linux/drivers/xen/evtchn.c
Arnd Bergmann 6038f373a3 llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.

The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.

New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time.  Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.

The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.

Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.

Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.

===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
//   but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}

@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}

@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
   *off = E
|
   *off += E
|
   func(..., off, ...)
|
   E = *off
)
...+>
}

@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}

@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
  *off = E
|
  *off += E
|
  func(..., off, ...)
|
  E = *off
)
...+>
}

@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}

@ fops0 @
identifier fops;
@@
struct file_operations fops = {
 ...
};

@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
 .llseek = llseek_f,
...
};

@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
 .read = read_f,
...
};

@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
 .write = write_f,
...
};

@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
 .open = open_f,
...
};

// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
...  .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};

@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
...  .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};

// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
...  .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};

// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};

// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};

@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+	.llseek = default_llseek, /* write accesses f_pos */
};

// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////

@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
 .write = write_f,
 .read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};

@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};

@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};

@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-10-15 15:53:27 +02:00

508 lines
12 KiB
C

/******************************************************************************
* evtchn.c
*
* Driver for receiving and demuxing event-channel signals.
*
* Copyright (c) 2004-2005, K A Fraser
* Multi-process extensions Copyright (c) 2004, Steven Smith
*
* 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; or, when distributed
* separately from the Linux kernel or incorporated into other
* software packages, subject to the following license:
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this source file (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy, modify,
* merge, publish, distribute, sublicense, and/or sell copies of the Software,
* and to permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/major.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/poll.h>
#include <linux/irq.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/cpu.h>
#include <xen/xen.h>
#include <xen/events.h>
#include <xen/evtchn.h>
#include <asm/xen/hypervisor.h>
struct per_user_data {
struct mutex bind_mutex; /* serialize bind/unbind operations */
/* Notification ring, accessed via /dev/xen/evtchn. */
#define EVTCHN_RING_SIZE (PAGE_SIZE / sizeof(evtchn_port_t))
#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
evtchn_port_t *ring;
unsigned int ring_cons, ring_prod, ring_overflow;
struct mutex ring_cons_mutex; /* protect against concurrent readers */
/* Processes wait on this queue when ring is empty. */
wait_queue_head_t evtchn_wait;
struct fasync_struct *evtchn_async_queue;
const char *name;
};
/* Who's bound to each port? */
static struct per_user_data *port_user[NR_EVENT_CHANNELS];
static DEFINE_SPINLOCK(port_user_lock); /* protects port_user[] and ring_prod */
irqreturn_t evtchn_interrupt(int irq, void *data)
{
unsigned int port = (unsigned long)data;
struct per_user_data *u;
spin_lock(&port_user_lock);
u = port_user[port];
disable_irq_nosync(irq);
if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
u->ring[EVTCHN_RING_MASK(u->ring_prod)] = port;
wmb(); /* Ensure ring contents visible */
if (u->ring_cons == u->ring_prod++) {
wake_up_interruptible(&u->evtchn_wait);
kill_fasync(&u->evtchn_async_queue,
SIGIO, POLL_IN);
}
} else {
u->ring_overflow = 1;
}
spin_unlock(&port_user_lock);
return IRQ_HANDLED;
}
static ssize_t evtchn_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
int rc;
unsigned int c, p, bytes1 = 0, bytes2 = 0;
struct per_user_data *u = file->private_data;
/* Whole number of ports. */
count &= ~(sizeof(evtchn_port_t)-1);
if (count == 0)
return 0;
if (count > PAGE_SIZE)
count = PAGE_SIZE;
for (;;) {
mutex_lock(&u->ring_cons_mutex);
rc = -EFBIG;
if (u->ring_overflow)
goto unlock_out;
c = u->ring_cons;
p = u->ring_prod;
if (c != p)
break;
mutex_unlock(&u->ring_cons_mutex);
if (file->f_flags & O_NONBLOCK)
return -EAGAIN;
rc = wait_event_interruptible(u->evtchn_wait,
u->ring_cons != u->ring_prod);
if (rc)
return rc;
}
/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
sizeof(evtchn_port_t);
bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
} else {
bytes1 = (p - c) * sizeof(evtchn_port_t);
bytes2 = 0;
}
/* Truncate chunks according to caller's maximum byte count. */
if (bytes1 > count) {
bytes1 = count;
bytes2 = 0;
} else if ((bytes1 + bytes2) > count) {
bytes2 = count - bytes1;
}
rc = -EFAULT;
rmb(); /* Ensure that we see the port before we copy it. */
if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
((bytes2 != 0) &&
copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
goto unlock_out;
u->ring_cons += (bytes1 + bytes2) / sizeof(evtchn_port_t);
rc = bytes1 + bytes2;
unlock_out:
mutex_unlock(&u->ring_cons_mutex);
return rc;
}
static ssize_t evtchn_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
int rc, i;
evtchn_port_t *kbuf = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
struct per_user_data *u = file->private_data;
if (kbuf == NULL)
return -ENOMEM;
/* Whole number of ports. */
count &= ~(sizeof(evtchn_port_t)-1);
rc = 0;
if (count == 0)
goto out;
if (count > PAGE_SIZE)
count = PAGE_SIZE;
rc = -EFAULT;
if (copy_from_user(kbuf, buf, count) != 0)
goto out;
spin_lock_irq(&port_user_lock);
for (i = 0; i < (count/sizeof(evtchn_port_t)); i++)
if ((kbuf[i] < NR_EVENT_CHANNELS) && (port_user[kbuf[i]] == u))
enable_irq(irq_from_evtchn(kbuf[i]));
spin_unlock_irq(&port_user_lock);
rc = count;
out:
free_page((unsigned long)kbuf);
return rc;
}
static int evtchn_bind_to_user(struct per_user_data *u, int port)
{
int rc = 0;
/*
* Ports are never reused, so every caller should pass in a
* unique port.
*
* (Locking not necessary because we haven't registered the
* interrupt handler yet, and our caller has already
* serialized bind operations.)
*/
BUG_ON(port_user[port] != NULL);
port_user[port] = u;
rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, IRQF_DISABLED,
u->name, (void *)(unsigned long)port);
if (rc >= 0)
rc = 0;
return rc;
}
static void evtchn_unbind_from_user(struct per_user_data *u, int port)
{
int irq = irq_from_evtchn(port);
unbind_from_irqhandler(irq, (void *)(unsigned long)port);
/* make sure we unbind the irq handler before clearing the port */
barrier();
port_user[port] = NULL;
}
static long evtchn_ioctl(struct file *file,
unsigned int cmd, unsigned long arg)
{
int rc;
struct per_user_data *u = file->private_data;
void __user *uarg = (void __user *) arg;
/* Prevent bind from racing with unbind */
mutex_lock(&u->bind_mutex);
switch (cmd) {
case IOCTL_EVTCHN_BIND_VIRQ: {
struct ioctl_evtchn_bind_virq bind;
struct evtchn_bind_virq bind_virq;
rc = -EFAULT;
if (copy_from_user(&bind, uarg, sizeof(bind)))
break;
bind_virq.virq = bind.virq;
bind_virq.vcpu = 0;
rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
&bind_virq);
if (rc != 0)
break;
rc = evtchn_bind_to_user(u, bind_virq.port);
if (rc == 0)
rc = bind_virq.port;
break;
}
case IOCTL_EVTCHN_BIND_INTERDOMAIN: {
struct ioctl_evtchn_bind_interdomain bind;
struct evtchn_bind_interdomain bind_interdomain;
rc = -EFAULT;
if (copy_from_user(&bind, uarg, sizeof(bind)))
break;
bind_interdomain.remote_dom = bind.remote_domain;
bind_interdomain.remote_port = bind.remote_port;
rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
&bind_interdomain);
if (rc != 0)
break;
rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
if (rc == 0)
rc = bind_interdomain.local_port;
break;
}
case IOCTL_EVTCHN_BIND_UNBOUND_PORT: {
struct ioctl_evtchn_bind_unbound_port bind;
struct evtchn_alloc_unbound alloc_unbound;
rc = -EFAULT;
if (copy_from_user(&bind, uarg, sizeof(bind)))
break;
alloc_unbound.dom = DOMID_SELF;
alloc_unbound.remote_dom = bind.remote_domain;
rc = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
&alloc_unbound);
if (rc != 0)
break;
rc = evtchn_bind_to_user(u, alloc_unbound.port);
if (rc == 0)
rc = alloc_unbound.port;
break;
}
case IOCTL_EVTCHN_UNBIND: {
struct ioctl_evtchn_unbind unbind;
rc = -EFAULT;
if (copy_from_user(&unbind, uarg, sizeof(unbind)))
break;
rc = -EINVAL;
if (unbind.port >= NR_EVENT_CHANNELS)
break;
spin_lock_irq(&port_user_lock);
rc = -ENOTCONN;
if (port_user[unbind.port] != u) {
spin_unlock_irq(&port_user_lock);
break;
}
evtchn_unbind_from_user(u, unbind.port);
spin_unlock_irq(&port_user_lock);
rc = 0;
break;
}
case IOCTL_EVTCHN_NOTIFY: {
struct ioctl_evtchn_notify notify;
rc = -EFAULT;
if (copy_from_user(&notify, uarg, sizeof(notify)))
break;
if (notify.port >= NR_EVENT_CHANNELS) {
rc = -EINVAL;
} else if (port_user[notify.port] != u) {
rc = -ENOTCONN;
} else {
notify_remote_via_evtchn(notify.port);
rc = 0;
}
break;
}
case IOCTL_EVTCHN_RESET: {
/* Initialise the ring to empty. Clear errors. */
mutex_lock(&u->ring_cons_mutex);
spin_lock_irq(&port_user_lock);
u->ring_cons = u->ring_prod = u->ring_overflow = 0;
spin_unlock_irq(&port_user_lock);
mutex_unlock(&u->ring_cons_mutex);
rc = 0;
break;
}
default:
rc = -ENOSYS;
break;
}
mutex_unlock(&u->bind_mutex);
return rc;
}
static unsigned int evtchn_poll(struct file *file, poll_table *wait)
{
unsigned int mask = POLLOUT | POLLWRNORM;
struct per_user_data *u = file->private_data;
poll_wait(file, &u->evtchn_wait, wait);
if (u->ring_cons != u->ring_prod)
mask |= POLLIN | POLLRDNORM;
if (u->ring_overflow)
mask = POLLERR;
return mask;
}
static int evtchn_fasync(int fd, struct file *filp, int on)
{
struct per_user_data *u = filp->private_data;
return fasync_helper(fd, filp, on, &u->evtchn_async_queue);
}
static int evtchn_open(struct inode *inode, struct file *filp)
{
struct per_user_data *u;
u = kzalloc(sizeof(*u), GFP_KERNEL);
if (u == NULL)
return -ENOMEM;
u->name = kasprintf(GFP_KERNEL, "evtchn:%s", current->comm);
if (u->name == NULL) {
kfree(u);
return -ENOMEM;
}
init_waitqueue_head(&u->evtchn_wait);
u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
if (u->ring == NULL) {
kfree(u->name);
kfree(u);
return -ENOMEM;
}
mutex_init(&u->bind_mutex);
mutex_init(&u->ring_cons_mutex);
filp->private_data = u;
return 0;
}
static int evtchn_release(struct inode *inode, struct file *filp)
{
int i;
struct per_user_data *u = filp->private_data;
spin_lock_irq(&port_user_lock);
free_page((unsigned long)u->ring);
for (i = 0; i < NR_EVENT_CHANNELS; i++) {
if (port_user[i] != u)
continue;
evtchn_unbind_from_user(port_user[i], i);
}
spin_unlock_irq(&port_user_lock);
kfree(u->name);
kfree(u);
return 0;
}
static const struct file_operations evtchn_fops = {
.owner = THIS_MODULE,
.read = evtchn_read,
.write = evtchn_write,
.unlocked_ioctl = evtchn_ioctl,
.poll = evtchn_poll,
.fasync = evtchn_fasync,
.open = evtchn_open,
.release = evtchn_release,
.llseek = noop_llseek,
};
static struct miscdevice evtchn_miscdev = {
.minor = MISC_DYNAMIC_MINOR,
.name = "evtchn",
.fops = &evtchn_fops,
};
static int __init evtchn_init(void)
{
int err;
if (!xen_domain())
return -ENODEV;
spin_lock_init(&port_user_lock);
memset(port_user, 0, sizeof(port_user));
/* Create '/dev/misc/evtchn'. */
err = misc_register(&evtchn_miscdev);
if (err != 0) {
printk(KERN_ALERT "Could not register /dev/misc/evtchn\n");
return err;
}
printk(KERN_INFO "Event-channel device installed.\n");
return 0;
}
static void __exit evtchn_cleanup(void)
{
misc_deregister(&evtchn_miscdev);
}
module_init(evtchn_init);
module_exit(evtchn_cleanup);
MODULE_LICENSE("GPL");