Merge tag 'ceph-for-4.17-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The big ticket items are:

   - support for rbd "fancy" striping (myself).

     The striping feature bit is now fully implemented, allowing mapping
     v2 images with non-default striping patterns. This completes
     support for --image-format 2.

   - CephFS quota support (Luis Henriques and Zheng Yan).

     This set is based on the new SnapRealm code in the upcoming v13.y.z
     ("Mimic") release. Quota handling will be rejected on older
     filesystems.

   - memory usage improvements in CephFS (Chengguang Xu).

     Directory specific bits have been split out of ceph_file_info and
     some effort went into improving cap reservation code to avoid OOM
     crashes.

  Also included a bunch of assorted fixes all over the place from
  Chengguang and others"

* tag 'ceph-for-4.17-rc1' of git://github.com/ceph/ceph-client: (67 commits)
  ceph: quota: report root dir quota usage in statfs
  ceph: quota: add counter for snaprealms with quota
  ceph: quota: cache inode pointer in ceph_snap_realm
  ceph: fix root quota realm check
  ceph: don't check quota for snap inode
  ceph: quota: update MDS when max_bytes is approaching
  ceph: quota: support for ceph.quota.max_bytes
  ceph: quota: don't allow cross-quota renames
  ceph: quota: support for ceph.quota.max_files
  ceph: quota: add initial infrastructure to support cephfs quotas
  rbd: remove VLA usage
  rbd: fix spelling mistake: "reregisteration" -> "reregistration"
  ceph: rename function drop_leases() to a more descriptive name
  ceph: fix invalid point dereference for error case in mdsc destroy
  ceph: return proper bool type to caller instead of pointer
  ceph: optimize memory usage
  ceph: optimize mds session register
  libceph, ceph: add __init attribution to init funcitons
  ceph: filter out used flags when printing unused open flags
  ceph: don't wait on writeback when there is no more dirty pages
  ...

9 files changed, 453 insertions, 168 deletions

diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index b4bded4b5396..12bf49772d24 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -8,6 +8,7 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
 	mon_client.o \
 	cls_lock_client.o \
 	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
+	striper.o \
 	debugfs.o \
 	auth.o auth_none.o \
 	crypto.o armor.o \
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 4adf07826f4a..584fdbef2088 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -72,6 +72,7 @@ const char *ceph_msg_type_name(int type)
 	case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
 	case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
 	case CEPH_MSG_MDS_MAP: return "mds_map";
+	case CEPH_MSG_FS_MAP_USER: return "fs_map_user";
 	case CEPH_MSG_CLIENT_SESSION: return "client_session";
 	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
 	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
@@ -79,8 +80,13 @@ const char *ceph_msg_type_name(int type)
 	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
 	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
 	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
+	case CEPH_MSG_CLIENT_QUOTA: return "client_quota";
 	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
 	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
+	case CEPH_MSG_POOLOP_REPLY: return "poolop_reply";
+	case CEPH_MSG_POOLOP: return "poolop";
+	case CEPH_MSG_MON_COMMAND: return "mon_command";
+	case CEPH_MSG_MON_COMMAND_ACK: return "mon_command_ack";
 	case CEPH_MSG_OSD_MAP: return "osd_map";
 	case CEPH_MSG_OSD_OP: return "osd_op";
 	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
@@ -217,7 +223,7 @@ static int parse_fsid(const char *str, struct ceph_fsid *fsid)
 
 	if (i == 16)
 		err = 0;
-	dout("parse_fsid ret %d got fsid %pU", err, fsid);
+	dout("parse_fsid ret %d got fsid %pU\n", err, fsid);
 	return err;
 }
 
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index bf9d079cbafd..02172c408ff2 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -347,10 +347,12 @@ struct key_type key_type_ceph = {
 	.destroy	= ceph_key_destroy,
 };
 
-int ceph_crypto_init(void) {
+int __init ceph_crypto_init(void)
+{
 	return register_key_type(&key_type_ceph);
 }
 
-void ceph_crypto_shutdown(void) {
+void ceph_crypto_shutdown(void)
+{
 	unregister_key_type(&key_type_ceph);
 }
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 1eef6806aa1a..02952605d121 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -389,7 +389,7 @@ CEPH_DEFINE_SHOW_FUNC(monc_show)
 CEPH_DEFINE_SHOW_FUNC(osdc_show)
 CEPH_DEFINE_SHOW_FUNC(client_options_show)
 
-int ceph_debugfs_init(void)
+int __init ceph_debugfs_init(void)
 {
 	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
 	if (!ceph_debugfs_dir)
@@ -418,7 +418,7 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 		goto out;
 
 	client->monc.debugfs_file = debugfs_create_file("monc",
-						      0600,
+						      0400,
 						      client->debugfs_dir,
 						      client,
 						      &monc_show_fops);
@@ -426,7 +426,7 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 		goto out;
 
 	client->osdc.debugfs_file = debugfs_create_file("osdc",
-						      0600,
+						      0400,
 						      client->debugfs_dir,
 						      client,
 						      &osdc_show_fops);
@@ -434,7 +434,7 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 		goto out;
 
 	client->debugfs_monmap = debugfs_create_file("monmap",
-					0600,
+					0400,
 					client->debugfs_dir,
 					client,
 					&monmap_show_fops);
@@ -442,7 +442,7 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 		goto out;
 
 	client->debugfs_osdmap = debugfs_create_file("osdmap",
-					0600,
+					0400,
 					client->debugfs_dir,
 					client,
 					&osdmap_show_fops);
@@ -450,7 +450,7 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 		goto out;
 
 	client->debugfs_options = debugfs_create_file("client_options",
-					0600,
+					0400,
 					client->debugfs_dir,
 					client,
 					&client_options_show_fops);
@@ -477,7 +477,7 @@ void ceph_debugfs_client_cleanup(struct ceph_client *client)
 
 #else  /* CONFIG_DEBUG_FS */
 
-int ceph_debugfs_init(void)
+int __init ceph_debugfs_init(void)
 {
 	return 0;
 }
@@ -496,6 +496,3 @@ void ceph_debugfs_client_cleanup(struct ceph_client *client)
 }
 
 #endif  /* CONFIG_DEBUG_FS */
-
-EXPORT_SYMBOL(ceph_debugfs_init);
-EXPORT_SYMBOL(ceph_debugfs_cleanup);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 8a4d3758030b..fcb40c12b1f8 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -277,7 +277,7 @@ static void _ceph_msgr_exit(void)
 	ceph_msgr_slab_exit();
 }
 
-int ceph_msgr_init(void)
+int __init ceph_msgr_init(void)
 {
 	if (ceph_msgr_slab_init())
 		return -ENOMEM;
@@ -299,7 +299,6 @@ int ceph_msgr_init(void)
 
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(ceph_msgr_init);
 
 void ceph_msgr_exit(void)
 {
@@ -307,7 +306,6 @@ void ceph_msgr_exit(void)
 
 	_ceph_msgr_exit();
 }
-EXPORT_SYMBOL(ceph_msgr_exit);
 
 void ceph_msgr_flush(void)
 {
@@ -839,93 +837,112 @@ static void ceph_msg_data_bio_cursor_init(struct ceph_msg_data_cursor *cursor,
 					size_t length)
 {
 	struct ceph_msg_data *data = cursor->data;
-	struct bio *bio;
+	struct ceph_bio_iter *it = &cursor->bio_iter;
 
-	BUG_ON(data->type != CEPH_MSG_DATA_BIO);
+	cursor->resid = min_t(size_t, length, data->bio_length);
+	*it = data->bio_pos;
+	if (cursor->resid < it->iter.bi_size)
+		it->iter.bi_size = cursor->resid;
 
-	bio = data->bio;
-	BUG_ON(!bio);
-
-	cursor->resid = min(length, data->bio_length);
-	cursor->bio = bio;
-	cursor->bvec_iter = bio->bi_iter;
-	cursor->last_piece =
-		cursor->resid <= bio_iter_len(bio, cursor->bvec_iter);
+	BUG_ON(cursor->resid < bio_iter_len(it->bio, it->iter));
+	cursor->last_piece = cursor->resid == bio_iter_len(it->bio, it->iter);
 }
 
 static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor,
 						size_t *page_offset,
 						size_t *length)
 {
-	struct ceph_msg_data *data = cursor->data;
-	struct bio *bio;
-	struct bio_vec bio_vec;
-
-	BUG_ON(data->type != CEPH_MSG_DATA_BIO);
-
-	bio = cursor->bio;
-	BUG_ON(!bio);
-
-	bio_vec = bio_iter_iovec(bio, cursor->bvec_iter);
-
-	*page_offset = (size_t) bio_vec.bv_offset;
-	BUG_ON(*page_offset >= PAGE_SIZE);
-	if (cursor->last_piece) /* pagelist offset is always 0 */
-		*length = cursor->resid;
-	else
-		*length = (size_t) bio_vec.bv_len;
-	BUG_ON(*length > cursor->resid);
-	BUG_ON(*page_offset + *length > PAGE_SIZE);
+	struct bio_vec bv = bio_iter_iovec(cursor->bio_iter.bio,
+					   cursor->bio_iter.iter);
 
-	return bio_vec.bv_page;
+	*page_offset = bv.bv_offset;
+	*length = bv.bv_len;
+	return bv.bv_page;
 }
 
 static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
 					size_t bytes)
 {
-	struct bio *bio;
-	struct bio_vec bio_vec;
+	struct ceph_bio_iter *it = &cursor->bio_iter;
 
-	BUG_ON(cursor->data->type != CEPH_MSG_DATA_BIO);
+	BUG_ON(bytes > cursor->resid);
+	BUG_ON(bytes > bio_iter_len(it->bio, it->iter));
+	cursor->resid -= bytes;
+	bio_advance_iter(it->bio, &it->iter, bytes);
 
-	bio = cursor->bio;
-	BUG_ON(!bio);
+	if (!cursor->resid) {
+		BUG_ON(!cursor->last_piece);
+		return false;   /* no more data */
+	}
 
-	bio_vec = bio_iter_iovec(bio, cursor->bvec_iter);
+	if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done))
+		return false;	/* more bytes to process in this segment */
 
-	/* Advance the cursor offset */
+	if (!it->iter.bi_size) {
+		it->bio = it->bio->bi_next;
+		it->iter = it->bio->bi_iter;
+		if (cursor->resid < it->iter.bi_size)
+			it->iter.bi_size = cursor->resid;
+	}
 
-	BUG_ON(cursor->resid < bytes);
-	cursor->resid -= bytes;
+	BUG_ON(cursor->last_piece);
+	BUG_ON(cursor->resid < bio_iter_len(it->bio, it->iter));
+	cursor->last_piece = cursor->resid == bio_iter_len(it->bio, it->iter);
+	return true;
+}
+#endif /* CONFIG_BLOCK */
 
-	bio_advance_iter(bio, &cursor->bvec_iter, bytes);
+static void ceph_msg_data_bvecs_cursor_init(struct ceph_msg_data_cursor *cursor,
+					size_t length)
+{
+	struct ceph_msg_data *data = cursor->data;
+	struct bio_vec *bvecs = data->bvec_pos.bvecs;
 
-	if (bytes < bio_vec.bv_len)
-		return false;	/* more bytes to process in this segment */
+	cursor->resid = min_t(size_t, length, data->bvec_pos.iter.bi_size);
+	cursor->bvec_iter = data->bvec_pos.iter;
+	cursor->bvec_iter.bi_size = cursor->resid;
 
-	/* Move on to the next segment, and possibly the next bio */
+	BUG_ON(cursor->resid < bvec_iter_len(bvecs, cursor->bvec_iter));
+	cursor->last_piece =
+	    cursor->resid == bvec_iter_len(bvecs, cursor->bvec_iter);
+}
 
-	if (!cursor->bvec_iter.bi_size) {
-		bio = bio->bi_next;
-		cursor->bio = bio;
-		if (bio)
-			cursor->bvec_iter = bio->bi_iter;
-		else
-			memset(&cursor->bvec_iter, 0,
-			       sizeof(cursor->bvec_iter));
-	}
+static struct page *ceph_msg_data_bvecs_next(struct ceph_msg_data_cursor *cursor,
+						size_t *page_offset,
+						size_t *length)
+{
+	struct bio_vec bv = bvec_iter_bvec(cursor->data->bvec_pos.bvecs,
+					   cursor->bvec_iter);
+
+	*page_offset = bv.bv_offset;
+	*length = bv.bv_len;
+	return bv.bv_page;
+}
+
+static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
+					size_t bytes)
+{
+	struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs;
+
+	BUG_ON(bytes > cursor->resid);
+	BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter));
+	cursor->resid -= bytes;
+	bvec_iter_advance(bvecs, &cursor->bvec_iter, bytes);
 
-	if (!cursor->last_piece) {
-		BUG_ON(!cursor->resid);
-		BUG_ON(!bio);
-		/* A short read is OK, so use <= rather than == */
-		if (cursor->resid <= bio_iter_len(bio, cursor->bvec_iter))
-			cursor->last_piece = true;
+	if (!cursor->resid) {
+		BUG_ON(!cursor->last_piece);
+		return false;   /* no more data */
 	}
 
+	if (!bytes || cursor->bvec_iter.bi_bvec_done)
+		return false;	/* more bytes to process in this segment */
+
+	BUG_ON(cursor->last_piece);
+	BUG_ON(cursor->resid < bvec_iter_len(bvecs, cursor->bvec_iter));
+	cursor->last_piece =
+	    cursor->resid == bvec_iter_len(bvecs, cursor->bvec_iter);
 	return true;
 }
-#endif /* CONFIG_BLOCK */
 
 /*
  * For a page array, a piece comes from the first page in the array
@@ -1110,6 +1127,9 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
 		ceph_msg_data_bio_cursor_init(cursor, length);
 		break;
 #endif /* CONFIG_BLOCK */
+	case CEPH_MSG_DATA_BVECS:
+		ceph_msg_data_bvecs_cursor_init(cursor, length);
+		break;
 	case CEPH_MSG_DATA_NONE:
 	default:
 		/* BUG(); */
@@ -1158,14 +1178,19 @@ static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
 		page = ceph_msg_data_bio_next(cursor, page_offset, length);
 		break;
 #endif /* CONFIG_BLOCK */
+	case CEPH_MSG_DATA_BVECS:
+		page = ceph_msg_data_bvecs_next(cursor, page_offset, length);
+		break;
 	case CEPH_MSG_DATA_NONE:
 	default:
 		page = NULL;
 		break;
 	}
+
 	BUG_ON(!page);
 	BUG_ON(*page_offset + *length > PAGE_SIZE);
 	BUG_ON(!*length);
+	BUG_ON(*length > cursor->resid);
 	if (last_piece)
 		*last_piece = cursor->last_piece;
 
@@ -1194,6 +1219,9 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
 		new_piece = ceph_msg_data_bio_advance(cursor, bytes);
 		break;
 #endif /* CONFIG_BLOCK */
+	case CEPH_MSG_DATA_BVECS:
+		new_piece = ceph_msg_data_bvecs_advance(cursor, bytes);
+		break;
 	case CEPH_MSG_DATA_NONE:
 	default:
 		BUG();
@@ -1575,13 +1603,18 @@ static int write_partial_message_data(struct ceph_connection *con)
 	 * been revoked, so use the zero page.
 	 */
 	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
-	while (cursor->resid) {
+	while (cursor->total_resid) {
 		struct page *page;
 		size_t page_offset;
 		size_t length;
 		bool last_piece;
 		int ret;
 
+		if (!cursor->resid) {
+			ceph_msg_data_advance(cursor, 0);
+			continue;
+		}
+
 		page = ceph_msg_data_next(cursor, &page_offset, &length,
 					  &last_piece);
 		ret = ceph_tcp_sendpage(con->sock, page, page_offset,
@@ -2297,7 +2330,12 @@ static int read_partial_msg_data(struct ceph_connection *con)
 
 	if (do_datacrc)
 		crc = con->in_data_crc;
-	while (cursor->resid) {
+	while (cursor->total_resid) {
+		if (!cursor->resid) {
+			ceph_msg_data_advance(cursor, 0);
+			continue;
+		}
+
 		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
 		ret = ceph_tcp_recvpage(con->sock, page, page_offset, length);
 		if (ret <= 0) {
@@ -3262,16 +3300,14 @@ void ceph_msg_data_add_pagelist(struct ceph_msg *msg,
 EXPORT_SYMBOL(ceph_msg_data_add_pagelist);
 
 #ifdef	CONFIG_BLOCK
-void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio,
-		size_t length)
+void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
+			   u32 length)
 {
 	struct ceph_msg_data *data;
 
-	BUG_ON(!bio);
-
 	data = ceph_msg_data_create(CEPH_MSG_DATA_BIO);
 	BUG_ON(!data);
-	data->bio = bio;
+	data->bio_pos = *bio_pos;
 	data->bio_length = length;
 
 	list_add_tail(&data->links, &msg->data);
@@ -3280,6 +3316,20 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio,
 EXPORT_SYMBOL(ceph_msg_data_add_bio);
 #endif	/* CONFIG_BLOCK */
 
+void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
+			     struct ceph_bvec_iter *bvec_pos)
+{
+	struct ceph_msg_data *data;
+
+	data = ceph_msg_data_create(CEPH_MSG_DATA_BVECS);
+	BUG_ON(!data);
+	data->bvec_pos = *bvec_pos;
+
+	list_add_tail(&data->links, &msg->data);
+	msg->data_length += bvec_pos->iter.bi_size;
+}
+EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
+
 /*
  * construct a new message with given type, size
  * the new msg has a ref count of 1.
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 1547107f4854..b3dac24412d3 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -60,7 +60,7 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
 	num_mon = ceph_decode_32(&p);
 	ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad);
 
-	if (num_mon >= CEPH_MAX_MON)
+	if (num_mon > CEPH_MAX_MON)
 		goto bad;
 	m = kmalloc(sizeof(*m) + sizeof(m->mon_inst[0])*num_mon, GFP_NOFS);
 	if (m == NULL)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 2814dba5902d..ea2a6c9fb7ce 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -20,6 +20,7 @@
 #include <linux/ceph/decode.h>
 #include <linux/ceph/auth.h>
 #include <linux/ceph/pagelist.h>
+#include <linux/ceph/striper.h>
 
 #define OSD_OPREPLY_FRONT_LEN	512
 
@@ -103,13 +104,12 @@ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen,
 			u64 *objnum, u64 *objoff, u64 *objlen)
 {
 	u64 orig_len = *plen;
-	int r;
+	u32 xlen;
 
 	/* object extent? */
-	r = ceph_calc_file_object_mapping(layout, off, orig_len, objnum,
-					  objoff, objlen);
-	if (r < 0)
-		return r;
+	ceph_calc_file_object_mapping(layout, off, orig_len, objnum,
+					  objoff, &xlen);
+	*objlen = xlen;
 	if (*objlen < orig_len) {
 		*plen = *objlen;
 		dout(" skipping last %llu, final file extent %llu~%llu\n",
@@ -117,7 +117,6 @@ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen,
 	}
 
 	dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen);
-
 	return 0;
 }
 
@@ -148,14 +147,22 @@ static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
 
 #ifdef CONFIG_BLOCK
 static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data,
-			struct bio *bio, size_t bio_length)
+				   struct ceph_bio_iter *bio_pos,
+				   u32 bio_length)
 {
 	osd_data->type = CEPH_OSD_DATA_TYPE_BIO;
-	osd_data->bio = bio;
+	osd_data->bio_pos = *bio_pos;
 	osd_data->bio_length = bio_length;
 }
 #endif /* CONFIG_BLOCK */
 
+static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
+				     struct ceph_bvec_iter *bvec_pos)
+{
+	osd_data->type = CEPH_OSD_DATA_TYPE_BVECS;
+	osd_data->bvec_pos = *bvec_pos;
+}
+
 #define osd_req_op_data(oreq, whch, typ, fld)				\
 ({									\
 	struct ceph_osd_request *__oreq = (oreq);			\
@@ -218,16 +225,29 @@ EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist);
 
 #ifdef CONFIG_BLOCK
 void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
-			unsigned int which, struct bio *bio, size_t bio_length)
+				    unsigned int which,
+				    struct ceph_bio_iter *bio_pos,
+				    u32 bio_length)
 {
 	struct ceph_osd_data *osd_data;
 
 	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
-	ceph_osd_data_bio_init(osd_data, bio, bio_length);
+	ceph_osd_data_bio_init(osd_data, bio_pos, bio_length);
 }
 EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio);
 #endif /* CONFIG_BLOCK */
 
+void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
+					 unsigned int which,
+					 struct ceph_bvec_iter *bvec_pos)
+{
+	struct ceph_osd_data *osd_data;
+
+	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
+	ceph_osd_data_bvecs_init(osd_data, bvec_pos);
+}
+EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos);
+
 static void osd_req_op_cls_request_info_pagelist(
 			struct ceph_osd_request *osd_req,
 			unsigned int which, struct ceph_pagelist *pagelist)
@@ -265,6 +285,23 @@ void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
 }
 EXPORT_SYMBOL(osd_req_op_cls_request_data_pages);
 
+void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req,
+				       unsigned int which,
+				       struct bio_vec *bvecs, u32 bytes)
+{
+	struct ceph_osd_data *osd_data;
+	struct ceph_bvec_iter it = {
+		.bvecs = bvecs,
+		.iter = { .bi_size = bytes },
+	};
+
+	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
+	ceph_osd_data_bvecs_init(osd_data, &it);
+	osd_req->r_ops[which].cls.indata_len += bytes;
+	osd_req->r_ops[which].indata_len += bytes;
+}
+EXPORT_SYMBOL(osd_req_op_cls_request_data_bvecs);
+
 void osd_req_op_cls_response_data_pages(struct ceph_osd_request *osd_req,
 			unsigned int which, struct page **pages, u64 length,
 			u32 alignment, bool pages_from_pool, bool own_pages)
@@ -290,6 +327,8 @@ static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data)
 	case CEPH_OSD_DATA_TYPE_BIO:
 		return (u64)osd_data->bio_length;
 #endif /* CONFIG_BLOCK */
+	case CEPH_OSD_DATA_TYPE_BVECS:
+		return osd_data->bvec_pos.iter.bi_size;
 	default:
 		WARN(true, "unrecognized data type %d\n", (int)osd_data->type);
 		return 0;
@@ -828,8 +867,10 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 		ceph_msg_data_add_pagelist(msg, osd_data->pagelist);
 #ifdef CONFIG_BLOCK
 	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) {
-		ceph_msg_data_add_bio(msg, osd_data->bio, length);
+		ceph_msg_data_add_bio(msg, &osd_data->bio_pos, length);
 #endif
+	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) {
+		ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos);
 	} else {
 		BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE);
 	}
@@ -5065,7 +5106,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 }
 EXPORT_SYMBOL(ceph_osdc_writepages);
 
-int ceph_osdc_setup(void)
+int __init ceph_osdc_setup(void)
 {
 	size_t size = sizeof(struct ceph_osd_request) +
 	    CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op);
@@ -5076,7 +5117,6 @@ int ceph_osdc_setup(void)
 
 	return ceph_osd_request_cache ? 0 : -ENOMEM;
 }
-EXPORT_SYMBOL(ceph_osdc_setup);
 
 void ceph_osdc_cleanup(void)
 {
@@ -5084,7 +5124,6 @@ void ceph_osdc_cleanup(void)
 	kmem_cache_destroy(ceph_osd_request_cache);
 	ceph_osd_request_cache = NULL;
 }
-EXPORT_SYMBOL(ceph_osdc_cleanup);
 
 /*
  * handle incoming message
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 0da27c66349a..9645ffd6acfb 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -4,7 +4,6 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <asm/div64.h>
 
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/osdmap.h>
@@ -2141,76 +2140,6 @@ bool ceph_osds_changed(const struct ceph_osds *old_acting,
 }
 
 /*
- * calculate file layout from given offset, length.
- * fill in correct oid, logical length, and object extent
- * offset, length.
- *
- * for now, we write only a single su, until we can
- * pass a stride back to the caller.
- */
-int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
-				   u64 off, u64 len,
-				   u64 *ono,
-				   u64 *oxoff, u64 *oxlen)
-{
-	u32 osize = layout->object_size;
-	u32 su = layout->stripe_unit;
-	u32 sc = layout->stripe_count;
-	u32 bl, stripeno, stripepos, objsetno;
-	u32 su_per_object;
-	u64 t, su_offset;
-
-	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, len,
-	     osize, su);
-	if (su == 0 || sc == 0)
-		goto invalid;
-	su_per_object = osize / su;
-	if (su_per_object == 0)
-		goto invalid;
-	dout("osize %u / su %u = su_per_object %u\n", osize, su,
-	     su_per_object);
-
-	if ((su & ~PAGE_MASK) != 0)
-		goto invalid;
-
-	/* bl = *off / su; */
-	t = off;
-	do_div(t, su);
-	bl = t;
-	dout("off %llu / su %u = bl %u\n", off, su, bl);
-
-	stripeno = bl / sc;
-	stripepos = bl % sc;
-	objsetno = stripeno / su_per_object;
-
-	*ono = objsetno * sc + stripepos;
-	dout("objset %u * sc %u = ono %u\n", objsetno, sc, (unsigned int)*ono);
-
-	/* *oxoff = *off % layout->fl_stripe_unit;  # offset in su */
-	t = off;
-	su_offset = do_div(t, su);
-	*oxoff = su_offset + (stripeno % su_per_object) * su;
-
-	/*
-	 * Calculate the length of the extent being written to the selected
-	 * object. This is the minimum of the full length requested (len) or
-	 * the remainder of the current stripe being written to.
-	 */
-	*oxlen = min_t(u64, len, su - su_offset);
-
-	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
-	return 0;
-
-invalid:
-	dout(" invalid layout\n");
-	*ono = 0;
-	*oxoff = 0;
-	*oxlen = 0;
-	return -EINVAL;
-}
-EXPORT_SYMBOL(ceph_calc_file_object_mapping);
-
-/*
  * Map an object into a PG.
  *
  * Should only be called with target_oid and target_oloc (as opposed to
diff --git a/net/ceph/striper.c b/net/ceph/striper.c
new file mode 100644
index 000000000000..c36462dc86b7
--- /dev/null
+++ b/net/ceph/striper.c
@@ -0,0 +1,261 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/math64.h>
+#include <linux/slab.h>
+
+#include <linux/ceph/striper.h>
+#include <linux/ceph/types.h>
+
+/*
+ * Map a file extent to a stripe unit within an object.
+ * Fill in objno, offset into object, and object extent length (i.e. the
+ * number of bytes mapped, less than or equal to @l->stripe_unit).
+ *
+ * Example for stripe_count = 3, stripes_per_object = 4:
+ *
+ * blockno   |  0  3  6  9 |  1  4  7 10 |  2  5  8 11 | 12 15 18 21 | 13 16 19
+ * stripeno  |  0  1  2  3 |  0  1  2  3 |  0  1  2  3 |  4  5  6  7 |  4  5  6
+ * stripepos |      0      |      1      |      2      |      0      |      1
+ * objno     |      0      |      1      |      2      |      3      |      4
+ * objsetno  |                    0                    |                    1
+ */
+void ceph_calc_file_object_mapping(struct ceph_file_layout *l,
+				   u64 off, u64 len,
+				   u64 *objno, u64 *objoff, u32 *xlen)
+{
+	u32 stripes_per_object = l->object_size / l->stripe_unit;
+	u64 blockno;	/* which su in the file (i.e. globally) */
+	u32 blockoff;	/* offset into su */
+	u64 stripeno;	/* which stripe */
+	u32 stripepos;	/* which su in the stripe,
+			   which object in the object set */
+	u64 objsetno;	/* which object set */
+	u32 objsetpos;	/* which stripe in the object set */
+
+	blockno = div_u64_rem(off, l->stripe_unit, &blockoff);
+	stripeno = div_u64_rem(blockno, l->stripe_count, &stripepos);
+	objsetno = div_u64_rem(stripeno, stripes_per_object, &objsetpos);
+
+	*objno = objsetno * l->stripe_count + stripepos;
+	*objoff = objsetpos * l->stripe_unit + blockoff;
+	*xlen = min_t(u64, len, l->stripe_unit - blockoff);
+}
+EXPORT_SYMBOL(ceph_calc_file_object_mapping);
+
+/*
+ * Return the last extent with given objno (@object_extents is sorted
+ * by objno).  If not found, return NULL and set @add_pos so that the
+ * new extent can be added with list_add(add_pos, new_ex).
+ */
+static struct ceph_object_extent *
+lookup_last(struct list_head *object_extents, u64 objno,
+	    struct list_head **add_pos)
+{
+	struct list_head *pos;
+
+	list_for_each_prev(pos, object_extents) {
+		struct ceph_object_extent *ex =
+		    list_entry(pos, typeof(*ex), oe_item);
+
+		if (ex->oe_objno == objno)
+			return ex;
+
+		if (ex->oe_objno < objno)
+			break;
+	}
+
+	*add_pos = pos;
+	return NULL;
+}
+
+static struct ceph_object_extent *
+lookup_containing(struct list_head *object_extents, u64 objno,
+		  u64 objoff, u32 xlen)
+{
+	struct ceph_object_extent *ex;
+
+	list_for_each_entry(ex, object_extents, oe_item) {
+		if (ex->oe_objno == objno &&
+		    ex->oe_off <= objoff &&
+		    ex->oe_off + ex->oe_len >= objoff + xlen) /* paranoia */
+			return ex;
+
+		if (ex->oe_objno > objno)
+			break;
+	}
+
+	return NULL;
+}
+
+/*
+ * Map a file extent to a sorted list of object extents.
+ *
+ * We want only one (or as few as possible) object extents per object.
+ * Adjacent object extents will be merged together, each returned object
+ * extent may reverse map to multiple different file extents.
+ *
+ * Call @alloc_fn for each new object extent and @action_fn for each
+ * mapped stripe unit, whether it was merged into an already allocated
+ * object extent or started a new object extent.
+ *
+ * Newly allocated object extents are added to @object_extents.
+ * To keep @object_extents sorted, successive calls to this function
+ * must map successive file extents (i.e. the list of file extents that
+ * are mapped using the same @object_extents must be sorted).
+ *
+ * The caller is responsible for @object_extents.
+ */
+int ceph_file_to_extents(struct ceph_file_layout *l, u64 off, u64 len,
+			 struct list_head *object_extents,
+			 struct ceph_object_extent *alloc_fn(void *arg),
+			 void *alloc_arg,
+			 ceph_object_extent_fn_t action_fn,
+			 void *action_arg)
+{
+	struct ceph_object_extent *last_ex, *ex;
+
+	while (len) {
+		struct list_head *add_pos = NULL;
+		u64 objno, objoff;
+		u32 xlen;
+
+		ceph_calc_file_object_mapping(l, off, len, &objno, &objoff,
+					      &xlen);
+
+		last_ex = lookup_last(object_extents, objno, &add_pos);
+		if (!last_ex || last_ex->oe_off + last_ex->oe_len != objoff) {
+			ex = alloc_fn(alloc_arg);
+			if (!ex)
+				return -ENOMEM;
+
+			ex->oe_objno = objno;
+			ex->oe_off = objoff;
+			ex->oe_len = xlen;
+			if (action_fn)
+				action_fn(ex, xlen, action_arg);
+
+			if (!last_ex)
+				list_add(&ex->oe_item, add_pos);
+			else
+				list_add(&ex->oe_item, &last_ex->oe_item);
+		} else {
+			last_ex->oe_len += xlen;
+			if (action_fn)
+				action_fn(last_ex, xlen, action_arg);
+		}
+
+		off += xlen;
+		len -= xlen;
+	}
+
+	for (last_ex = list_first_entry(object_extents, typeof(*ex), oe_item),
+	     ex = list_next_entry(last_ex, oe_item);
+	     &ex->oe_item != object_extents;
+	     last_ex = ex, ex = list_next_entry(ex, oe_item)) {
+		if (last_ex->oe_objno > ex->oe_objno ||
+		    (last_ex->oe_objno == ex->oe_objno &&
+		     last_ex->oe_off + last_ex->oe_len >= ex->oe_off)) {
+			WARN(1, "%s: object_extents list not sorted!\n",
+			     __func__);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ceph_file_to_extents);
+
+/*
+ * A stripped down, non-allocating version of ceph_file_to_extents(),
+ * for when @object_extents is already populated.
+ */
+int ceph_iterate_extents(struct ceph_file_layout *l, u64 off, u64 len,
+			 struct list_head *object_extents,
+			 ceph_object_extent_fn_t action_fn,
+			 void *action_arg)
+{
+	while (len) {
+		struct ceph_object_extent *ex;
+		u64 objno, objoff;
+		u32 xlen;
+
+		ceph_calc_file_object_mapping(l, off, len, &objno, &objoff,
+					      &xlen);
+
+		ex = lookup_containing(object_extents, objno, objoff, xlen);
+		if (!ex) {
+			WARN(1, "%s: objno %llu %llu~%u not found!\n",
+			     __func__, objno, objoff, xlen);
+			return -EINVAL;
+		}
+
+		action_fn(ex, xlen, action_arg);
+
+		off += xlen;
+		len -= xlen;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ceph_iterate_extents);
+
+/*
+ * Reverse map an object extent to a sorted list of file extents.
+ *
+ * On success, the caller is responsible for:
+ *
+ *     kfree(file_extents)
+ */
+int ceph_extent_to_file(struct ceph_file_layout *l,
+			u64 objno, u64 objoff, u64 objlen,
+			struct ceph_file_extent **file_extents,
+			u32 *num_file_extents)
+{
+	u32 stripes_per_object = l->object_size / l->stripe_unit;
+	u64 blockno;	/* which su */
+	u32 blockoff;	/* offset into su */
+	u64 stripeno;	/* which stripe */
+	u32 stripepos;	/* which su in the stripe,
+			   which object in the object set */
+	u64 objsetno;	/* which object set */
+	u32 i = 0;
+
+	if (!objlen) {
+		*file_extents = NULL;
+		*num_file_extents = 0;
+		return 0;
+	}
+
+	*num_file_extents = DIV_ROUND_UP_ULL(objoff + objlen, l->stripe_unit) -
+				     DIV_ROUND_DOWN_ULL(objoff, l->stripe_unit);
+	*file_extents = kmalloc_array(*num_file_extents, sizeof(**file_extents),
+				      GFP_NOIO);
+	if (!*file_extents)
+		return -ENOMEM;
+
+	div_u64_rem(objoff, l->stripe_unit, &blockoff);
+	while (objlen) {
+		u64 off, len;
+
+		objsetno = div_u64_rem(objno, l->stripe_count, &stripepos);
+		stripeno = div_u64(objoff, l->stripe_unit) +
+						objsetno * stripes_per_object;
+		blockno = stripeno * l->stripe_count + stripepos;
+		off = blockno * l->stripe_unit + blockoff;
+		len = min_t(u64, objlen, l->stripe_unit - blockoff);
+
+		(*file_extents)[i].fe_off = off;
+		(*file_extents)[i].fe_len = len;
+
+		blockoff = 0;
+		objoff += len;
+		objlen -= len;
+		i++;
+	}
+
+	BUG_ON(i != *num_file_extents);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_extent_to_file);