2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/fs/eventfd.c
Davide Libenzi 562787a5c3 anonfd: split interface into file creation and install
Split the anonfd interface into a bare file pointer creation one, and a
file pointer creation plus install one.

There are cases, like the usage of eventfds inside other kernel
interfaces, where the file pointer created by anonfd needs to be used
inside the initialization of other structures.

As it is right now, as soon as anon_inode_getfd() returns, the kenrle can
race with userspace closing the newly installed file descriptor.

This patch, while keeping the old anon_inode_getfd(), introduces a new
anon_inode_getfile() (whose services are reused in anon_inode_getfd())
that allows to split the file creation phase and the fd install one.

Once all the kernel structures are initialized, the code can call the
proper fd_install().

Gregory manifested the need for something like this inside KVM.

Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: James Morris <jmorris@namei.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Gregory Haskins <ghaskins@novell.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Acked-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-23 07:39:29 -07:00

379 lines
9.2 KiB
C

/*
* fs/eventfd.c
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/anon_inodes.h>
#include <linux/syscalls.h>
#include <linux/module.h>
#include <linux/kref.h>
#include <linux/eventfd.h>
struct eventfd_ctx {
struct kref kref;
wait_queue_head_t wqh;
/*
* Every time that a write(2) is performed on an eventfd, the
* value of the __u64 being written is added to "count" and a
* wakeup is performed on "wqh". A read(2) will return the "count"
* value to userspace, and will reset "count" to zero. The kernel
* side eventfd_signal() also, adds to the "count" counter and
* issue a wakeup.
*/
__u64 count;
unsigned int flags;
};
/**
* eventfd_signal - Adds @n to the eventfd counter.
* @ctx: [in] Pointer to the eventfd context.
* @n: [in] Value of the counter to be added to the eventfd internal counter.
* The value cannot be negative.
*
* This function is supposed to be called by the kernel in paths that do not
* allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
* value, and we signal this as overflow condition by returining a POLLERR
* to poll(2).
*
* Returns @n in case of success, a non-negative number lower than @n in case
* of overflow, or the following error codes:
*
* -EINVAL : The value of @n is negative.
*/
int eventfd_signal(struct eventfd_ctx *ctx, int n)
{
unsigned long flags;
if (n < 0)
return -EINVAL;
spin_lock_irqsave(&ctx->wqh.lock, flags);
if (ULLONG_MAX - ctx->count < n)
n = (int) (ULLONG_MAX - ctx->count);
ctx->count += n;
if (waitqueue_active(&ctx->wqh))
wake_up_locked_poll(&ctx->wqh, POLLIN);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return n;
}
EXPORT_SYMBOL_GPL(eventfd_signal);
static void eventfd_free_ctx(struct eventfd_ctx *ctx)
{
kfree(ctx);
}
static void eventfd_free(struct kref *kref)
{
struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref);
eventfd_free_ctx(ctx);
}
/**
* eventfd_ctx_get - Acquires a reference to the internal eventfd context.
* @ctx: [in] Pointer to the eventfd context.
*
* Returns: In case of success, returns a pointer to the eventfd context.
*/
struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx)
{
kref_get(&ctx->kref);
return ctx;
}
EXPORT_SYMBOL_GPL(eventfd_ctx_get);
/**
* eventfd_ctx_put - Releases a reference to the internal eventfd context.
* @ctx: [in] Pointer to eventfd context.
*
* The eventfd context reference must have been previously acquired either
* with eventfd_ctx_get() or eventfd_ctx_fdget()).
*/
void eventfd_ctx_put(struct eventfd_ctx *ctx)
{
kref_put(&ctx->kref, eventfd_free);
}
EXPORT_SYMBOL_GPL(eventfd_ctx_put);
static int eventfd_release(struct inode *inode, struct file *file)
{
struct eventfd_ctx *ctx = file->private_data;
wake_up_poll(&ctx->wqh, POLLHUP);
eventfd_ctx_put(ctx);
return 0;
}
static unsigned int eventfd_poll(struct file *file, poll_table *wait)
{
struct eventfd_ctx *ctx = file->private_data;
unsigned int events = 0;
unsigned long flags;
poll_wait(file, &ctx->wqh, wait);
spin_lock_irqsave(&ctx->wqh.lock, flags);
if (ctx->count > 0)
events |= POLLIN;
if (ctx->count == ULLONG_MAX)
events |= POLLERR;
if (ULLONG_MAX - 1 > ctx->count)
events |= POLLOUT;
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return events;
}
static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
struct eventfd_ctx *ctx = file->private_data;
ssize_t res;
__u64 ucnt = 0;
DECLARE_WAITQUEUE(wait, current);
if (count < sizeof(ucnt))
return -EINVAL;
spin_lock_irq(&ctx->wqh.lock);
res = -EAGAIN;
if (ctx->count > 0)
res = sizeof(ucnt);
else if (!(file->f_flags & O_NONBLOCK)) {
__add_wait_queue(&ctx->wqh, &wait);
for (res = 0;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (ctx->count > 0) {
res = sizeof(ucnt);
break;
}
if (signal_pending(current)) {
res = -ERESTARTSYS;
break;
}
spin_unlock_irq(&ctx->wqh.lock);
schedule();
spin_lock_irq(&ctx->wqh.lock);
}
__remove_wait_queue(&ctx->wqh, &wait);
__set_current_state(TASK_RUNNING);
}
if (likely(res > 0)) {
ucnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
ctx->count -= ucnt;
if (waitqueue_active(&ctx->wqh))
wake_up_locked_poll(&ctx->wqh, POLLOUT);
}
spin_unlock_irq(&ctx->wqh.lock);
if (res > 0 && put_user(ucnt, (__u64 __user *) buf))
return -EFAULT;
return res;
}
static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
loff_t *ppos)
{
struct eventfd_ctx *ctx = file->private_data;
ssize_t res;
__u64 ucnt;
DECLARE_WAITQUEUE(wait, current);
if (count < sizeof(ucnt))
return -EINVAL;
if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
return -EFAULT;
if (ucnt == ULLONG_MAX)
return -EINVAL;
spin_lock_irq(&ctx->wqh.lock);
res = -EAGAIN;
if (ULLONG_MAX - ctx->count > ucnt)
res = sizeof(ucnt);
else if (!(file->f_flags & O_NONBLOCK)) {
__add_wait_queue(&ctx->wqh, &wait);
for (res = 0;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (ULLONG_MAX - ctx->count > ucnt) {
res = sizeof(ucnt);
break;
}
if (signal_pending(current)) {
res = -ERESTARTSYS;
break;
}
spin_unlock_irq(&ctx->wqh.lock);
schedule();
spin_lock_irq(&ctx->wqh.lock);
}
__remove_wait_queue(&ctx->wqh, &wait);
__set_current_state(TASK_RUNNING);
}
if (likely(res > 0)) {
ctx->count += ucnt;
if (waitqueue_active(&ctx->wqh))
wake_up_locked_poll(&ctx->wqh, POLLIN);
}
spin_unlock_irq(&ctx->wqh.lock);
return res;
}
static const struct file_operations eventfd_fops = {
.release = eventfd_release,
.poll = eventfd_poll,
.read = eventfd_read,
.write = eventfd_write,
};
/**
* eventfd_fget - Acquire a reference of an eventfd file descriptor.
* @fd: [in] Eventfd file descriptor.
*
* Returns a pointer to the eventfd file structure in case of success, or the
* following error pointer:
*
* -EBADF : Invalid @fd file descriptor.
* -EINVAL : The @fd file descriptor is not an eventfd file.
*/
struct file *eventfd_fget(int fd)
{
struct file *file;
file = fget(fd);
if (!file)
return ERR_PTR(-EBADF);
if (file->f_op != &eventfd_fops) {
fput(file);
return ERR_PTR(-EINVAL);
}
return file;
}
EXPORT_SYMBOL_GPL(eventfd_fget);
/**
* eventfd_ctx_fdget - Acquires a reference to the internal eventfd context.
* @fd: [in] Eventfd file descriptor.
*
* Returns a pointer to the internal eventfd context, otherwise the error
* pointers returned by the following functions:
*
* eventfd_fget
*/
struct eventfd_ctx *eventfd_ctx_fdget(int fd)
{
struct file *file;
struct eventfd_ctx *ctx;
file = eventfd_fget(fd);
if (IS_ERR(file))
return (struct eventfd_ctx *) file;
ctx = eventfd_ctx_get(file->private_data);
fput(file);
return ctx;
}
EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
/**
* eventfd_ctx_fileget - Acquires a reference to the internal eventfd context.
* @file: [in] Eventfd file pointer.
*
* Returns a pointer to the internal eventfd context, otherwise the error
* pointer:
*
* -EINVAL : The @fd file descriptor is not an eventfd file.
*/
struct eventfd_ctx *eventfd_ctx_fileget(struct file *file)
{
if (file->f_op != &eventfd_fops)
return ERR_PTR(-EINVAL);
return eventfd_ctx_get(file->private_data);
}
EXPORT_SYMBOL_GPL(eventfd_ctx_fileget);
/**
* eventfd_file_create - Creates an eventfd file pointer.
* @count: Initial eventfd counter value.
* @flags: Flags for the eventfd file.
*
* This function creates an eventfd file pointer, w/out installing it into
* the fd table. This is useful when the eventfd file is used during the
* initialization of data structures that require extra setup after the eventfd
* creation. So the eventfd creation is split into the file pointer creation
* phase, and the file descriptor installation phase.
* In this way races with userspace closing the newly installed file descriptor
* can be avoided.
* Returns an eventfd file pointer, or a proper error pointer.
*/
struct file *eventfd_file_create(unsigned int count, int flags)
{
struct file *file;
struct eventfd_ctx *ctx;
/* Check the EFD_* constants for consistency. */
BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
if (flags & ~EFD_FLAGS_SET)
return ERR_PTR(-EINVAL);
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return ERR_PTR(-ENOMEM);
kref_init(&ctx->kref);
init_waitqueue_head(&ctx->wqh);
ctx->count = count;
ctx->flags = flags;
file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx,
flags & EFD_SHARED_FCNTL_FLAGS);
if (IS_ERR(file))
eventfd_free_ctx(ctx);
return file;
}
SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
{
int fd, error;
struct file *file;
error = get_unused_fd_flags(flags & EFD_SHARED_FCNTL_FLAGS);
if (error < 0)
return error;
fd = error;
file = eventfd_file_create(count, flags);
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_put_unused_fd;
}
fd_install(fd, file);
return fd;
err_put_unused_fd:
put_unused_fd(fd);
return error;
}
SYSCALL_DEFINE1(eventfd, unsigned int, count)
{
return sys_eventfd2(count, 0);
}