Commit 8d7a8fe2 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client 

Pull ceph fixes from Sage Weil:
 "There is a pair of fixes for double-frees in the recent bundle for
  3.10, a couple of fixes for long-standing bugs (sleep while atomic and
  an endianness fix), and a locking fix that can be triggered when osds
  are going down"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  rbd: fix cleanup in rbd_add()
  rbd: don't destroy ceph_opts in rbd_add()
  ceph: ceph_pagelist_append might sleep while atomic
  ceph: add cpu_to_le32() calls when encoding a reconnect capability
  libceph: must hold mutex for reset_changed_osds()
parents 77293e21 3abef3b3

drivers/block/rbd.c

+18 −15
Original line number Diff line number Diff line
@@ -519,8 +519,8 @@ static const struct block_device_operations rbd_bd_ops = { 
};



/*

 * Initialize an rbd client instance.

 * We own *ceph_opts.

 * Initialize an rbd client instance.  Success or not, this function

 * consumes ceph_opts.

 */

static struct rbd_client *rbd_client_create(struct ceph_options *ceph_opts)

{
@@ -675,7 +675,8 @@ static int parse_rbd_opts_token(char *c, void *private) 


/*

 * Get a ceph client with specific addr and configuration, if one does

 * not exist create it.

 * not exist create it.  Either way, ceph_opts is consumed by this

 * function.

 */

static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts)

{
@@ -4697,8 +4698,10 @@ out: 
	return ret;

}



/* Undo whatever state changes are made by v1 or v2 image probe */



/*

 * Undo whatever state changes are made by v1 or v2 header info

 * call.

 */

static void rbd_dev_unprobe(struct rbd_device *rbd_dev)

{

	struct rbd_image_header	*header;
@@ -4902,9 +4905,10 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) 
	int tmp;



	/*

	 * Get the id from the image id object.  If it's not a

	 * format 2 image, we'll get ENOENT back, and we'll assume

	 * it's a format 1 image.

	 * Get the id from the image id object.  Unless there's an

	 * error, rbd_dev->spec->image_id will be filled in with

	 * a dynamically-allocated string, and rbd_dev->image_format

	 * will be set to either 1 or 2.

	 */

	ret = rbd_dev_image_id(rbd_dev);

	if (ret)
@@ -4992,7 +4996,6 @@ static ssize_t rbd_add(struct bus_type *bus, 
		rc = PTR_ERR(rbdc);

		goto err_out_args;

	}

	ceph_opts = NULL;	/* rbd_dev client now owns this */



	/* pick the pool */

	osdc = &rbdc->client->osdc;
@@ -5027,18 +5030,18 @@ static ssize_t rbd_add(struct bus_type *bus, 
	rbd_dev->mapping.read_only = read_only;



	rc = rbd_dev_device_setup(rbd_dev);

	if (!rc)

	if (rc) {

		rbd_dev_image_release(rbd_dev);

		goto err_out_module;

	}



	return count;



	rbd_dev_image_release(rbd_dev);

err_out_rbd_dev:

	rbd_dev_destroy(rbd_dev);

err_out_client:

	rbd_put_client(rbdc);

err_out_args:

	if (ceph_opts)

		ceph_destroy_options(ceph_opts);

	kfree(rbd_opts);

	rbd_spec_put(spec);

err_out_module:

	module_put(THIS_MODULE);

fs/ceph/locks.c

+47 −26
Original line number Diff line number Diff line
@@ -191,27 +191,23 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) 
}



/**

 * Encode the flock and fcntl locks for the given inode into the pagelist.

 * Format is: #fcntl locks, sequential fcntl locks, #flock locks,

 * sequential flock locks.

 * Must be called with lock_flocks() already held.

 * If we encounter more of a specific lock type than expected,

 * we return the value 1.

 * Encode the flock and fcntl locks for the given inode into the ceph_filelock

 * array. Must be called with lock_flocks() already held.

 * If we encounter more of a specific lock type than expected, return -ENOSPC.

 */

int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,

int ceph_encode_locks_to_buffer(struct inode *inode,

				struct ceph_filelock *flocks,

				int num_fcntl_locks, int num_flock_locks)

{

	struct file_lock *lock;

	struct ceph_filelock cephlock;

	int err = 0;

	int seen_fcntl = 0;

	int seen_flock = 0;

	int l = 0;



	dout("encoding %d flock and %d fcntl locks", num_flock_locks,

	     num_fcntl_locks);

	err = ceph_pagelist_append(pagelist, &num_fcntl_locks, sizeof(u32));

	if (err)

		goto fail;



	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {

		if (lock->fl_flags & FL_POSIX) {

			++seen_fcntl;
@@ -219,19 +215,12 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist, 
				err = -ENOSPC;

				goto fail;

			}

			err = lock_to_ceph_filelock(lock, &cephlock);

			err = lock_to_ceph_filelock(lock, &flocks[l]);

			if (err)

				goto fail;

			err = ceph_pagelist_append(pagelist, &cephlock,

					   sizeof(struct ceph_filelock));

			++l;

		}

		if (err)

			goto fail;

	}



	err = ceph_pagelist_append(pagelist, &num_flock_locks, sizeof(u32));

	if (err)

		goto fail;

	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {

		if (lock->fl_flags & FL_FLOCK) {

			++seen_flock;
@@ -239,19 +228,51 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist, 
				err = -ENOSPC;

				goto fail;

			}

			err = lock_to_ceph_filelock(lock, &cephlock);

			err = lock_to_ceph_filelock(lock, &flocks[l]);

			if (err)

				goto fail;

			err = ceph_pagelist_append(pagelist, &cephlock,

					   sizeof(struct ceph_filelock));

			++l;

		}

		if (err)

			goto fail;

	}

fail:

	return err;

}



/**

 * Copy the encoded flock and fcntl locks into the pagelist.

 * Format is: #fcntl locks, sequential fcntl locks, #flock locks,

 * sequential flock locks.

 * Returns zero on success.

 */

int ceph_locks_to_pagelist(struct ceph_filelock *flocks,

			   struct ceph_pagelist *pagelist,

			   int num_fcntl_locks, int num_flock_locks)

{

	int err = 0;

	__le32 nlocks;



	nlocks = cpu_to_le32(num_fcntl_locks);

	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));

	if (err)

		goto out_fail;



	err = ceph_pagelist_append(pagelist, flocks,

				   num_fcntl_locks * sizeof(*flocks));

	if (err)

		goto out_fail;



	nlocks = cpu_to_le32(num_flock_locks);

	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));

	if (err)

		goto out_fail;



	err = ceph_pagelist_append(pagelist,

				   &flocks[num_fcntl_locks],

				   num_flock_locks * sizeof(*flocks));

out_fail:

	return err;

}



/*

 * Given a pointer to a lock, convert it to a ceph filelock

 */

fs/ceph/mds_client.c

+35 −30
Original line number Diff line number Diff line
@@ -2478,39 +2478,44 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, 


	if (recon_state->flock) {

		int num_fcntl_locks, num_flock_locks;

		struct ceph_pagelist_cursor trunc_point;

		struct ceph_filelock *flocks;



		ceph_pagelist_set_cursor(pagelist, &trunc_point);

		do {

encode_again:

		lock_flocks();

			ceph_count_locks(inode, &num_fcntl_locks,

					 &num_flock_locks);

			rec.v2.flock_len = (2*sizeof(u32) +

					    (num_fcntl_locks+num_flock_locks) *

					    sizeof(struct ceph_filelock));

		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);

		unlock_flocks();



			/* pre-alloc pagelist */

			ceph_pagelist_truncate(pagelist, &trunc_point);

			err = ceph_pagelist_append(pagelist, &rec, reclen);

			if (!err)

				err = ceph_pagelist_reserve(pagelist,

							    rec.v2.flock_len);



			/* encode locks */

			if (!err) {

		flocks = kmalloc((num_fcntl_locks+num_flock_locks) *

				 sizeof(struct ceph_filelock), GFP_NOFS);

		if (!flocks) {

			err = -ENOMEM;

			goto out_free;

		}

		lock_flocks();

				err = ceph_encode_locks(inode,

							pagelist,

		err = ceph_encode_locks_to_buffer(inode, flocks,

						  num_fcntl_locks,

						  num_flock_locks);

		unlock_flocks();

		if (err) {

			kfree(flocks);

			if (err == -ENOSPC)

				goto encode_again;

			goto out_free;

		}

		} while (err == -ENOSPC);

		/*

		 * number of encoded locks is stable, so copy to pagelist

		 */

		rec.v2.flock_len = cpu_to_le32(2*sizeof(u32) +

				    (num_fcntl_locks+num_flock_locks) *

				    sizeof(struct ceph_filelock));

		err = ceph_pagelist_append(pagelist, &rec, reclen);

		if (!err)

			err = ceph_locks_to_pagelist(flocks, pagelist,

						     num_fcntl_locks,

						     num_flock_locks);

		kfree(flocks);

	} else {

		err = ceph_pagelist_append(pagelist, &rec, reclen);

	}



out_free:

	kfree(path);

out_dput:

fs/ceph/super.h

+7 −2
Original line number Diff line number Diff line
@@ -822,8 +822,13 @@ extern const struct export_operations ceph_export_ops; 
extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);

extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);

extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);

extern int ceph_encode_locks(struct inode *i, struct ceph_pagelist *p,

			     int p_locks, int f_locks);

extern int ceph_encode_locks_to_buffer(struct inode *inode,

				       struct ceph_filelock *flocks,

				       int num_fcntl_locks,

				       int num_flock_locks);

extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks,

				  struct ceph_pagelist *pagelist,

				  int num_fcntl_locks, int num_flock_locks);

extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c);



/* debugfs.c */

net/ceph/osd_client.c

+1 −1
Original line number Diff line number Diff line
@@ -1675,13 +1675,13 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) 
		__register_request(osdc, req);

		__unregister_linger_request(osdc, req);

	}

	reset_changed_osds(osdc);

	mutex_unlock(&osdc->request_mutex);



	if (needmap) {

		dout("%d requests for down osds, need new map\n", needmap);

		ceph_monc_request_next_osdmap(&osdc->client->monc);

	}

	reset_changed_osds(osdc);

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE