Commit 72b5ac54 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'ceph-for-4.8-rc1' of git://github.com/ceph/ceph-client 

Pull Ceph updates from Ilya Dryomov:
 "The highlights are:

   - RADOS namespace support in libceph and CephFS (Zheng Yan and
     myself).  The stopgaps added in 4.5 to deny access to inodes in
     namespaces are removed and CEPH_FEATURE_FS_FILE_LAYOUT_V2 feature
     bit is now fully supported

   - A large rework of the MDS cap flushing code (Zheng Yan)

   - Handle some of ->d_revalidate() in RCU mode (Jeff Layton).  We were
     overly pessimistic before, bailing at the first sight of LOOKUP_RCU

  On top of that we've got a few CephFS bug fixes, a couple of cleanups
  and Arnd's workaround for a weird genksyms issue"

* tag 'ceph-for-4.8-rc1' of git://github.com/ceph/ceph-client: (34 commits)
  ceph: fix symbol versioning for ceph_monc_do_statfs
  ceph: Correctly return NXIO errors from ceph_llseek
  ceph: Mark the file cache as unreclaimable
  ceph: optimize cap flush waiting
  ceph: cleanup ceph_flush_snaps()
  ceph: kick cap flushes before sending other cap message
  ceph: introduce an inode flag to indicates if snapflush is needed
  ceph: avoid sending duplicated cap flush message
  ceph: unify cap flush and snapcap flush
  ceph: use list instead of rbtree to track cap flushes
  ceph: update types of some local varibles
  ceph: include 'follows' of pending snapflush in cap reconnect message
  ceph: update cap reconnect message to version 3
  ceph: mount non-default filesystem by name
  libceph: fsmap.user subscription support
  ceph: handle LOOKUP_RCU in ceph_d_revalidate
  ceph: allow dentry_lease_is_valid to work under RCU walk
  ceph: clear d_fsinfo pointer under d_lock
  ceph: remove ceph_mdsc_lease_release
  ceph: don't use ->d_time
  ...
parents c7fac299 a0f2b652

drivers/block/rbd.c

+8 −7
Original line number Diff line number Diff line
@@ -1937,7 +1937,7 @@ static struct ceph_osd_request *rbd_osd_req_create( 
	osd_req->r_callback = rbd_osd_req_callback;

	osd_req->r_priv = obj_request;



	osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);

	osd_req->r_base_oloc.pool = rbd_dev->layout.pool_id;

	if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",

			     obj_request->object_name))

		goto fail;
@@ -1991,7 +1991,7 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request) 
	osd_req->r_callback = rbd_osd_req_callback;

	osd_req->r_priv = obj_request;



	osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);

	osd_req->r_base_oloc.pool = rbd_dev->layout.pool_id;

	if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",

			     obj_request->object_name))

		goto fail;
@@ -3995,10 +3995,11 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, 


	/* Initialize the layout used for all rbd requests */



	rbd_dev->layout.fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);

	rbd_dev->layout.fl_stripe_count = cpu_to_le32(1);

	rbd_dev->layout.fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);

	rbd_dev->layout.fl_pg_pool = cpu_to_le32((u32) spec->pool_id);

	rbd_dev->layout.stripe_unit = 1 << RBD_MAX_OBJ_ORDER;

	rbd_dev->layout.stripe_count = 1;

	rbd_dev->layout.object_size = 1 << RBD_MAX_OBJ_ORDER;

	rbd_dev->layout.pool_id = spec->pool_id;

	RCU_INIT_POINTER(rbd_dev->layout.pool_ns, NULL);



	/*

	 * If this is a mapping rbd_dev (as opposed to a parent one),
@@ -5187,7 +5188,7 @@ static int rbd_dev_header_name(struct rbd_device *rbd_dev) 


	rbd_assert(rbd_image_format_valid(rbd_dev->image_format));



	rbd_dev->header_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);

	rbd_dev->header_oloc.pool = rbd_dev->layout.pool_id;

	if (rbd_dev->image_format == 1)

		ret = ceph_oid_aprintf(&rbd_dev->header_oid, GFP_KERNEL, "%s%s",

				       spec->image_name, RBD_SUFFIX);

fs/ceph/addr.c

+57 −20
Original line number Diff line number Diff line
@@ -1730,7 +1730,8 @@ enum { 
	POOL_WRITE	= 2,

};



static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)

static int __ceph_pool_perm_get(struct ceph_inode_info *ci,

				s64 pool, struct ceph_string *pool_ns)

{

	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);

	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1738,6 +1739,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
	struct rb_node **p, *parent;

	struct ceph_pool_perm *perm;

	struct page **pages;

	size_t pool_ns_len;

	int err = 0, err2 = 0, have = 0;



	down_read(&mdsc->pool_perm_rwsem);
@@ -1748,18 +1750,32 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
			p = &(*p)->rb_left;

		else if (pool > perm->pool)

			p = &(*p)->rb_right;

		else {

			int ret = ceph_compare_string(pool_ns,

						perm->pool_ns,

						perm->pool_ns_len);

			if (ret < 0)

				p = &(*p)->rb_left;

			else if (ret > 0)

				p = &(*p)->rb_right;

			else {

				have = perm->perm;

				break;

			}

		}

	}

	up_read(&mdsc->pool_perm_rwsem);

	if (*p)

		goto out;



	dout("__ceph_pool_perm_get pool %u no perm cached\n", pool);

	if (pool_ns)

		dout("__ceph_pool_perm_get pool %lld ns %.*s no perm cached\n",

		     pool, (int)pool_ns->len, pool_ns->str);

	else

		dout("__ceph_pool_perm_get pool %lld no perm cached\n", pool);



	down_write(&mdsc->pool_perm_rwsem);

	p = &mdsc->pool_perm_tree.rb_node;

	parent = NULL;

	while (*p) {

		parent = *p;
@@ -1768,11 +1784,20 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
			p = &(*p)->rb_left;

		else if (pool > perm->pool)

			p = &(*p)->rb_right;

		else {

			int ret = ceph_compare_string(pool_ns,

						perm->pool_ns,

						perm->pool_ns_len);

			if (ret < 0)

				p = &(*p)->rb_left;

			else if (ret > 0)

				p = &(*p)->rb_right;

			else {

				have = perm->perm;

				break;

			}

		}

	}

	if (*p) {

		up_write(&mdsc->pool_perm_rwsem);

		goto out;
@@ -1788,6 +1813,8 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
	rd_req->r_flags = CEPH_OSD_FLAG_READ;

	osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);

	rd_req->r_base_oloc.pool = pool;

	if (pool_ns)

		rd_req->r_base_oloc.pool_ns = ceph_get_string(pool_ns);

	ceph_oid_printf(&rd_req->r_base_oid, "%llx.00000000", ci->i_vino.ino);



	err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS);
@@ -1841,7 +1868,8 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
		goto out_unlock;

	}



	perm = kmalloc(sizeof(*perm), GFP_NOFS);

	pool_ns_len = pool_ns ? pool_ns->len : 0;

	perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS);

	if (!perm) {

		err = -ENOMEM;

		goto out_unlock;
@@ -1849,6 +1877,11 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 


	perm->pool = pool;

	perm->perm = have;

	perm->pool_ns_len = pool_ns_len;

	if (pool_ns_len > 0)

		memcpy(perm->pool_ns, pool_ns->str, pool_ns_len);

	perm->pool_ns[pool_ns_len] = 0;



	rb_link_node(&perm->node, parent, p);

	rb_insert_color(&perm->node, &mdsc->pool_perm_tree);

	err = 0;
@@ -1860,43 +1893,46 @@ out_unlock: 
out:

	if (!err)

		err = have;

	dout("__ceph_pool_perm_get pool %u result = %d\n", pool, err);

	if (pool_ns)

		dout("__ceph_pool_perm_get pool %lld ns %.*s result = %d\n",

		     pool, (int)pool_ns->len, pool_ns->str, err);

	else

		dout("__ceph_pool_perm_get pool %lld result = %d\n", pool, err);

	return err;

}



int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)

{

	u32 pool;

	s64 pool;

	struct ceph_string *pool_ns;

	int ret, flags;



	/* does not support pool namespace yet */

	if (ci->i_pool_ns_len)

		return -EIO;



	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),

				NOPOOLPERM))

		return 0;



	spin_lock(&ci->i_ceph_lock);

	flags = ci->i_ceph_flags;

	pool = ceph_file_layout_pg_pool(ci->i_layout);

	pool = ci->i_layout.pool_id;

	spin_unlock(&ci->i_ceph_lock);

check:

	if (flags & CEPH_I_POOL_PERM) {

		if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {

			dout("ceph_pool_perm_check pool %u no read perm\n",

			dout("ceph_pool_perm_check pool %lld no read perm\n",

			     pool);

			return -EPERM;

		}

		if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {

			dout("ceph_pool_perm_check pool %u no write perm\n",

			dout("ceph_pool_perm_check pool %lld no write perm\n",

			     pool);

			return -EPERM;

		}

		return 0;

	}



	ret = __ceph_pool_perm_get(ci, pool);

	pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);

	ret = __ceph_pool_perm_get(ci, pool, pool_ns);

	ceph_put_string(pool_ns);

	if (ret < 0)

		return ret;
@@ -1907,10 +1943,11 @@ check: 
		flags |= CEPH_I_POOL_WR;



	spin_lock(&ci->i_ceph_lock);

	if (pool == ceph_file_layout_pg_pool(ci->i_layout)) {

		ci->i_ceph_flags = flags;

	if (pool == ci->i_layout.pool_id &&

	    pool_ns == rcu_dereference_raw(ci->i_layout.pool_ns)) {

		ci->i_ceph_flags |= flags;

        } else {

		pool = ceph_file_layout_pg_pool(ci->i_layout);

		pool = ci->i_layout.pool_id;

		flags = ci->i_ceph_flags;

	}

	spin_unlock(&ci->i_ceph_lock);

fs/ceph/cache.c

+1 −1
Original line number Diff line number Diff line
@@ -71,7 +71,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc) 
					      &ceph_fscache_fsid_object_def,

					      fsc, true);

	if (!fsc->fscache)

		pr_err("Unable to resgister fsid: %p fscache cookie", fsc);

		pr_err("Unable to register fsid: %p fscache cookie\n", fsc);



	return 0;

}

fs/ceph/caps.c

+466 −407

File changed.

Preview size limit exceeded, changes collapsed.

fs/ceph/dir.c

+48 −25
Original line number Diff line number Diff line
@@ -59,7 +59,7 @@ int ceph_init_dentry(struct dentry *dentry) 


	di->dentry = dentry;

	di->lease_session = NULL;

	dentry->d_time = jiffies;

	di->time = jiffies;

	/* avoid reordering d_fsdata setup so that the check above is safe */

	smp_mb();

	dentry->d_fsdata = di;
@@ -1124,7 +1124,7 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, 
void ceph_invalidate_dentry_lease(struct dentry *dentry)

{

	spin_lock(&dentry->d_lock);

	dentry->d_time = jiffies;

	ceph_dentry(dentry)->time = jiffies;

	ceph_dentry(dentry)->lease_shared_gen = 0;

	spin_unlock(&dentry->d_lock);

}
@@ -1133,7 +1133,8 @@ void ceph_invalidate_dentry_lease(struct dentry *dentry) 
 * Check if dentry lease is valid.  If not, delete the lease.  Try to

 * renew if the least is more than half up.

 */

static int dentry_lease_is_valid(struct dentry *dentry)

static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags,

				 struct inode *dir)

{

	struct ceph_dentry_info *di;

	struct ceph_mds_session *s;
@@ -1141,12 +1142,11 @@ static int dentry_lease_is_valid(struct dentry *dentry) 
	u32 gen;

	unsigned long ttl;

	struct ceph_mds_session *session = NULL;

	struct inode *dir = NULL;

	u32 seq = 0;



	spin_lock(&dentry->d_lock);

	di = ceph_dentry(dentry);

	if (di->lease_session) {

	if (di && di->lease_session) {

		s = di->lease_session;

		spin_lock(&s->s_gen_ttl_lock);

		gen = s->s_cap_gen;
@@ -1154,13 +1154,19 @@ static int dentry_lease_is_valid(struct dentry *dentry) 
		spin_unlock(&s->s_gen_ttl_lock);



		if (di->lease_gen == gen &&

		    time_before(jiffies, dentry->d_time) &&

		    time_before(jiffies, di->time) &&

		    time_before(jiffies, ttl)) {

			valid = 1;

			if (di->lease_renew_after &&

			    time_after(jiffies, di->lease_renew_after)) {

				/* we should renew */

				dir = d_inode(dentry->d_parent);

				/*

				 * We should renew. If we're in RCU walk mode

				 * though, we can't do that so just return

				 * -ECHILD.

				 */

				if (flags & LOOKUP_RCU) {

					valid = -ECHILD;

				} else {

					session = ceph_get_mds_session(s);

					seq = di->lease_seq;

					di->lease_renew_after = 0;
@@ -1168,6 +1174,7 @@ static int dentry_lease_is_valid(struct dentry *dentry) 
				}

			}

		}

	}

	spin_unlock(&dentry->d_lock);



	if (session) {
@@ -1207,15 +1214,19 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) 
	struct dentry *parent;

	struct inode *dir;



	if (flags & LOOKUP_RCU)

	if (flags & LOOKUP_RCU) {

		parent = ACCESS_ONCE(dentry->d_parent);

		dir = d_inode_rcu(parent);

		if (!dir)

			return -ECHILD;

	} else {

		parent = dget_parent(dentry);

		dir = d_inode(parent);

	}



	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,

	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);



	parent = dget_parent(dentry);

	dir = d_inode(parent);



	/* always trust cached snapped dentries, snapdir dentry */

	if (ceph_snap(dir) != CEPH_NOSNAP) {

		dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
@@ -1224,13 +1235,17 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) 
	} else if (d_really_is_positive(dentry) &&

		   ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {

		valid = 1;

	} else if (dentry_lease_is_valid(dentry) ||

		   dir_lease_is_valid(dir, dentry)) {

	} else {

		valid = dentry_lease_is_valid(dentry, flags, dir);

		if (valid == -ECHILD)

			return valid;

		if (valid || dir_lease_is_valid(dir, dentry)) {

			if (d_really_is_positive(dentry))

				valid = ceph_is_any_caps(d_inode(dentry));

			else

				valid = 1;

		}

	}



	if (!valid) {

		struct ceph_mds_client *mdsc =
@@ -1238,6 +1253,9 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) 
		struct ceph_mds_request *req;

		int op, mask, err;



		if (flags & LOOKUP_RCU)

			return -ECHILD;



		op = ceph_snap(dir) == CEPH_SNAPDIR ?

			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;

		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
@@ -1273,6 +1291,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) 
		ceph_dir_clear_complete(dir);

	}



	if (!(flags & LOOKUP_RCU))

		dput(parent);

	return valid;

}
@@ -1286,10 +1305,14 @@ static void ceph_d_release(struct dentry *dentry) 


	dout("d_release %p\n", dentry);

	ceph_dentry_lru_del(dentry);



	spin_lock(&dentry->d_lock);

	dentry->d_fsdata = NULL;

	spin_unlock(&dentry->d_lock);



	if (di->lease_session)

		ceph_put_mds_session(di->lease_session);

	kmem_cache_free(ceph_dentry_cachep, di);

	dentry->d_fsdata = NULL;

}



static int ceph_snapdir_d_revalidate(struct dentry *dentry,

CRA Git | Maintained and supported by SUSTech CRA and CCSE