X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fosc%2Fosc_io.c;h=03b4cf8af22f8521a86866f168cc06cfc53ca7ab;hp=1ab41d875f50913e79e94adafb943436e8ffd84d;hb=6bce536725efd166d2772f13fe954f271f9c53b8;hpb=db59ecb5d1d0284fb918def6348a11e0966d7767

diff --git a/lustre/osc/osc_io.c b/lustre/osc/osc_io.c
index 1ab41d8..03b4cf8 100644
--- a/lustre/osc/osc_io.c
+++ b/lustre/osc/osc_io.c
@@ -23,7 +23,7 @@
  * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
  * Use is subject to license terms.
  *
- * Copyright (c) 2011, 2016, Intel Corporation.
+ * Copyright (c) 2011, 2017, Intel Corporation.
  */
 /*
  * This file is part of Lustre, http://www.lustre.org/
@@ -38,29 +38,17 @@
 #define DEBUG_SUBSYSTEM S_OSC
 
 #include <lustre_obdo.h>
+#include <lustre_osc.h>
+#include <linux/pagevec.h>
 
-#include "osc_cl_internal.h"
+#include "osc_internal.h"
 
-/** \addtogroup osc 
- *  @{ 
+/** \addtogroup osc
+ *  @{
  */
 
 /*****************************************************************************
  *
- * Type conversions.
- *
- */
-
-static struct osc_io *cl2osc_io(const struct lu_env *env,
-                                const struct cl_io_slice *slice)
-{
-        struct osc_io *oio = container_of0(slice, struct osc_io, oi_cl);
-        LINVRNT(oio == osc_env_io(env));
-        return oio;
-}
-
-/*****************************************************************************
- *
  * io operations.
  *
  */
@@ -69,8 +57,7 @@ static void osc_io_fini(const struct lu_env *env, const struct cl_io_slice *io)
 {
 }
 
-static void osc_read_ahead_release(const struct lu_env *env,
-				   void *cbdata)
+void osc_read_ahead_release(const struct lu_env *env, void *cbdata)
 {
 	struct ldlm_lock *dlmlock = cbdata;
 	struct lustre_handle lockh;
@@ -79,6 +66,7 @@ static void osc_read_ahead_release(const struct lu_env *env,
 	ldlm_lock_decref(&lockh, LCK_PR);
 	LDLM_LOCK_PUT(dlmlock);
 }
+EXPORT_SYMBOL(osc_read_ahead_release);
 
 static int osc_io_read_ahead(const struct lu_env *env,
 			     const struct cl_io_slice *ios,
@@ -99,11 +87,13 @@ static int osc_io_read_ahead(const struct lu_env *env,
 			ldlm_lock_decref(&lockh, dlmlock->l_req_mode);
 		}
 
-		ra->cra_rpc_size = osc_cli(osc)->cl_max_pages_per_rpc;
-		ra->cra_end = cl_index(osc2cl(osc),
-				       dlmlock->l_policy_data.l_extent.end);
+		ra->cra_rpc_pages = osc_cli(osc)->cl_max_pages_per_rpc;
+		ra->cra_end_idx = cl_index(osc2cl(osc),
+					   dlmlock->l_policy_data.l_extent.end);
 		ra->cra_release = osc_read_ahead_release;
 		ra->cra_cbdata = dlmlock;
+		if (ra->cra_end_idx != CL_PAGE_EOF)
+			ra->cra_contention = true;
 		result = 0;
 	}
 
@@ -117,9 +107,8 @@ static int osc_io_read_ahead(const struct lu_env *env,
  * or, if page is already submitted, changes osc flags through
  * osc_set_async_flags().
  */
-static int osc_io_submit(const struct lu_env *env,
-                         const struct cl_io_slice *ios,
-			 enum cl_req_type crt, struct cl_2queue *queue)
+int osc_io_submit(const struct lu_env *env, const struct cl_io_slice *ios,
+		  enum cl_req_type crt, struct cl_2queue *queue)
 {
 	struct cl_page	  *page;
 	struct cl_page	  *tmp;
@@ -127,15 +116,17 @@ static int osc_io_submit(const struct lu_env *env,
 	struct osc_object *osc  = NULL;	/* to keep gcc happy */
 	struct osc_page	  *opg;
 	struct cl_io	  *io;
-	struct list_head  list = LIST_HEAD_INIT(list);
+	LIST_HEAD(list);
 
 	struct cl_page_list *qin      = &queue->c2_qin;
 	struct cl_page_list *qout     = &queue->c2_qout;
 	unsigned int queued = 0;
 	int result = 0;
-	int cmd;
 	int brw_flags;
 	unsigned int max_pages;
+	unsigned int ppc_bits; /* pages per chunk bits */
+	unsigned int ppc;
+	bool sync_queue = false;
 
 	LASSERT(qin->pl_nr > 0);
 
@@ -144,9 +135,17 @@ static int osc_io_submit(const struct lu_env *env,
 	osc = cl2osc(ios->cis_obj);
 	cli = osc_cli(osc);
 	max_pages = cli->cl_max_pages_per_rpc;
+	ppc_bits = cli->cl_chunkbits - PAGE_SHIFT;
+	ppc = 1 << ppc_bits;
 
-	cmd = crt == CRT_WRITE ? OBD_BRW_WRITE : OBD_BRW_READ;
 	brw_flags = osc_io_srvlock(cl2osc_io(env, ios)) ? OBD_BRW_SRVLOCK : 0;
+	brw_flags |= crt == CRT_WRITE ? OBD_BRW_WRITE : OBD_BRW_READ;
+	if (crt == CRT_READ && ios->cis_io->ci_ndelay)
+		brw_flags |= OBD_BRW_NDELAY;
+
+	page = cl_page_list_first(qin);
+	if (page->cp_type == CPT_TRANSIENT)
+		brw_flags |= OBD_BRW_NOCACHE;
 
         /*
          * NOTE: here @page is a top-level page. This is done to avoid
@@ -198,25 +197,43 @@ static int osc_io_submit(const struct lu_env *env,
 		else /* async IO */
 			cl_page_list_del(env, qin, page);
 
-		if (++queued == max_pages) {
-			queued = 0;
-			result = osc_queue_sync_pages(env, osc, &list, cmd,
+		queued++;
+		if (queued == max_pages) {
+			sync_queue = true;
+		} else if (crt == CRT_WRITE) {
+			unsigned int chunks;
+			unsigned int next_chunks;
+
+			chunks = (queued + ppc - 1) >> ppc_bits;
+			/* chunk number if add another page */
+			next_chunks = (queued + ppc) >> ppc_bits;
+
+			/* next page will excceed write chunk limit */
+			if (chunks == osc_max_write_chunks(cli) &&
+			    next_chunks > chunks)
+				sync_queue = true;
+		}
+
+		if (sync_queue) {
+			result = osc_queue_sync_pages(env, io, osc, &list,
 						      brw_flags);
 			if (result < 0)
 				break;
+			queued = 0;
+			sync_queue = false;
 		}
 	}
 
 	if (queued > 0)
-		result = osc_queue_sync_pages(env, osc, &list, cmd, brw_flags);
+		result = osc_queue_sync_pages(env, io, osc, &list, brw_flags);
 
 	/* Update c/mtime for sync write. LU-7310 */
-	if (qout->pl_nr > 0 && result == 0) {
+	if (crt == CRT_WRITE && qout->pl_nr > 0 && result == 0) {
 		struct cl_object *obj   = ios->cis_obj;
 		struct cl_attr *attr = &osc_env_info(env)->oti_attr;
 
 		cl_object_attr_lock(obj);
-		attr->cat_mtime = attr->cat_ctime = LTIME_S(CURRENT_TIME);
+		attr->cat_mtime = attr->cat_ctime = ktime_get_real_seconds();
 		cl_object_attr_update(env, obj, attr, CAT_MTIME | CAT_CTIME);
 		cl_object_attr_unlock(obj);
 	}
@@ -224,38 +241,33 @@ static int osc_io_submit(const struct lu_env *env,
 	CDEBUG(D_INFO, "%d/%d %d\n", qin->pl_nr, qout->pl_nr, result);
 	return qout->pl_nr > 0 ? 0 : result;
 }
+EXPORT_SYMBOL(osc_io_submit);
 
 /**
- * This is called when a page is accessed within file in a way that creates
- * new page, if one were missing (i.e., if there were a hole at that place in
- * the file, or accessed page is beyond the current file size).
+ * This is called to update the attributes when modifying a specific page,
+ * both when making new pages and when doing updates to existing cached pages.
  *
  * Expand stripe KMS if necessary.
  */
-static void osc_page_touch_at(const struct lu_env *env,
-			      struct cl_object *obj, pgoff_t idx, size_t to)
+void osc_page_touch_at(const struct lu_env *env, struct cl_object *obj,
+		       pgoff_t idx, size_t to)
 {
-        struct lov_oinfo  *loi  = cl2osc(obj)->oo_oinfo;
-        struct cl_attr    *attr = &osc_env_info(env)->oti_attr;
-        int valid;
-        __u64 kms;
+	struct lov_oinfo  *loi  = cl2osc(obj)->oo_oinfo;
+	struct cl_attr    *attr = &osc_env_info(env)->oti_attr;
+	int valid;
+	__u64 kms;
 
-        /* offset within stripe */
-        kms = cl_offset(obj, idx) + to;
+	ENTRY;
 
-        cl_object_attr_lock(obj);
-        /*
-         * XXX old code used
-         *
-         *         ll_inode_size_lock(inode, 0); lov_stripe_lock(lsm);
-         *
-         * here
-         */
+	/* offset within stripe */
+	kms = cl_offset(obj, idx) + to;
+
+	cl_object_attr_lock(obj);
 	CDEBUG(D_INODE, "stripe KMS %sincreasing %llu->%llu %llu\n",
-               kms > loi->loi_kms ? "" : "not ", loi->loi_kms, kms,
-               loi->loi_lvb.lvb_size);
+	       kms > loi->loi_kms ? "" : "not ", loi->loi_kms, kms,
+	       loi->loi_lvb.lvb_size);
 
-	attr->cat_mtime = attr->cat_ctime = LTIME_S(CURRENT_TIME);
+	attr->cat_mtime = attr->cat_ctime = ktime_get_real_seconds();
 	valid = CAT_MTIME | CAT_CTIME;
 	if (kms > loi->loi_kms) {
 		attr->cat_kms = kms;
@@ -267,12 +279,14 @@ static void osc_page_touch_at(const struct lu_env *env,
 	}
 	cl_object_attr_update(env, obj, attr, valid);
 	cl_object_attr_unlock(obj);
+
+	EXIT;
 }
 
-static int osc_io_commit_async(const struct lu_env *env,
-				const struct cl_io_slice *ios,
-				struct cl_page_list *qin, int from, int to,
-				cl_commit_cbt cb)
+int osc_io_commit_async(const struct lu_env *env,
+			const struct cl_io_slice *ios,
+			struct cl_page_list *qin, int from, int to,
+			cl_commit_cbt cb)
 {
 	struct cl_io    *io = ios->cis_io;
 	struct osc_io   *oio = cl2osc_io(env, ios);
@@ -280,6 +294,7 @@ static int osc_io_commit_async(const struct lu_env *env,
 	struct cl_page  *page;
 	struct cl_page  *last_page;
 	struct osc_page *opg;
+	struct pagevec  *pvec = &osc_env_info(env)->oti_pagevec;
 	int result = 0;
 	ENTRY;
 
@@ -299,6 +314,8 @@ static int osc_io_commit_async(const struct lu_env *env,
 		}
 	}
 
+	ll_pagevec_init(pvec, 0);
+
 	while (qin->pl_nr > 0) {
 		struct osc_async_page *oap;
 
@@ -306,6 +323,9 @@ static int osc_io_commit_async(const struct lu_env *env,
 		opg = osc_cl_page_osc(page, osc);
 		oap = &opg->ops_oap;
 
+		LASSERTF(osc == oap->oap_obj,
+			 "obj mismatch: %p / %p\n", osc, oap->oap_obj);
+
 		if (!list_empty(&oap->oap_rpc_item)) {
 			CDEBUG(D_CACHE, "Busy oap %p page %p for submit.\n",
 			       oap, opg);
@@ -315,7 +335,7 @@ static int osc_io_commit_async(const struct lu_env *env,
 
 		/* The page may be already in dirty cache. */
 		if (list_empty(&oap->oap_pending_item)) {
-			result = osc_page_cache_add(env, &opg->ops_cl, io);
+			result = osc_page_cache_add(env, opg, io, cb);
 			if (result != 0)
 				break;
 		}
@@ -325,11 +345,20 @@ static int osc_io_commit_async(const struct lu_env *env,
 
 		cl_page_list_del(env, qin, page);
 
-		(*cb)(env, io, page);
-		/* Can't access page any more. Page can be in transfer and
-		 * complete at any time. */
+		/* if there are no more slots, do the callback & reinit */
+		if (pagevec_add(pvec, page->cp_vmpage) == 0) {
+			(*cb)(env, io, pvec);
+			pagevec_reinit(pvec);
+		}
 	}
 
+	/* Clean up any partially full pagevecs */
+	if (pagevec_count(pvec) != 0)
+		(*cb)(env, io, pvec);
+
+	/* Can't access these pages any more. Page can be in transfer and
+	 * complete at any time. */
+
 	/* for sync write, kernel will wait for this page to be flushed before
 	 * osc_io_end() is called, so release it earlier.
 	 * for mkwrite(), it's known there is no further pages. */
@@ -341,29 +370,47 @@ static int osc_io_commit_async(const struct lu_env *env,
 	CDEBUG(D_INFO, "%d %d\n", qin->pl_nr, result);
 	RETURN(result);
 }
+EXPORT_SYMBOL(osc_io_commit_async);
 
-static int osc_io_iter_init(const struct lu_env *env,
-			    const struct cl_io_slice *ios)
+static bool osc_import_not_healthy(struct obd_import *imp)
+{
+	return imp->imp_invalid || imp->imp_deactive ||
+	       !(imp->imp_state == LUSTRE_IMP_FULL ||
+		 imp->imp_state == LUSTRE_IMP_IDLE);
+}
+
+int osc_io_iter_init(const struct lu_env *env, const struct cl_io_slice *ios)
 {
 	struct osc_object *osc = cl2osc(ios->cis_obj);
 	struct obd_import *imp = osc_cli(osc)->cl_import;
+	struct osc_io *oio = osc_env_io(env);
 	int rc = -EIO;
+	ENTRY;
 
 	spin_lock(&imp->imp_lock);
-	if (likely(!imp->imp_invalid)) {
-		struct osc_io *oio = osc_env_io(env);
-
+	/**
+	 * check whether this OSC device is available for non-delay read,
+	 * fast switching mirror if we haven't tried all mirrors.
+	 */
+	if (ios->cis_io->ci_type == CIT_READ && ios->cis_io->ci_ndelay &&
+	    !ios->cis_io->ci_tried_all_mirrors && osc_import_not_healthy(imp)) {
+		rc = -EWOULDBLOCK;
+	} else if (likely(!imp->imp_invalid)) {
 		atomic_inc(&osc->oo_nr_ios);
 		oio->oi_is_active = 1;
 		rc = 0;
 	}
 	spin_unlock(&imp->imp_lock);
 
-	return rc;
+	if (cfs_capable(CFS_CAP_SYS_RESOURCE))
+		oio->oi_cap_sys_resource = 1;
+
+	RETURN(rc);
 }
+EXPORT_SYMBOL(osc_io_iter_init);
 
-static int osc_io_write_iter_init(const struct lu_env *env,
-				  const struct cl_io_slice *ios)
+int osc_io_rw_iter_init(const struct lu_env *env,
+			const struct cl_io_slice *ios)
 {
 	struct cl_io *io = ios->cis_io;
 	struct osc_io *oio = osc_env_io(env);
@@ -374,17 +421,18 @@ static int osc_io_write_iter_init(const struct lu_env *env,
 	if (cl_io_is_append(io))
 		RETURN(osc_io_iter_init(env, ios));
 
-	npages = io->u.ci_rw.rw_range.cir_count >> PAGE_SHIFT;
-	if (io->u.ci_rw.rw_range.cir_pos & ~PAGE_MASK)
+	npages = io->u.ci_rw.crw_count >> PAGE_SHIFT;
+	if (io->u.ci_rw.crw_pos & ~PAGE_MASK)
 		++npages;
 
 	oio->oi_lru_reserved = osc_lru_reserve(osc_cli(osc), npages);
 
 	RETURN(osc_io_iter_init(env, ios));
 }
+EXPORT_SYMBOL(osc_io_rw_iter_init);
 
-static void osc_io_iter_fini(const struct lu_env *env,
-			     const struct cl_io_slice *ios)
+void osc_io_iter_fini(const struct lu_env *env,
+		      const struct cl_io_slice *ios)
 {
 	struct osc_io *oio = osc_env_io(env);
 
@@ -397,9 +445,10 @@ static void osc_io_iter_fini(const struct lu_env *env,
 			wake_up_all(&osc->oo_io_waitq);
 	}
 }
+EXPORT_SYMBOL(osc_io_iter_fini);
 
-static void osc_io_write_iter_fini(const struct lu_env *env,
-				   const struct cl_io_slice *ios)
+void osc_io_rw_iter_fini(const struct lu_env *env,
+			 const struct cl_io_slice *ios)
 {
 	struct osc_io *oio = osc_env_io(env);
 	struct osc_object *osc = cl2osc(ios->cis_obj);
@@ -412,9 +461,9 @@ static void osc_io_write_iter_fini(const struct lu_env *env,
 
 	osc_io_iter_fini(env, ios);
 }
+EXPORT_SYMBOL(osc_io_rw_iter_fini);
 
-static int osc_io_fault_start(const struct lu_env *env,
-			      const struct cl_io_slice *ios)
+int osc_io_fault_start(const struct lu_env *env, const struct cl_io_slice *ios)
 {
 	struct cl_io       *io;
 	struct cl_fault_io *fio;
@@ -434,6 +483,8 @@ static int osc_io_fault_start(const struct lu_env *env,
 				  fio->ft_index, fio->ft_nob);
 	RETURN(0);
 }
+EXPORT_SYMBOL(osc_io_fault_start);
+
 
 static int osc_async_upcall(void *a, int rc)
 {
@@ -497,10 +548,11 @@ static int osc_io_setattr_start(const struct lu_env *env,
         struct obdo             *oa     = &oio->oi_oa;
 	struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
 	__u64                    size   = io->u.ci_setattr.sa_attr.lvb_size;
-	unsigned int             ia_valid = io->u.ci_setattr.sa_valid;
-	int                      result = 0;
-	ENTRY;
+	unsigned int ia_avalid = io->u.ci_setattr.sa_avalid;
+	enum op_xvalid ia_xvalid = io->u.ci_setattr.sa_xvalid;
+	int result = 0;
 
+	ENTRY;
 	/* truncate cache dirty pages first */
 	if (cl_io_is_trunc(io))
 		result = osc_cache_truncate_start(env, cl2osc(obj), size,
@@ -513,19 +565,20 @@ static int osc_io_setattr_start(const struct lu_env *env,
 			struct ost_lvb *lvb = &io->u.ci_setattr.sa_attr;
 			unsigned int cl_valid = 0;
 
-			if (ia_valid & ATTR_SIZE) {
-				attr->cat_size = attr->cat_kms = size;
+			if (ia_avalid & ATTR_SIZE) {
+				attr->cat_size = size;
+				attr->cat_kms = size;
 				cl_valid = (CAT_SIZE | CAT_KMS);
 			}
-			if (ia_valid & ATTR_MTIME_SET) {
+			if (ia_avalid & ATTR_MTIME_SET) {
 				attr->cat_mtime = lvb->lvb_mtime;
 				cl_valid |= CAT_MTIME;
 			}
-			if (ia_valid & ATTR_ATIME_SET) {
+			if (ia_avalid & ATTR_ATIME_SET) {
 				attr->cat_atime = lvb->lvb_atime;
 				cl_valid |= CAT_ATIME;
 			}
-			if (ia_valid & ATTR_CTIME_SET) {
+			if (ia_xvalid & OP_XVALID_CTIME_SET) {
 				attr->cat_ctime = lvb->lvb_ctime;
 				cl_valid |= CAT_CTIME;
 			}
@@ -542,42 +595,47 @@ static int osc_io_setattr_start(const struct lu_env *env,
 		oa->o_layout = io->u.ci_setattr.sa_layout;
 		oa->o_valid |= OBD_MD_FLID | OBD_MD_FLGROUP |
 			OBD_MD_FLOSTLAYOUT;
-		if (ia_valid & ATTR_CTIME) {
+		if (ia_avalid & ATTR_CTIME) {
 			oa->o_valid |= OBD_MD_FLCTIME;
 			oa->o_ctime = attr->cat_ctime;
 		}
-		if (ia_valid & ATTR_ATIME) {
+		if (ia_avalid & ATTR_ATIME) {
 			oa->o_valid |= OBD_MD_FLATIME;
 			oa->o_atime = attr->cat_atime;
 		}
-		if (ia_valid & ATTR_MTIME) {
+		if (ia_avalid & ATTR_MTIME) {
 			oa->o_valid |= OBD_MD_FLMTIME;
 			oa->o_mtime = attr->cat_mtime;
 		}
-                if (ia_valid & ATTR_SIZE) {
-                        oa->o_size = size;
-                        oa->o_blocks = OBD_OBJECT_EOF;
-                        oa->o_valid |= OBD_MD_FLSIZE | OBD_MD_FLBLOCKS;
-
-                        if (oio->oi_lockless) {
-                                oa->o_flags = OBD_FL_SRVLOCK;
-                                oa->o_valid |= OBD_MD_FLFLAGS;
-                        }
-                } else {
-                        LASSERT(oio->oi_lockless == 0);
-                }
+		if (ia_avalid & ATTR_SIZE) {
+			oa->o_size = size;
+			oa->o_blocks = OBD_OBJECT_EOF;
+			oa->o_valid |= OBD_MD_FLSIZE | OBD_MD_FLBLOCKS;
+
+			if (oio->oi_lockless) {
+				oa->o_flags = OBD_FL_SRVLOCK;
+				oa->o_valid |= OBD_MD_FLFLAGS;
+			}
+
+			if (io->ci_layout_version > 0) {
+				/* verify layout version */
+				oa->o_valid |= OBD_MD_LAYOUT_VERSION;
+				oa->o_layout_version = io->ci_layout_version;
+			}
+		} else {
+			LASSERT(oio->oi_lockless == 0);
+		}
 
-		if (ia_valid & ATTR_ATTR_FLAG) {
+		if (ia_xvalid & OP_XVALID_FLAGS) {
 			oa->o_flags = io->u.ci_setattr.sa_attr_flags;
 			oa->o_valid |= OBD_MD_FLFLAGS;
 		}
 
 		init_completion(&cbargs->opc_sync);
 
-		if (ia_valid & ATTR_SIZE)
-			result = osc_punch_base(osc_export(cl2osc(obj)),
-						oa, osc_async_upcall,
-						cbargs, PTLRPCD_SET);
+		if (ia_avalid & ATTR_SIZE)
+			result = osc_punch_send(osc_export(cl2osc(obj)),
+						oa, osc_async_upcall, cbargs);
 		else
 			result = osc_setattr_async(osc_export(cl2osc(obj)),
 						   oa, osc_async_upcall,
@@ -589,37 +647,50 @@ static int osc_io_setattr_start(const struct lu_env *env,
 	RETURN(result);
 }
 
-static void osc_io_setattr_end(const struct lu_env *env,
-                               const struct cl_io_slice *slice)
+void osc_io_setattr_end(const struct lu_env *env,
+			const struct cl_io_slice *slice)
 {
 	struct cl_io     *io  = slice->cis_io;
 	struct osc_io    *oio = cl2osc_io(env, slice);
 	struct cl_object *obj = slice->cis_obj;
 	struct osc_async_cbargs *cbargs = &oio->oi_cbarg;
-        int result = 0;
+	struct cl_attr  *attr = &osc_env_info(env)->oti_attr;
+	struct obdo *oa = &oio->oi_oa;
+	unsigned int cl_valid = 0;
+	int result = 0;
 
 	if (cbargs->opc_rpc_sent) {
 		wait_for_completion(&cbargs->opc_sync);
 		result = io->ci_result = cbargs->opc_rc;
 	}
-        if (result == 0) {
-                if (oio->oi_lockless) {
-                        /* lockless truncate */
-                        struct osc_device *osd = lu2osc_dev(obj->co_lu.lo_dev);
-
-                        LASSERT(cl_io_is_trunc(io));
-                        /* XXX: Need a lock. */
-                        osd->od_stats.os_lockless_truncates++;
-                }
-        }
+
+	if (result == 0) {
+		if (oio->oi_lockless) {
+			/* lockless truncate */
+			struct osc_device *osd = lu2osc_dev(obj->co_lu.lo_dev);
+
+			LASSERT(cl_io_is_trunc(io));
+			/* XXX: Need a lock. */
+			osd->od_stats.os_lockless_truncates++;
+		}
+	}
 
 	if (cl_io_is_trunc(io)) {
 		__u64 size = io->u.ci_setattr.sa_attr.lvb_size;
+		cl_object_attr_lock(obj);
+		if (oa->o_valid & OBD_MD_FLBLOCKS) {
+			attr->cat_blocks = oa->o_blocks;
+			cl_valid |= CAT_BLOCKS;
+		}
+
+		cl_object_attr_update(env, obj, attr, cl_valid);
+		cl_object_attr_unlock(obj);
 		osc_trunc_check(env, io, oio, size);
 		osc_cache_truncate_end(env, oio->oi_trunc);
 		oio->oi_trunc = NULL;
 	}
 }
+EXPORT_SYMBOL(osc_io_setattr_end);
 
 struct osc_data_version_args {
 	struct osc_io *dva_oio;
@@ -627,9 +698,9 @@ struct osc_data_version_args {
 
 static int
 osc_data_version_interpret(const struct lu_env *env, struct ptlrpc_request *req,
-			   void *arg, int rc)
+			   void *args, int rc)
 {
-	struct osc_data_version_args *dva = arg;
+	struct osc_data_version_args *dva = args;
 	struct osc_io *oio = dva->dva_oio;
 	const struct ost_body *body;
 
@@ -695,8 +766,7 @@ static int osc_io_data_version_start(const struct lu_env *env,
 
 	ptlrpc_request_set_replen(req);
 	req->rq_interpret_reply = osc_data_version_interpret;
-	CLASSERT(sizeof(*dva) <= sizeof(req->rq_async_args));
-	dva = ptlrpc_req_async_args(req);
+	dva = ptlrpc_req_async_args(dva, req);
 	dva->dva_oio = oio;
 
 	ptlrpcd_add_req(req);
@@ -716,18 +786,23 @@ static void osc_io_data_version_end(const struct lu_env *env,
 
 	if (cbargs->opc_rc != 0) {
 		slice->cis_io->ci_result = cbargs->opc_rc;
-	} else if (!(oio->oi_oa.o_valid & OBD_MD_FLDATAVERSION)) {
-		slice->cis_io->ci_result = -EOPNOTSUPP;
 	} else {
-		dv->dv_data_version = oio->oi_oa.o_data_version;
 		slice->cis_io->ci_result = 0;
+		if (!(oio->oi_oa.o_valid &
+		      (OBD_MD_LAYOUT_VERSION | OBD_MD_FLDATAVERSION)))
+			slice->cis_io->ci_result = -ENOTSUPP;
+
+		if (oio->oi_oa.o_valid & OBD_MD_LAYOUT_VERSION)
+			dv->dv_layout_version = oio->oi_oa.o_layout_version;
+		if (oio->oi_oa.o_valid & OBD_MD_FLDATAVERSION)
+			dv->dv_data_version = oio->oi_oa.o_data_version;
 	}
 
 	EXIT;
 }
 
-static int osc_io_read_start(const struct lu_env *env,
-                             const struct cl_io_slice *slice)
+int osc_io_read_start(const struct lu_env *env,
+		      const struct cl_io_slice *slice)
 {
 	struct cl_object *obj  = slice->cis_obj;
 	struct cl_attr	 *attr = &osc_env_info(env)->oti_attr;
@@ -743,9 +818,10 @@ static int osc_io_read_start(const struct lu_env *env,
 
 	RETURN(rc);
 }
+EXPORT_SYMBOL(osc_io_read_start);
 
-static int osc_io_write_start(const struct lu_env *env,
-                              const struct cl_io_slice *slice)
+int osc_io_write_start(const struct lu_env *env,
+		       const struct cl_io_slice *slice)
 {
 	struct cl_object *obj   = slice->cis_obj;
 	struct cl_attr   *attr  = &osc_env_info(env)->oti_attr;
@@ -760,9 +836,10 @@ static int osc_io_write_start(const struct lu_env *env,
 
 	RETURN(rc);
 }
+EXPORT_SYMBOL(osc_io_write_start);
 
-static int osc_fsync_ost(const struct lu_env *env, struct osc_object *obj,
-			 struct cl_fsync_io *fio)
+int osc_fsync_ost(const struct lu_env *env, struct osc_object *obj,
+		  struct cl_fsync_io *fio)
 {
 	struct osc_io    *oio   = osc_env_io(env);
 	struct obdo      *oa    = &oio->oi_oa;
@@ -787,9 +864,10 @@ static int osc_fsync_ost(const struct lu_env *env, struct osc_object *obj,
 	rc = osc_sync_base(obj, oa, osc_async_upcall, cbargs, PTLRPCD_SET);
 	RETURN(rc);
 }
+EXPORT_SYMBOL(osc_fsync_ost);
 
-static int osc_io_fsync_start(const struct lu_env *env,
-			      const struct cl_io_slice *slice)
+int osc_io_fsync_start(const struct lu_env *env,
+		       const struct cl_io_slice *slice)
 {
 	struct cl_io       *io  = slice->cis_io;
 	struct cl_fsync_io *fio = &io->u.ci_fsync;
@@ -828,8 +906,8 @@ static int osc_io_fsync_start(const struct lu_env *env,
 	RETURN(result);
 }
 
-static void osc_io_fsync_end(const struct lu_env *env,
-			     const struct cl_io_slice *slice)
+void osc_io_fsync_end(const struct lu_env *env,
+		      const struct cl_io_slice *slice)
 {
 	struct cl_fsync_io *fio = &slice->cis_io->u.ci_fsync;
 	struct cl_object   *obj = slice->cis_obj;
@@ -849,6 +927,7 @@ static void osc_io_fsync_end(const struct lu_env *env,
 	}
 	slice->cis_io->ci_result = result;
 }
+EXPORT_SYMBOL(osc_io_fsync_end);
 
 static int osc_io_ladvise_start(const struct lu_env *env,
 				const struct cl_io_slice *slice)
@@ -920,8 +999,7 @@ static void osc_io_ladvise_end(const struct lu_env *env,
 	slice->cis_io->ci_result = result;
 }
 
-static void osc_io_end(const struct lu_env *env,
-		       const struct cl_io_slice *slice)
+void osc_io_end(const struct lu_env *env, const struct cl_io_slice *slice)
 {
 	struct osc_io *oio = cl2osc_io(env, slice);
 
@@ -930,18 +1008,19 @@ static void osc_io_end(const struct lu_env *env,
 		oio->oi_active = NULL;
 	}
 }
+EXPORT_SYMBOL(osc_io_end);
 
 static const struct cl_io_operations osc_io_ops = {
 	.op = {
 		[CIT_READ] = {
-			.cio_iter_init = osc_io_iter_init,
-			.cio_iter_fini = osc_io_iter_fini,
+			.cio_iter_init = osc_io_rw_iter_init,
+			.cio_iter_fini = osc_io_rw_iter_fini,
 			.cio_start  = osc_io_read_start,
 			.cio_fini   = osc_io_fini
 		},
 		[CIT_WRITE] = {
-			.cio_iter_init = osc_io_write_iter_init,
-			.cio_iter_fini = osc_io_write_iter_fini,
+			.cio_iter_init = osc_io_rw_iter_init,
+			.cio_iter_fini = osc_io_rw_iter_fini,
 			.cio_start  = osc_io_write_start,
 			.cio_end    = osc_io_end,
 			.cio_fini   = osc_io_fini