dev.c

linux 内核源代码

/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2006  Miklos Szeredi <[e-mail]>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/

#include "fuse_i.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/poll.h>
#include <linux/uio.h>
#include <linux/miscdevice.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/slab.h>

MODULE_ALIAS_MISCDEV(FUSE_MINOR);

static struct kmem_cache *fuse_req_cachep;

static struct fuse_conn *fuse_get_conn(struct file *file)
{
	/*
	 * Lockless access is OK, because file->private data is set
	 * once during mount and is valid until the file is released.
	 */
	return file->private_data;
}

static void fuse_request_init(struct fuse_req *req)
{
	memset(req, 0, sizeof(*req));
	INIT_LIST_HEAD(&req->list);
	INIT_LIST_HEAD(&req->intr_entry);
	init_waitqueue_head(&req->waitq);
	atomic_set(&req->count, 1);
}

struct fuse_req *fuse_request_alloc(void)
{
	struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, GFP_KERNEL);
	if (req)
		fuse_request_init(req);
	return req;
}

void fuse_request_free(struct fuse_req *req)
{
	kmem_cache_free(fuse_req_cachep, req);
}

static void block_sigs(sigset_t *oldset)
{
	sigset_t mask;

	siginitsetinv(&mask, sigmask(SIGKILL));
	sigprocmask(SIG_BLOCK, &mask, oldset);
}

static void restore_sigs(sigset_t *oldset)
{
	sigprocmask(SIG_SETMASK, oldset, NULL);
}

static void __fuse_get_request(struct fuse_req *req)
{
	atomic_inc(&req->count);
}

/* Must be called with > 1 refcount */
static void __fuse_put_request(struct fuse_req *req)
{
	BUG_ON(atomic_read(&req->count) < 2);
	atomic_dec(&req->count);
}

static void fuse_req_init_context(struct fuse_req *req)
{
	req->in.h.uid = current->fsuid;
	req->in.h.gid = current->fsgid;
	req->in.h.pid = current->pid;
}

struct fuse_req *fuse_get_req(struct fuse_conn *fc)
{
	struct fuse_req *req;
	sigset_t oldset;
	int intr;
	int err;

	atomic_inc(&fc->num_waiting);
	block_sigs(&oldset);
	intr = wait_event_interruptible(fc->blocked_waitq, !fc->blocked);
	restore_sigs(&oldset);
	err = -EINTR;
	if (intr)
		goto out;

	err = -ENOTCONN;
	if (!fc->connected)
		goto out;

	req = fuse_request_alloc();
	err = -ENOMEM;
	if (!req)
		goto out;

	fuse_req_init_context(req);
	req->waiting = 1;
	return req;

 out:
	atomic_dec(&fc->num_waiting);
	return ERR_PTR(err);
}

/*
 * Return request in fuse_file->reserved_req.  However that may
 * currently be in use.  If that is the case, wait for it to become
 * available.
 */
static struct fuse_req *get_reserved_req(struct fuse_conn *fc,
					 struct file *file)
{
	struct fuse_req *req = NULL;
	struct fuse_file *ff = file->private_data;

	do {
		wait_event(fc->reserved_req_waitq, ff->reserved_req);
		spin_lock(&fc->lock);
		if (ff->reserved_req) {
			req = ff->reserved_req;
			ff->reserved_req = NULL;
			get_file(file);
			req->stolen_file = file;
		}
		spin_unlock(&fc->lock);
	} while (!req);

	return req;
}

/*
 * Put stolen request back into fuse_file->reserved_req
 */
static void put_reserved_req(struct fuse_conn *fc, struct fuse_req *req)
{
	struct file *file = req->stolen_file;
	struct fuse_file *ff = file->private_data;

	spin_lock(&fc->lock);
	fuse_request_init(req);
	BUG_ON(ff->reserved_req);
	ff->reserved_req = req;
	wake_up_all(&fc->reserved_req_waitq);
	spin_unlock(&fc->lock);
	fput(file);
}

/*
 * Gets a requests for a file operation, always succeeds
 *
 * This is used for sending the FLUSH request, which must get to
 * userspace, due to POSIX locks which may need to be unlocked.
 *
 * If allocation fails due to OOM, use the reserved request in
 * fuse_file.
 *
 * This is very unlikely to deadlock accidentally, since the
 * filesystem should not have it's own file open.  If deadlock is
 * intentional, it can still be broken by "aborting" the filesystem.
 */
struct fuse_req *fuse_get_req_nofail(struct fuse_conn *fc, struct file *file)
{
	struct fuse_req *req;

	atomic_inc(&fc->num_waiting);
	wait_event(fc->blocked_waitq, !fc->blocked);
	req = fuse_request_alloc();
	if (!req)
		req = get_reserved_req(fc, file);

	fuse_req_init_context(req);
	req->waiting = 1;
	return req;
}

void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
{
	if (atomic_dec_and_test(&req->count)) {
		if (req->waiting)
			atomic_dec(&fc->num_waiting);

		if (req->stolen_file)
			put_reserved_req(fc, req);
		else
			fuse_request_free(req);
	}
}

/*
 * This function is called when a request is finished.  Either a reply
 * has arrived or it was aborted (and not yet sent) or some error
 * occurred during communication with userspace, or the device file
 * was closed.  The requester thread is woken up (if still waiting),
 * the 'end' callback is called if given, else the reference to the
 * request is released
 *
 * Called with fc->lock, unlocks it
 */
static void request_end(struct fuse_conn *fc, struct fuse_req *req)
	__releases(fc->lock)
{
	void (*end) (struct fuse_conn *, struct fuse_req *) = req->end;
	req->end = NULL;
	list_del(&req->list);
	list_del(&req->intr_entry);
	req->state = FUSE_REQ_FINISHED;
	if (req->background) {
		if (fc->num_background == FUSE_MAX_BACKGROUND) {
			fc->blocked = 0;
			wake_up_all(&fc->blocked_waitq);
		}
		if (fc->num_background == FUSE_CONGESTION_THRESHOLD) {
			clear_bdi_congested(&fc->bdi, READ);
			clear_bdi_congested(&fc->bdi, WRITE);
		}
		fc->num_background--;
	}
	spin_unlock(&fc->lock);
	wake_up(&req->waitq);
	if (end)
		end(fc, req);
	else
		fuse_put_request(fc, req);
}

static void wait_answer_interruptible(struct fuse_conn *fc,
				      struct fuse_req *req)
{
	if (signal_pending(current))
		return;

	spin_unlock(&fc->lock);
	wait_event_interruptible(req->waitq, req->state == FUSE_REQ_FINISHED);
	spin_lock(&fc->lock);
}

static void queue_interrupt(struct fuse_conn *fc, struct fuse_req *req)
{
	list_add_tail(&req->intr_entry, &fc->interrupts);
	wake_up(&fc->waitq);
	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
}

/* Called with fc->lock held.  Releases, and then reacquires it. */
static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
{
	if (!fc->no_interrupt) {
		/* Any signal may interrupt this */
		wait_answer_interruptible(fc, req);

		if (req->aborted)
			goto aborted;
		if (req->state == FUSE_REQ_FINISHED)
			return;

		req->interrupted = 1;
		if (req->state == FUSE_REQ_SENT)
			queue_interrupt(fc, req);
	}

	if (!req->force) {
		sigset_t oldset;

		/* Only fatal signals may interrupt this */
		block_sigs(&oldset);
		wait_answer_interruptible(fc, req);
		restore_sigs(&oldset);

		if (req->aborted)
			goto aborted;
		if (req->state == FUSE_REQ_FINISHED)
			return;

		/* Request is not yet in userspace, bail out */
		if (req->state == FUSE_REQ_PENDING) {
			list_del(&req->list);
			__fuse_put_request(req);
			req->out.h.error = -EINTR;
			return;
		}
	}

	/*
	 * Either request is already in userspace, or it was forced.
	 * Wait it out.
	 */
	spin_unlock(&fc->lock);
	wait_event(req->waitq, req->state == FUSE_REQ_FINISHED);
	spin_lock(&fc->lock);

	if (!req->aborted)
		return;

 aborted:
	BUG_ON(req->state != FUSE_REQ_FINISHED);
	if (req->locked) {
		/* This is uninterruptible sleep, because data is
		   being copied to/from the buffers of req.  During
		   locked state, there mustn't be any filesystem
		   operation (e.g. page fault), since that could lead
		   to deadlock */
		spin_unlock(&fc->lock);
		wait_event(req->waitq, !req->locked);
		spin_lock(&fc->lock);
	}
}

static unsigned len_args(unsigned numargs, struct fuse_arg *args)
{
	unsigned nbytes = 0;
	unsigned i;

	for (i = 0; i < numargs; i++)
		nbytes += args[i].size;

	return nbytes;
}

static u64 fuse_get_unique(struct fuse_conn *fc)
 {
 	fc->reqctr++;
 	/* zero is special */
 	if (fc->reqctr == 0)
 		fc->reqctr = 1;

	return fc->reqctr;
}

static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
{
	req->in.h.unique = fuse_get_unique(fc);
	req->in.h.len = sizeof(struct fuse_in_header) +
		len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
	list_add_tail(&req->list, &fc->pending);
	req->state = FUSE_REQ_PENDING;
	if (!req->waiting) {
		req->waiting = 1;
		atomic_inc(&fc->num_waiting);
	}
	wake_up(&fc->waitq);
	kill_fasync(&fc->fasync, SIGIO, POLL_IN);
}

void request_send(struct fuse_conn *fc, struct fuse_req *req)
{
	req->isreply = 1;
	spin_lock(&fc->lock);
	if (!fc->connected)
		req->out.h.error = -ENOTCONN;
	else if (fc->conn_error)
		req->out.h.error = -ECONNREFUSED;
	else {
		queue_request(fc, req);
		/* acquire extra reference, since request is still needed
		   after request_end() */
		__fuse_get_request(req);

		request_wait_answer(fc, req);
	}
	spin_unlock(&fc->lock);
}

static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req)
{
	spin_lock(&fc->lock);
	if (fc->connected) {
		req->background = 1;
		fc->num_background++;
		if (fc->num_background == FUSE_MAX_BACKGROUND)
			fc->blocked = 1;
		if (fc->num_background == FUSE_CONGESTION_THRESHOLD) {
			set_bdi_congested(&fc->bdi, READ);
			set_bdi_congested(&fc->bdi, WRITE);
		}

		queue_request(fc, req);
		spin_unlock(&fc->lock);
	} else {
		req->out.h.error = -ENOTCONN;
		request_end(fc, req);
	}
}

void request_send_noreply(struct fuse_conn *fc, struct fuse_req *req)
{
	req->isreply = 0;
	request_send_nowait(fc, req);
}

void request_send_background(struct fuse_conn *fc, struct fuse_req *req)
{
	req->isreply = 1;
	request_send_nowait(fc, req);
}

/*
 * Lock the request.  Up to the next unlock_request() there mustn't be
 * anything that could cause a page-fault.  If the request was already
 * aborted bail out.
 */
static int lock_request(struct fuse_conn *fc, struct fuse_req *req)
{
	int err = 0;
	if (req) {
		spin_lock(&fc->lock);
		if (req->aborted)
			err = -ENOENT;
		else
			req->locked = 1;
		spin_unlock(&fc->lock);
	}
	return err;
}

/*
 * Unlock request.  If it was aborted during being locked, the
 * requester thread is currently waiting for it to be unlocked, so
 * wake it up.
 */
static void unlock_request(struct fuse_conn *fc, struct fuse_req *req)
{
	if (req) {
		spin_lock(&fc->lock);
		req->locked = 0;
		if (req->aborted)
			wake_up(&req->waitq);
		spin_unlock(&fc->lock);
	}
}

struct fuse_copy_state {
	struct fuse_conn *fc;
	int write;
	struct fuse_req *req;
	const struct iovec *iov;
	unsigned long nr_segs;
	unsigned long seglen;
	unsigned long addr;
	struct page *pg;
	void *mapaddr;
	void *buf;
	unsigned len;
};

static void fuse_copy_init(struct fuse_copy_state *cs, struct fuse_conn *fc,
			   int write, struct fuse_req *req,
			   const struct iovec *iov, unsigned long nr_segs)
{
	memset(cs, 0, sizeof(*cs));
	cs->fc = fc;
	cs->write = write;
	cs->req = req;
	cs->iov = iov;
	cs->nr_segs = nr_segs;
}

/* Unmap and put previous page of userspace buffer */
static void fuse_copy_finish(struct fuse_copy_state *cs)
{
	if (cs->mapaddr) {
		kunmap_atomic(cs->mapaddr, KM_USER0);
		if (cs->write) {
			flush_dcache_page(cs->pg);
			set_page_dirty_lock(cs->pg);
		}
		put_page(cs->pg);
		cs->mapaddr = NULL;
	}
}

/*
 * Get another pagefull of userspace buffer, and map it to kernel
 * address space, and lock request
 */
static int fuse_copy_fill(struct fuse_copy_state *cs)
{
	unsigned long offset;
	int err;

	unlock_request(cs->fc, cs->req);
	fuse_copy_finish(cs);
	if (!cs->seglen) {
		BUG_ON(!cs->nr_segs);
		cs->seglen = cs->iov[0].iov_len;
		cs->addr = (unsigned long) cs->iov[0].iov_base;
		cs->iov ++;
		cs->nr_segs --;
	}
	down_read(&current->mm->mmap_sem);
	err = get_user_pages(current, current->mm, cs->addr, 1, cs->write, 0,
			     &cs->pg, NULL);
	up_read(&current->mm->mmap_sem);
	if (err < 0)
		return err;
	BUG_ON(err != 1);
	offset = cs->addr % PAGE_SIZE;
	cs->mapaddr = kmap_atomic(cs->pg, KM_USER0);
	cs->buf = cs->mapaddr + offset;
	cs->len = min(PAGE_SIZE - offset, cs->seglen);
	cs->seglen -= cs->len;
	cs->addr += cs->len;

	return lock_request(cs->fc, cs->req);
}

/* Do as much copy to/from userspace buffer as we can */
static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
	unsigned ncpy = min(*size, cs->len);
	if (val) {
		if (cs->write)
			memcpy(cs->buf, *val, ncpy);
		else
			memcpy(*val, cs->buf, ncpy);
		*val += ncpy;
	}
	*size -= ncpy;
	cs->len -= ncpy;
	cs->buf += ncpy;
	return ncpy;
}

/*
 * Copy a page in the request to/from the userspace buffer.  Must be