Merge tag 'ceph-for-4.20-rc1' of git://github.com/ceph/ceph-client

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

   - a series that fixes some old memory allocation issues in libceph
     (myself). We no longer allocate memory in places where allocation
     failures cannot be handled and BUG when the allocation fails.

   - support for copy_file_range() syscall (Luis Henriques). If size and
     alignment conditions are met, it leverages RADOS copy-from
     operation. Otherwise, a local copy is performed.

   - a patch that reduces memory requirement of ceph_sync_read() from
     the size of the entire read to the size of one object (Zheng Yan).

   - fallocate() syscall is now restricted to FALLOC_FL_PUNCH_HOLE (Luis
     Henriques)"

* tag 'ceph-for-4.20-rc1' of git://github.com/ceph/ceph-client: (25 commits)
  ceph: new mount option to disable usage of copy-from op
  ceph: support copy_file_range file operation
  libceph: support the RADOS copy-from operation
  ceph: add non-blocking parameter to ceph_try_get_caps()
  libceph: check reply num_data_items in setup_request_data()
  libceph: preallocate message data items
  libceph, rbd, ceph: move ceph_osdc_alloc_messages() calls
  libceph: introduce alloc_watch_request()
  libceph: assign cookies in linger_submit()
  libceph: enable fallback to ceph_msg_new() in ceph_msgpool_get()
  ceph: num_ops is off by one in ceph_aio_retry_work()
  libceph: no need to call osd_req_opcode_valid() in osd_req_encode_op()
  ceph: set timeout conditionally in __cap_delay_requeue
  libceph: don't consume a ref on pagelist in ceph_msg_data_add_pagelist()
  libceph: introduce ceph_pagelist_alloc()
  libceph: osd_req_op_cls_init() doesn't need to take opcode
  libceph: bump CEPH_MSG_MAX_DATA_LEN
  ceph: only allow punch hole mode in fallocate
  ceph: refactor ceph_sync_read()
  ceph: check if LOOKUPNAME request was aborted when filling trace
  ...

Documentation/filesystems/ceph.txt

@@ -151,6 +151,11 @@ Mount Options
         Report overall filesystem usage in statfs instead of using the root
         directory quota.
 
+  nocopyfrom
+        Don't use the RADOS 'copy-from' operation to perform remote object
+        copies.  Currently, it's only used in copy_file_range, which will revert
+        to the default VFS implementation if this option is used.
+
 More Information
 ================
 

drivers/block/rbd.c

@@ -1500,9 +1500,6 @@ rbd_osd_req_create(struct rbd_obj_request *obj_req, unsigned int num_ops)
 			rbd_dev->header.object_prefix, obj_req->ex.oe_objno))
 		goto err_req;
 
-	if (ceph_osdc_alloc_messages(req, GFP_NOIO))
-		goto err_req;
-
 	return req;
 
 err_req:
@@ -1945,6 +1942,10 @@ static int __rbd_img_fill_request(struct rbd_img_request *img_req)
 		}
 		if (ret)
 			return ret;
+
+		ret = ceph_osdc_alloc_messages(obj_req->osd_req, GFP_NOIO);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -2374,8 +2375,7 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes)
 	if (!obj_req->osd_req)
 		return -ENOMEM;
 
-	ret = osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
-				  "copyup");
+	ret = osd_req_op_cls_init(obj_req->osd_req, 0, "rbd", "copyup");
 	if (ret)
 		return ret;
 
@@ -2405,6 +2405,10 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes)
 		rbd_assert(0);
 	}
 
+	ret = ceph_osdc_alloc_messages(obj_req->osd_req, GFP_NOIO);
+	if (ret)
+		return ret;
+
 	rbd_obj_request_submit(obj_req);
 	return 0;
 }
@@ -3784,10 +3788,6 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	ceph_oloc_copy(&req->r_base_oloc, oloc);
 	req->r_flags = CEPH_OSD_FLAG_READ;
 
-	ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
-	if (ret)
-		goto out_req;
-
 	pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
 	if (IS_ERR(pages)) {
 		ret = PTR_ERR(pages);
@@ -3798,6 +3798,10 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	osd_req_op_extent_osd_data_pages(req, 0, pages, buf_len, 0, false,
 					 true);
 
+	ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+	if (ret)
+		goto out_req;
+
 	ceph_osdc_start_request(osdc, req, false);
 	ret = ceph_osdc_wait_request(osdc, req);
 	if (ret >= 0)
@@ -6067,7 +6071,7 @@ static ssize_t rbd_remove_single_major(struct bus_type *bus,
  * create control files in sysfs
  * /sys/bus/rbd/...
  */
-static int rbd_sysfs_init(void)
+static int __init rbd_sysfs_init(void)
 {
 	int ret;
 
@@ -6082,13 +6086,13 @@ static int rbd_sysfs_init(void)
 	return ret;
 }
 
-static void rbd_sysfs_cleanup(void)
+static void __exit rbd_sysfs_cleanup(void)
 {
 	bus_unregister(&rbd_bus_type);
 	device_unregister(&rbd_root_dev);
 }
 
-static int rbd_slab_init(void)
+static int __init rbd_slab_init(void)
 {
 	rbd_assert(!rbd_img_request_cache);
 	rbd_img_request_cache = KMEM_CACHE(rbd_img_request, 0);

fs/ceph/acl.c

@@ -104,6 +104,11 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	struct timespec64 old_ctime = inode->i_ctime;
 	umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
 
+	if (ceph_snap(inode) != CEPH_NOSNAP) {
+		ret = -EROFS;
+		goto out;
+	}
+
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
@@ -138,11 +143,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 			goto out_free;
 	}
 
-	if (ceph_snap(inode) != CEPH_NOSNAP) {
-		ret = -EROFS;
-		goto out_free;
-	}
-
 	if (new_mode != old_mode) {
 		newattrs.ia_ctime = current_time(inode);
 		newattrs.ia_mode = new_mode;
@@ -206,10 +206,9 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
 	tmp_buf = kmalloc(max(val_size1, val_size2), GFP_KERNEL);
 	if (!tmp_buf)
 		goto out_err;
-	pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_KERNEL);
+	pagelist = ceph_pagelist_alloc(GFP_KERNEL);
 	if (!pagelist)
 		goto out_err;
-	ceph_pagelist_init(pagelist);
 
 	err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
 	if (err)

fs/ceph/addr.c

@@ -322,7 +322,7 @@ static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx,
 		/* 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);
+		ret = ceph_try_get_caps(ci, CEPH_CAP_FILE_RD, want, true, &got);
 		if (ret < 0) {
 			dout("start_read %p, error getting cap\n", inode);
 		} else if (!(got & want)) {

fs/ceph/caps.c

@@ -519,9 +519,9 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
  *    -> we take mdsc->cap_delay_lock
  */
 static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
-				struct ceph_inode_info *ci)
+				struct ceph_inode_info *ci,
+				bool set_timeout)
 {
-	__cap_set_timeouts(mdsc, ci);
 	dout("__cap_delay_requeue %p flags %d at %lu\n", &ci->vfs_inode,
 	     ci->i_ceph_flags, ci->i_hold_caps_max);
 	if (!mdsc->stopping) {
@@ -531,6 +531,8 @@ static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
 				goto no_change;
 			list_del_init(&ci->i_cap_delay_list);
 		}
+		if (set_timeout)
+			__cap_set_timeouts(mdsc, ci);
 		list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_delay_list);
 no_change:
 		spin_unlock(&mdsc->cap_delay_lock);
@@ -720,7 +722,7 @@ void ceph_add_cap(struct inode *inode,
 		dout(" issued %s, mds wanted %s, actual %s, queueing\n",
 		     ceph_cap_string(issued), ceph_cap_string(wanted),
 		     ceph_cap_string(actual_wanted));
-		__cap_delay_requeue(mdsc, ci);
+		__cap_delay_requeue(mdsc, ci, true);
 	}
 
 	if (flags & CEPH_CAP_FLAG_AUTH) {
@@ -1647,7 +1649,7 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 	if (((was | ci->i_flushing_caps) & CEPH_CAP_FILE_BUFFER) &&
 	    (mask & CEPH_CAP_FILE_BUFFER))
 		dirty |= I_DIRTY_DATASYNC;
-	__cap_delay_requeue(mdsc, ci);
+	__cap_delay_requeue(mdsc, ci, true);
 	return dirty;
 }
 
@@ -2065,7 +2067,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 
 	/* Reschedule delayed caps release if we delayed anything */
 	if (delayed)
-		__cap_delay_requeue(mdsc, ci);
+		__cap_delay_requeue(mdsc, ci, false);
 
 	spin_unlock(&ci->i_ceph_lock);
 
@@ -2125,7 +2127,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid)
 
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
-			__cap_delay_requeue(mdsc, ci);
+			__cap_delay_requeue(mdsc, ci, true);
 			spin_unlock(&ci->i_ceph_lock);
 		}
 	} else {
@@ -2671,17 +2673,18 @@ 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 ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want,
+		      bool nonblock, int *got)
 {
 	int ret, err = 0;
 
 	BUG_ON(need & ~CEPH_CAP_FILE_RD);
-	BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO));
+	BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO|CEPH_CAP_FILE_SHARED));
 	ret = ceph_pool_perm_check(ci, need);
 	if (ret < 0)
 		return ret;
 
-	ret = try_get_cap_refs(ci, need, want, 0, true, got, &err);
+	ret = try_get_cap_refs(ci, need, want, 0, nonblock, got, &err);
 	if (ret) {
 		if (err == -EAGAIN) {
 			ret = 0;