cregit-Linux how code gets into the kernel

Release 4.11 net/9p/trans_fd.c

Directory: net/9p
/*
 * 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 <linux/slab.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

/**
 * 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;
	
int 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_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);
}


Contributors
PersonTokensPropCommitsCommitProp
Tejun Heo8382.18%150.00%


Eric Van Hensbergen1817.82%150.00%


Total101100.00%2100.00%



/**
 * 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;
	unsigned long flags;
	LIST_HEAD(cancel_list);

	p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err);

	spin_lock_irqsave(&m->client->lock, flags);

	if (m->err) {
		spin_unlock_irqrestore(&m->client->lock, flags);
		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);
	}
	spin_unlock_irqrestore(&m->client->lock, flags);

	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);
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen16786.98%562.50%


Dominique Martinet157.81%112.50%


Latchesar Ionkov84.17%112.50%


Joe Perches21.04%112.50%


Total192100.00%8100.00%





static int

p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt)
{
	int ret, n;
	struct p9_trans_fd *ts = NULL;

	if (client && client->status == Connected)
		ts = client->trans;

	if (!ts)
		return -EREMOTEIO;

	if (!ts->rd->f_op->poll)
		return -EIO;

	if (!ts->wr->f_op->poll)
		return -EIO;

	ret = ts->rd->f_op->poll(ts->rd, pt);
	if (ret < 0)
		return ret;

	if (ts->rd != ts->wr) {
		n = ts->wr->f_op->poll(ts->wr, pt);
		if (n < 0)
			return n;
		ret = (ret & ~POLLOUT) | (n & ~POLLIN);
	}

	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen15090.36%480.00%


Tejun Heo169.64%120.00%


Total166100.00%5100.00%



/**
 * 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;

	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");

	ret = kernel_read(ts->rd, ts->rd->f_pos, v, len);
	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
		client->status = Disconnected;
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen10589.74%250.00%


Tejun Heo119.40%125.00%


Joe Perches10.85%125.00%


Total117100.00%4100.00%



/**
 * 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)
{
	int n, 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");

		err = p9_parse_header(&m->rc, NULL, 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");
		spin_lock(&m->client->lock);
		if (m->req->status != REQ_STATUS_ERROR)
			status = REQ_STATUS_RCVD;
		list_del(&m->req->req_list);
		spin_unlock(&m->client->lock);
		p9_client_cb(m->client, m->req, status);
		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 = POLLIN;
		else
			n = p9_fd_poll(m->client, NULL);

		if ((n & POLLIN) && !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);
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen48767.27%746.67%


Dominique Martinet15921.96%320.00%


Simon Derr283.87%16.67%


Latchesar Ionkov243.31%16.67%


Tejun Heo172.35%213.33%


Joe Perches91.24%16.67%


Total724100.00%15100.00%



/**
 * 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)
{
	int ret;
	mm_segment_t oldfs;
	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");

	oldfs = get_fs();
	set_fs(get_ds());
	/* The cast to a user pointer is valid due to the set_fs() */
	ret = vfs_write(ts->wr, (__force void __user *)v, len, &ts->wr->f_pos);
	set_fs(oldfs);

	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
		client->status = Disconnected;
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen14298.61%360.00%


Joe Perches10.69%120.00%


Hannes Eder10.69%120.00%


Total144100.00%5100.00%



/**
 * 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)
{
	int n, 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 = POLLOUT;
		else
			n = p9_fd_poll(m->client, NULL);

		if ((n & POLLOUT) &&
		   !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);
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen37687.24%545.45%


Simon Derr429.74%327.27%


Latchesar Ionkov81.86%19.09%


Joe Perches40.93%19.09%


Tejun Heo10.23%19.09%


Total431100.00%11100.00%






static int p9_pollwake(wait_queue_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;
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen8993.68%250.00%


Tejun Heo55.26%125.00%


Eric Dumazet11.05%125.00%


Total95100.00%4100.00%



/**
 * 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);
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen13699.27%266.67%


Joe Perches10.73%133.33%


Total137100.00%3100.00%



/**
 * 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)
{
	int 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);
	if (n & POLLIN) {
		p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
		set_bit(Rpending, &m->wsched);
	}

	if (n & POLLOUT) {
		p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
		set_bit(Wpending, &m->wsched);
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen16290.00%360.00%


Simon Derr158.33%120.00%


Joe Perches31.67%120.00%


Total180100.00%5100.00%



/**
 * 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)
{
	int n;

	if (m->err < 0)
		return;

	n = p9_fd_poll(m->client, NULL);
	if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) {
		p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n);
		if (n >= 0)
			n = -ECONNRESET;
		p9_conn_cancel(m, n);
	}

	if (n & POLLIN) {
		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 & POLLOUT) {
		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);
		}
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen20796.73%360.00%


Joe Perches52.34%120.00%


Tejun Heo20.93%120.00%


Total214100.00%5100.00%



/**
 * 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)
{
	int 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 = POLLOUT;
	else
		n = p9_fd_poll(m->client, NULL);

	if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
		schedule_work(&m->wq);

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Van Hensbergen15092.02%969.23%


Latchesar Ionkov106.13%17.69%


Simon Derr10.61%17.69%


Joe Perches10.61%17.69%


Tejun Heo10.61%17.69%


Total163100.00%13100.00%






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->