Merge remote-tracking branch 'linux-fslc/4.9-1.0.x-imx' into toradex_4.9-1.0.x-imx-next

10 files changed, 141 insertions, 58 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index ef3ebd780aff..7b79a54a2789 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -188,7 +188,7 @@ static int ceph_releasepage(struct page *page, gfp_t g)
 /*
  * read a single page, without unlocking it.
  */
-static int readpage_nounlock(struct file *filp, struct page *page)
+static int ceph_do_readpage(struct file *filp, struct page *page)
 {
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -218,7 +218,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 
 	err = ceph_readpage_from_fscache(inode, page);
 	if (err == 0)
-		goto out;
+		return -EINPROGRESS;
 
 	dout("readpage inode %p file %p page %p index %lu\n",
 	     inode, filp, page, page->index);
@@ -248,8 +248,11 @@ out:
 
 static int ceph_readpage(struct file *filp, struct page *page)
 {
-	int r = readpage_nounlock(filp, page);
-	unlock_page(page);
+	int r = ceph_do_readpage(filp, page);
+	if (r != -EINPROGRESS)
+		unlock_page(page);
+	else
+		r = 0;
 	return r;
 }
 
@@ -315,7 +318,32 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	struct page **pages;
 	pgoff_t next_index;
 	int nr_pages = 0;
-	int ret;
+	int got = 0;
+	int ret = 0;
+
+	if (!current->journal_info) {
+		/* caller of readpages does not hold buffer and read caps
+		 * (fadvise, madvise and readahead cases) */
+		int want = CEPH_CAP_FILE_CACHE;
+		ret = ceph_try_get_caps(ci, CEPH_CAP_FILE_RD, want, &got);
+		if (ret < 0) {
+			dout("start_read %p, error getting cap\n", inode);
+		} else if (!(got & want)) {
+			dout("start_read %p, no cache cap\n", inode);
+			ret = 0;
+		}
+		if (ret <= 0) {
+			if (got)
+				ceph_put_cap_refs(ci, got);
+			while (!list_empty(page_list)) {
+				page = list_entry(page_list->prev,
+						  struct page, lru);
+				list_del(&page->lru);
+				put_page(page);
+			}
+			return ret;
+		}
+	}
 
 	off = (u64) page_offset(page);
 
@@ -338,15 +366,18 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 				    CEPH_OSD_FLAG_READ, NULL,
 				    ci->i_truncate_seq, ci->i_truncate_size,
 				    false);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
+	if (IS_ERR(req)) {
+		ret = PTR_ERR(req);
+		goto out;
+	}
 
 	/* build page vector */
 	nr_pages = calc_pages_for(0, len);
 	pages = kmalloc(sizeof(*pages) * nr_pages, GFP_KERNEL);
-	ret = -ENOMEM;
-	if (!pages)
-		goto out;
+	if (!pages) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
 	for (i = 0; i < nr_pages; ++i) {
 		page = list_entry(page_list->prev, struct page, lru);
 		BUG_ON(PageLocked(page));
@@ -363,6 +394,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 			nr_pages = i;
 			if (nr_pages > 0) {
 				len = nr_pages << PAGE_SHIFT;
+				osd_req_op_extent_update(req, 0, len);
 				break;
 			}
 			goto out_pages;
@@ -378,6 +410,12 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	if (ret < 0)
 		goto out_pages;
 	ceph_osdc_put_request(req);
+
+	/* After adding locked pages to page cache, the inode holds cache cap.
+	 * So we can drop our cap refs. */
+	if (got)
+		ceph_put_cap_refs(ci, got);
+
 	return nr_pages;
 
 out_pages:
@@ -386,8 +424,11 @@ out_pages:
 		unlock_page(pages[i]);
 	}
 	ceph_put_page_vector(pages, nr_pages, false);
-out:
+out_put:
 	ceph_osdc_put_request(req);
+out:
+	if (got)
+		ceph_put_cap_refs(ci, got);
 	return ret;
 }
 
@@ -424,7 +465,6 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
 		rc = start_read(inode, page_list, max);
 		if (rc < 0)
 			goto out;
-		BUG_ON(rc == 0);
 	}
 out:
 	ceph_fscache_readpages_cancel(inode, page_list);
@@ -708,7 +748,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
-	unsigned wsize = 1 << inode->i_blkbits;
+	unsigned int wsize = i_blocksize(inode);
 	struct ceph_osd_request *req = NULL;
 	int do_sync = 0;
 	loff_t snap_size, i_size;
@@ -1198,7 +1238,7 @@ retry_locked:
 			goto retry_locked;
 		r = writepage_nounlock(page, NULL);
 		if (r < 0)
-			goto fail_nosnap;
+			goto fail_unlock;
 		goto retry_locked;
 	}
 
@@ -1226,11 +1266,14 @@ retry_locked:
 	}
 
 	/* we need to read it. */
-	r = readpage_nounlock(file, page);
-	if (r < 0)
-		goto fail_nosnap;
+	r = ceph_do_readpage(file, page);
+	if (r < 0) {
+		if (r == -EINPROGRESS)
+			return -EAGAIN;
+		goto fail_unlock;
+	}
 	goto retry_locked;
-fail_nosnap:
+fail_unlock:
 	unlock_page(page);
 	return r;
 }
@@ -1371,9 +1414,11 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	     inode, off, (size_t)PAGE_SIZE, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
-	    ci->i_inline_version == CEPH_INLINE_NONE)
+	    ci->i_inline_version == CEPH_INLINE_NONE) {
+		current->journal_info = vma->vm_file;
 		ret = filemap_fault(vma, vmf);
-	else
+		current->journal_info = NULL;
+	} else
 		ret = -EAGAIN;
 
 	dout("filemap_fault %p %llu~%zd dropping cap refs on %s ret %d\n",
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 5bc5d37b1217..a2d7997afd94 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -240,13 +240,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
 	}
 }
 
-static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
-{
-	if (!error)
-		SetPageUptodate(page);
-}
-
-static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error)
+static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
 {
 	if (!error)
 		SetPageUptodate(page);
@@ -274,7 +268,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
 		return -ENOBUFS;
 
 	ret = fscache_read_or_alloc_page(ci->fscache, page,
-					 ceph_vfs_readpage_complete, NULL,
+					 ceph_readpage_from_fscache_complete, NULL,
 					 GFP_KERNEL);
 
 	switch (ret) {
@@ -303,7 +297,7 @@ int ceph_readpages_from_fscache(struct inode *inode,
 		return -ENOBUFS;
 
 	ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
-					  ceph_vfs_readpage_complete_unlock,
+					  ceph_readpage_from_fscache_complete,
 					  NULL, mapping_gfp_mask(mapping));
 
 	switch (ret) {
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index f3f21105b860..3e1c136aadb7 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1900,6 +1900,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid)
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
+		spin_unlock(&ci->i_ceph_lock);
 		dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
 		goto out;
 	}
@@ -1917,8 +1918,10 @@ retry:
 			mutex_lock(&session->s_mutex);
 			goto retry;
 		}
-		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN)
+		if (cap->session->s_state < CEPH_MDS_SESSION_OPEN) {
+			spin_unlock(&ci->i_ceph_lock);
 			goto out;
+		}
 
 		flushing = __mark_caps_flushing(inode, session, true,
 						&flush_tid, &oldest_flush_tid);
@@ -2479,6 +2482,27 @@ static void check_max_size(struct inode *inode, loff_t endoff)
 		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
 }
 
+int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, int *got)
+{
+	int ret, err = 0;
+
+	BUG_ON(need & ~CEPH_CAP_FILE_RD);
+	BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO));
+	ret = ceph_pool_perm_check(ci, need);
+	if (ret < 0)
+		return ret;
+
+	ret = try_get_cap_refs(ci, need, want, 0, true, got, &err);
+	if (ret) {
+		if (err == -EAGAIN) {
+			ret = 0;
+		} else if (err < 0) {
+			ret = err;
+		}
+	}
+	return ret;
+}
+
 /*
  * Wait for caps, and take cap references.  If we can't get a WR cap
  * due to a small max_size, make sure we check_max_size (and possibly
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 1afa11191000..cec25691cbae 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -292,6 +292,11 @@ out:
 		if (ret < 0)
 			err = ret;
 		dput(last);
+		/* last_name no longer match cache index */
+		if (fi->readdir_cache_idx >= 0) {
+			fi->readdir_cache_idx = -1;
+			fi->dir_release_count = 0;
+		}
 	}
 	return err;
 }
@@ -315,7 +320,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int i;
 	int err;
-	u32 ftype;
+	unsigned frag = -1;
 	struct ceph_mds_reply_info_parsed *rinfo;
 
 	dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
@@ -362,7 +367,6 @@ more:
 	/* do we have the correct frag content buffered? */
 	if (need_send_readdir(fi, ctx->pos)) {
 		struct ceph_mds_request *req;
-		unsigned frag;
 		int op = ceph_snap(inode) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
 
@@ -373,8 +377,11 @@ more:
 		}
 
 		if (is_hash_order(ctx->pos)) {
-			frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
-						NULL, NULL);
+			/* fragtree isn't always accurate. choose frag
+			 * based on previous reply when possible. */
+			if (frag == (unsigned)-1)
+				frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
+							NULL, NULL);
 		} else {
 			frag = fpos_frag(ctx->pos);
 		}
@@ -497,6 +504,7 @@ more:
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 		struct ceph_vino vino;
 		ino_t ino;
+		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -519,15 +527,17 @@ more:
 		ctx->pos++;
 	}
 
+	ceph_mdsc_put_request(fi->last_readdir);
+	fi->last_readdir = NULL;
+
 	if (fi->next_offset > 2) {
-		ceph_mdsc_put_request(fi->last_readdir);
-		fi->last_readdir = NULL;
+		frag = fi->frag;
 		goto more;
 	}
 
 	/* more frags? */
 	if (!ceph_frag_is_rightmost(fi->frag)) {
-		unsigned frag = ceph_frag_next(fi->frag);
+		frag = ceph_frag_next(fi->frag);
 		if (is_hash_order(ctx->pos)) {
 			loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
 							fi->next_offset, true);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f995e3528a33..ca3f630db90f 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1249,8 +1249,9 @@ again:
 		dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
 		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
 		     ceph_cap_string(got));
-
+		current->journal_info = filp;
 		ret = generic_file_read_iter(iocb, to);
+		current->journal_info = NULL;
 	}
 	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
 	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 12f2252f6c98..4a6df2ce0f76 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1323,8 +1323,8 @@ retry_lookup:
 				ceph_dir_clear_ordered(dir);
 				dout("d_delete %p\n", dn);
 				d_delete(dn);
-			} else {
-				if (have_lease && d_unhashed(dn))
+			} else if (have_lease) {
+				if (d_unhashed(dn))
 					d_add(dn, NULL);
 				update_dentry_lease(dn, rinfo->dlease,
 						    session,
@@ -2080,11 +2080,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
-	if (ia_valid & ATTR_MODE) {
-		err = posix_acl_chmod(inode, attr->ia_mode);
-		if (err)
-			goto out_put;
-	}
 
 	if (mask) {
 		req->r_inode = inode;
@@ -2098,13 +2093,11 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	     ceph_cap_string(dirtied), mask);
 
 	ceph_mdsc_put_request(req);
-	if (mask & CEPH_SETATTR_SIZE)
-		__ceph_do_pending_vmtruncate(inode);
-	ceph_free_cap_flush(prealloc_cf);
-	return err;
-out_put:
-	ceph_mdsc_put_request(req);
 	ceph_free_cap_flush(prealloc_cf);
+
+	if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+		__ceph_do_pending_vmtruncate(inode);
+
 	return err;
 }
 
@@ -2123,7 +2116,12 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err != 0)
 		return err;
 
-	return __ceph_setattr(inode, attr);
+	err = __ceph_setattr(inode, attr);
+
+	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+		err = posix_acl_chmod(inode, attr->ia_mode);
+
+	return err;
 }
 
 /*
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 7d752d53353a..4c9c72f26eb9 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -25,7 +25,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
 		l.stripe_count = ci->i_layout.stripe_count;
 		l.object_size = ci->i_layout.object_size;
 		l.data_pool = ci->i_layout.pool_id;
-		l.preferred_osd = (s32)-1;
+		l.preferred_osd = -1;
 		if (copy_to_user(arg, &l, sizeof(l)))
 			return -EFAULT;
 	}
@@ -97,7 +97,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 		nl.data_pool = ci->i_layout.pool_id;
 
 	/* this is obsolete, and always -1 */
-	nl.preferred_osd = le64_to_cpu(-1);
+	nl.preferred_osd = -1;
 
 	err = __validate_layout(mdsc, &nl);
 	if (err)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 6a26c7bd1286..c0f52c443c34 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -628,6 +628,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 {
 	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
 
+	/* Never leave an unregistered request on an unsafe list! */
+	list_del_init(&req->r_unsafe_item);
+
 	if (req->r_tid == mdsc->oldest_tid) {
 		struct rb_node *p = rb_next(&req->r_node);
 		mdsc->oldest_tid = 0;
@@ -1036,7 +1039,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc,
 	while (!list_empty(&session->s_unsafe)) {
 		req = list_first_entry(&session->s_unsafe,
 				       struct ceph_mds_request, r_unsafe_item);
-		list_del_init(&req->r_unsafe_item);
 		pr_warn_ratelimited(" dropping unsafe request %llu\n",
 				    req->r_tid);
 		__unregister_request(mdsc, req);
@@ -1780,13 +1782,18 @@ static int build_dentry_path(struct dentry *dentry,
 			     int *pfreepath)
 {
 	char *path;
+	struct inode *dir;
 
-	if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP) {
-		*pino = ceph_ino(d_inode(dentry->d_parent));
+	rcu_read_lock();
+	dir = d_inode_rcu(dentry->d_parent);
+	if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
+		*pino = ceph_ino(dir);
+		rcu_read_unlock();
 		*ppath = dentry->d_name.name;
 		*ppathlen = dentry->d_name.len;
 		return 0;
 	}
+	rcu_read_unlock();
 	path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
@@ -2423,7 +2430,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			 * useful we could do with a revised return value.
 			 */
 			dout("got safe reply %llu, mds%d\n", tid, mds);
-			list_del_init(&req->r_unsafe_item);
 
 			/* last unsafe request during umount? */
 			if (mdsc->stopping && !__get_oldest_req(mdsc))
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3e3fa9163059..622d5dd9f616 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -905,6 +905,8 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
 
 extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 			 loff_t endoff, int *got, struct page **pinned_page);
+extern int ceph_try_get_caps(struct ceph_inode_info *ci,
+			     int need, int want, int *got);
 
 /* for counting open files by mode */
 extern void __ceph_get_fmode(struct ceph_inode_info *ci, int mode);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index febc28f9e2c2..75267cdd5dfd 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -392,6 +392,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 
 	if (update_xattr) {
 		int err = 0;
+
 		if (xattr && (flags & XATTR_CREATE))
 			err = -EEXIST;
 		else if (!xattr && (flags & XATTR_REPLACE))
@@ -399,12 +400,14 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		if (err) {
 			kfree(name);
 			kfree(val);
+			kfree(*newxattr);
 			return err;
 		}
 		if (update_xattr < 0) {
 			if (xattr)
 				__remove_xattr(ci, xattr);
 			kfree(name);
+			kfree(*newxattr);
 			return 0;
 		}
 	}