mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 16:29:59 +00:00
![Tejun Heo](/assets/img/avatar_default.png)
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>
438 lines
11 KiB
C
438 lines
11 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/slab.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 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
|
|
{
|
|
*cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
|
|
ctx->count -= *cnt;
|
|
}
|
|
|
|
/**
|
|
* eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
|
|
* @ctx: [in] Pointer to eventfd context.
|
|
* @wait: [in] Wait queue to be removed.
|
|
* @cnt: [out] Pointer to the 64bit conter value.
|
|
*
|
|
* Returns zero if successful, or the following error codes:
|
|
*
|
|
* -EAGAIN : The operation would have blocked.
|
|
*
|
|
* This is used to atomically remove a wait queue entry from the eventfd wait
|
|
* queue head, and read/reset the counter value.
|
|
*/
|
|
int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
|
|
__u64 *cnt)
|
|
{
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&ctx->wqh.lock, flags);
|
|
eventfd_ctx_do_read(ctx, cnt);
|
|
__remove_wait_queue(&ctx->wqh, wait);
|
|
if (*cnt != 0 && waitqueue_active(&ctx->wqh))
|
|
wake_up_locked_poll(&ctx->wqh, POLLOUT);
|
|
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
|
|
|
|
return *cnt != 0 ? 0 : -EAGAIN;
|
|
}
|
|
EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
|
|
|
|
/**
|
|
* eventfd_ctx_read - Reads the eventfd counter or wait if it is zero.
|
|
* @ctx: [in] Pointer to eventfd context.
|
|
* @no_wait: [in] Different from zero if the operation should not block.
|
|
* @cnt: [out] Pointer to the 64bit conter value.
|
|
*
|
|
* Returns zero if successful, or the following error codes:
|
|
*
|
|
* -EAGAIN : The operation would have blocked but @no_wait was nonzero.
|
|
* -ERESTARTSYS : A signal interrupted the wait operation.
|
|
*
|
|
* If @no_wait is zero, the function might sleep until the eventfd internal
|
|
* counter becomes greater than zero.
|
|
*/
|
|
ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt)
|
|
{
|
|
ssize_t res;
|
|
DECLARE_WAITQUEUE(wait, current);
|
|
|
|
spin_lock_irq(&ctx->wqh.lock);
|
|
*cnt = 0;
|
|
res = -EAGAIN;
|
|
if (ctx->count > 0)
|
|
res = 0;
|
|
else if (!no_wait) {
|
|
__add_wait_queue(&ctx->wqh, &wait);
|
|
for (;;) {
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
if (ctx->count > 0) {
|
|
res = 0;
|
|
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)) {
|
|
eventfd_ctx_do_read(ctx, cnt);
|
|
if (waitqueue_active(&ctx->wqh))
|
|
wake_up_locked_poll(&ctx->wqh, POLLOUT);
|
|
}
|
|
spin_unlock_irq(&ctx->wqh.lock);
|
|
|
|
return res;
|
|
}
|
|
EXPORT_SYMBOL_GPL(eventfd_ctx_read);
|
|
|
|
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 cnt;
|
|
|
|
if (count < sizeof(cnt))
|
|
return -EINVAL;
|
|
res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt);
|
|
if (res < 0)
|
|
return res;
|
|
|
|
return put_user(cnt, (__u64 __user *) buf) ? -EFAULT : sizeof(cnt);
|
|
}
|
|
|
|
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,
|
|
O_RDWR | (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);
|
|
}
|
|
|