-specific structure to parse options into
*
* Returns 0 upon success, -ERRNO upon failure
*/
static int parse_opts(char *params, struct p9_fd_opts *opts)
{
char *p;
substring_t args[MAX_OPT_ARGS];
int option;
char *options, *tmp_options;
opts->port = P9_PORT;
opts->rfd = ~0;
opts->wfd = ~0;
opts->privport = false;
if (!params)
return 0;
tmp_options = kstrdup(params, GFP_KERNEL);
if (!tmp_options) {
p9_debug(P9_DEBUG_ERROR,
"failed to allocate copy of option string\n");
return -ENOMEM;
}
options = tmp_options;
while ((p = strsep(&options, ",")) != NULL) {
int token;
int r;
if (!*p)
continue;
token = match_token(p, tokens, args);
if ((token != Opt_err) && (token != Opt_privport)) {
r = match_int(&args[0], &option);
if (r < 0) {
p9_debug(P9_DEBUG_ERROR,
"integer field, but no integer?\n");
continue;
}
}
switch (token) {
case Opt_port:
opts->port = option;
break;
case Opt_rfdno:
opts->rfd = option;
break;
case Opt_wfdno:
opts->wfd = option;
break;
case Opt_privport:
opts->privport = true;
break;
default:
continue;
}
}
kfree(tmp_options);
return 0;
}
static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
{
struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd),
GFP_KERNEL);
if (!ts)
return -ENOMEM;
ts->rd = fget(rfd);
ts->wr = fget(wfd);
if (!ts->rd || !ts->wr) {
if (ts->rd)
fput(ts->rd);
if (ts->wr)
fput(ts->wr);
kfree(ts);
return -EIO;
}
client->trans = ts;
client->status = Connected;
return 0;
}
static int p9_socket_open(struct p9_client *client, struct socket *csocket)
{
struct p9_trans_fd *p;
struct file *file;
p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL);
if (!p)
return -ENOMEM;
csocket->sk->sk_allocation = GFP_NOIO;
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull vfs update from Al Viro: - big one - consolidation of descriptor-related logics; almost all of that is moved to fs/file.c (BTW, I'm seriously tempted to rename the result to fd.c. As it is, we have a situation when file_table.c is about handling of struct file and file.c is about handling of descriptor tables; the reasons are historical - file_table.c used to be about a static array of struct file we used to have way back). A lot of stray ends got cleaned up and converted to saner primitives, disgusting mess in android/binder.c is still disgusting, but at least doesn't poke so much in descriptor table guts anymore. A bunch of relatively minor races got fixed in process, plus an ext4 struct file leak. - related thing - fget_light() partially unuglified; see fdget() in there (and yes, it generates the code as good as we used to have). - also related - bits of Cyrill's procfs stuff that got entangled into that work; _not_ all of it, just the initial move to fs/proc/fd.c and switch of fdinfo to seq_file. - Alex's fs/coredump.c spiltoff - the same story, had been easier to take that commit than mess with conflicts. The rest is a separate pile, this was just a mechanical code movement. - a few misc patches all over the place. Not all for this cycle, there'll be more (and quite a few currently sit in akpm's tree)." Fix up trivial conflicts in the android binder driver, and some fairly simple conflicts due to two different changes to the sock_alloc_file() interface ("take descriptor handling from sock_alloc_file() to callers" vs "net: Providing protocol type via system.sockprotoname xattr of /proc/PID/fd entries" adding a dentry name to the socket) * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits) MAX_LFS_FILESIZE should be a loff_t compat: fs: Generic compat_sys_sendfile implementation fs: push rcu_barrier() from deactivate_locked_super() to filesystems btrfs: reada_extent doesn't need kref for refcount coredump: move core dump functionality into its own file coredump: prevent double-free on an error path in core dumper usb/gadget: fix misannotations fcntl: fix misannotations ceph: don't abuse d_delete() on failure exits hypfs: ->d_parent is never NULL or negative vfs: delete surplus inode NULL check switch simple cases of fget_light to fdget new helpers: fdget()/fdput() switch o2hb_region_dev_write() to fget_light() proc_map_files_readdir(): don't bother with grabbing files make get_file() return its argument vhost_set_vring(): turn pollstart/pollstop into bool switch prctl_set_mm_exe_file() to fget_light() switch xfs_find_handle() to fget_light() switch xfs_swapext() to fget_light() ...
2012-10-03 11:25:04 +08:00
file = sock_alloc_file(csocket, 0, NULL);
if (IS_ERR(file)) {
pr_err("%s (%d): failed to map fd\n",
__func__, task_pid_nr(current));
kfree(p);
return PTR_ERR(file);
}
get_file(file);
p->wr = p->rd = file;
client->trans = p;
client->status = Connected;
p->rd->f_flags |= O_NONBLOCK;
p9_conn_create(client);
return 0;
}
/**
* p9_mux_destroy - cancels all pending requests of mux
* @m: mux to destroy
*
*/
static void p9_conn_destroy(struct p9_conn *m)
{
p9_debug(P9_DEBUG_TRANS, "mux %p prev %p next %p\n",
m, m->mux_list.prev, m->mux_list.next);
p9_mux_poll_stop(m);
cancel_work_sync(&m->rq);
cancel_work_sync(&m->wq);
p9_conn_cancel(m, -ECONNRESET);
m->client = NULL;
}
/**
* p9_fd_close - shutdown file descriptor transport
* @client: client instance
*
*/
static void p9_fd_close(struct p9_client *client)
{
struct p9_trans_fd *ts;
if (!client)
return;
ts = client->trans;
if (!ts)
return;
client->status = Disconnected;
p9_conn_destroy(&ts->conn);
if (ts->rd)
fput(ts->rd);
if (ts->wr)
fput(ts->wr);
kfree(ts);
}
/*
* stolen from NFS - maybe should be made a generic function?
*/
static inline int valid_ipaddr4(const char *buf)
{
int rc, count, in[4];
rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
if (rc != 4)
return -EINVAL;
for (count = 0; count < 4; count++) {
if (in[count] > 255)
return -EINVAL;
}
return 0;
}
static int p9_bind_privport(struct socket *sock)
{
struct sockaddr_in cl;
int port, err = -EINVAL;
memset(&cl, 0, sizeof(cl));
cl.sin_family = AF_INET;
cl.sin_addr.s_addr = INADDR_ANY;
for (port = p9_ipport_resv_max; port >= p9_ipport_resv_min; port--) {
cl.sin_port = htons((ushort)port);
err = kernel_bind(sock, (struct sockaddr *)&cl, sizeof(cl));
if (err != -EADDRINUSE)
break;
}
return err;
}
static int
p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
{
int err;
struct socket *csocket;
struct sockaddr_in sin_server;
struct p9_fd_opts opts;
err = parse_opts(args, &opts);
if (err < 0)
return err;
if (addr == NULL || valid_ipaddr4(addr) < 0)
return -EINVAL;
csocket = NULL;
client->trans_opts.tcp.port = opts.port;
client->trans_opts.tcp.privport = opts.privport;
sin_server.sin_family = AF_INET;
sin_server.sin_addr.s_addr = in_aton(addr);
sin_server.sin_port = htons(opts.port);
err = __sock_create(current->nsproxy->net_ns, PF_INET,
SOCK_STREAM, IPPROTO_TCP, &csocket, 1);
if (err) {
pr_err("%s (%d): problem creating socket\n",
__func__, task_pid_nr(current));
return err;
}
if (opts.privport) {
err = p9_bind_privport(csocket);
if (err < 0) {
pr_err("%s (%d): problem binding to privport\n",
__func__, task_pid_nr(current));
sock_release(csocket);
return err;
}
}
err = csocket->ops->connect(csocket,
(struct sockaddr *)&sin_server,
sizeof(struct sockaddr_in), 0);
if (err < 0) {
pr_err("%s (%d): problem connecting socket to %s\n",
__func__, task_pid_nr(current), addr);
sock_release(csocket);
return err;
}
return p9_socket_open(client, csocket);
}
static int
p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
{
int err;
struct socket *csocket;
struct sockaddr_un sun_server;
csocket = NULL;
if (addr == NULL)
return -EINVAL;
if (strlen(addr) >= UNIX_PATH_MAX) {
pr_err("%s (%d): address too long: %s\n",
__func__, task_pid_nr(current), addr);
return -ENAMETOOLONG;
}
sun_server.sun_family = PF_UNIX;
strcpy(sun_server.sun_path, addr);
err = __sock_create(current->nsproxy->net_ns, PF_UNIX,
SOCK_STREAM, 0, &csocket, 1);
if (err < 0) {
pr_err("%s (%d): problem creating socket\n",
__func__, task_pid_nr(current));
return err;
}
err = csocket->ops->connect(csocket, (struct sockaddr *)&sun_server,
sizeof(struct sockaddr_un) - 1, 0);
if (err < 0) {
pr_err("%s (%d): problem connecting socket: %s: %d\n",
__func__, task_pid_nr(current), addr, err);
sock_release(csocket);
return err;
}
return p9_socket_open(client, csocket);
}
static int
p9_fd_create(struct p9_client *client, const char *addr, char *args)
{
int err;
struct p9_fd_opts opts;
parse_opts(args, &opts);
client->trans_opts.fd.rfd = opts.rfd;
client->trans_opts.fd.wfd = opts.wfd;
if (opts.rfd == ~0 || opts.wfd == ~0) {
pr_err("Insufficient options for proto=fd\n");
return -ENOPROTOOPT;
}
err = p9_fd_open(client, opts.rfd, opts.wfd);
if (err < 0)
return err;
p9_conn_create(client);
return 0;
}
static struct p9_trans_module p9_tcp_trans = {
.name = "tcp",
.maxsize = MAX_SOCK_BUF,
.def = 0,
.create = p9_fd_create_tcp,
.close = p9_fd_close,
.request = p9_fd_request,
.cancel = p9_fd_cancel,
.cancelled = p9_fd_cancelled,
.show_options = p9_fd_show_options,
.owner = THIS_MODULE,
};
static struct p9_trans_module p9_unix_trans = {
.name = "unix",
.maxsize = MAX_SOCK_BUF,
.def = 0,
.create = p9_fd_create_unix,
.close = p9_fd_close,
.request = p9_fd_request,
.cancel = p9_fd_cancel,
.cancelled = p9_fd_cancelled,
.show_options = p9_fd_show_options,
.owner = THIS_MODULE,
};
static struct p9_trans_module p9_fd_trans = {
.name = "fd",
.maxsize = MAX_SOCK_BUF,
.def = 0,
.create = p9_fd_create,
.close = p9_fd_close,
.request = p9_fd_request,
.cancel = p9_fd_cancel,
.cancelled = p9_fd_cancelled,
.show_options = p9_fd_show_options,
.owner = THIS_MODULE,
};
/**
* p9_poll_workfn - poll worker thread
* @work: work queue
*
* polls all v9fs transports for new events and queues the appropriate
* work to the work queue
*
*/
static void p9_poll_workfn(struct work_struct *work)
{
unsigned long flags;
p9_debug(P9_DEBUG_TRANS, "start %p\n", current);
spin_lock_irqsave(&p9_poll_lock, flags);
while (!list_empty(&p9_poll_pending_list)) {
struct p9_conn *conn = list_first_entry(&p9_poll_pending_list,
struct p9_conn,
poll_pending_link);
list_del_init(&conn->poll_pending_link);
spin_unlock_irqrestore(&p9_poll_lock, flags);
p9_poll_mux(conn);
spin_lock_irqsave(&p9_poll_lock, flags);
}
spin_unlock_irqrestore(&p9_poll_lock, flags);
p9_debug(P9_DEBUG_TRANS, "finish\n");
}
int p9_trans_fd_init(void)
{
v9fs_register_trans(&p9_tcp_trans);
v9fs_register_trans(&p9_unix_trans);
v9fs_register_trans(&p9_fd_trans);
return 0;
}
void p9_trans_fd_exit(void)
{
workqueue: deprecate flush[_delayed]_work_sync() flush[_delayed]_work_sync() are now spurious. Mark them deprecated and convert all users to flush[_delayed]_work(). If you're cc'd and wondering what's going on: Now all workqueues are non-reentrant and the regular flushes guarantee that the work item is not pending or running on any CPU on return, so there's no reason to use the sync flushes at all and they're going away. This patch doesn't make any functional difference. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Ian Campbell <ian.campbell@citrix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Mattia Dongili <malattia@linux.it> Cc: Kent Yoder <key@linux.vnet.ibm.com> Cc: David Airlie <airlied@linux.ie> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Karsten Keil <isdn@linux-pingi.de> Cc: Bryan Wu <bryan.wu@canonical.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: Florian Tobias Schandinat <FlorianSchandinat@gmx.de> Cc: David Woodhouse <dwmw2@infradead.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: linux-wireless@vger.kernel.org Cc: Anton Vorontsov <cbou@mail.ru> Cc: Sangbeom Kim <sbkim73@samsung.com> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Takashi Iwai <tiwai@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Avi Kivity <avi@redhat.com>
2012-08-21 05:51:24 +08:00
flush_work(&p9_poll_work);
v9fs_unregister_trans(&p9_tcp_trans);
v9fs_unregister_trans(&p9_unix_trans);
v9fs_unregister_trans(&p9_fd_trans);
}