staging/lustre: Get rid of cl_env hash table

cl_env hash table is under heavy contention when there are lots of
processes doing IO at the same time;
reduce lock contention by replacing cl_env cache with percpu array;
remove cl_env_nested_get() and cl_env_nested_put();
remove cl_env_reenter() and cl_env_reexit();

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/20254
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4257
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Bobi Jam <bobijam@hotmail.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

6 files changed, 48 insertions, 70 deletions

diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index 0ae78c7..c1c7551 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -1584,11 +1584,11 @@ restart:
  */
 int ll_hsm_release(struct inode *inode)
 {
-	struct cl_env_nest nest;
 	struct lu_env *env;
 	struct obd_client_handle *och = NULL;
 	__u64 data_version = 0;
 	int rc;
+	int refcheck;
 
 	CDEBUG(D_INODE, "%s: Releasing file "DFID".\n",
 	       ll_get_fsname(inode->i_sb, NULL, 0),
@@ -1605,14 +1605,14 @@ int ll_hsm_release(struct inode *inode)
 	if (rc != 0)
 		goto out;
 
-	env = cl_env_nested_get(&nest);
+	env = cl_env_get(&refcheck);
 	if (IS_ERR(env)) {
 		rc = PTR_ERR(env);
 		goto out;
 	}
 
 	ll_merge_attr(env, inode);
-	cl_env_nested_put(&nest, env);
+	cl_env_put(env, &refcheck);
 
 	/* Release the file.
 	 * NB: lease lock handle is released in mdc_hsm_release_pack() because
@@ -2268,17 +2268,17 @@ static int ll_flush(struct file *file, fl_owner_t id)
 int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end,
 		       enum cl_fsync_mode mode, int ignore_layout)
 {
-	struct cl_env_nest nest;
 	struct lu_env *env;
 	struct cl_io *io;
 	struct cl_fsync_io *fio;
 	int result;
+	int refcheck;
 
 	if (mode != CL_FSYNC_NONE && mode != CL_FSYNC_LOCAL &&
 	    mode != CL_FSYNC_DISCARD && mode != CL_FSYNC_ALL)
 		return -EINVAL;
 
-	env = cl_env_nested_get(&nest);
+	env = cl_env_get(&refcheck);
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
@@ -2301,7 +2301,7 @@ int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end,
 	if (result == 0)
 		result = fio->fi_nr_written;
 	cl_io_fini(env, io);
-	cl_env_nested_put(&nest, env);
+	cl_env_put(env, &refcheck);
 
 	return result;
 }
@@ -3149,14 +3149,14 @@ int ll_layout_conf(struct inode *inode, const struct cl_object_conf *conf)
 {
 	struct ll_inode_info *lli = ll_i2info(inode);
 	struct cl_object *obj = lli->lli_clob;
-	struct cl_env_nest nest;
 	struct lu_env *env;
 	int rc;
+	int refcheck;
 
 	if (!obj)
 		return 0;
 
-	env = cl_env_nested_get(&nest);
+	env = cl_env_get(&refcheck);
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
@@ -3190,7 +3190,7 @@ int ll_layout_conf(struct inode *inode, const struct cl_object_conf *conf)
 		ll_layout_version_set(lli, cl.cl_layout_gen);
 	}
 out:
-	cl_env_nested_put(&nest, env);
+	cl_env_put(env, &refcheck);
 	return rc;
 }
 
diff --git a/drivers/staging/lustre/lustre/llite/lcommon_cl.c b/drivers/staging/lustre/lustre/llite/lcommon_cl.c
index 56e414b..dd1cfd8 100644
--- a/drivers/staging/lustre/lustre/llite/lcommon_cl.c
+++ b/drivers/staging/lustre/lustre/llite/lcommon_cl.c
@@ -246,15 +246,11 @@ void cl_inode_fini(struct inode *inode)
 	int emergency;
 
 	if (clob) {
-		void		    *cookie;
-
-		cookie = cl_env_reenter();
 		env = cl_env_get(&refcheck);
 		emergency = IS_ERR(env);
 		if (emergency) {
 			mutex_lock(&cl_inode_fini_guard);
 			LASSERT(cl_inode_fini_env);
-			cl_env_implant(cl_inode_fini_env, &refcheck);
 			env = cl_inode_fini_env;
 		}
 		/*
@@ -266,13 +262,10 @@ void cl_inode_fini(struct inode *inode)
 		lu_object_ref_del(&clob->co_lu, "inode", inode);
 		cl_object_put_last(env, clob);
 		lli->lli_clob = NULL;
-		if (emergency) {
-			cl_env_unplant(cl_inode_fini_env, &refcheck);
+		if (emergency)
 			mutex_unlock(&cl_inode_fini_guard);
-		} else {
+		else
 			cl_env_put(env, &refcheck);
-		}
-		cl_env_reexit(cookie);
 	}
 }
 
diff --git a/drivers/staging/lustre/lustre/llite/lcommon_misc.c b/drivers/staging/lustre/lustre/llite/lcommon_misc.c
index 1558b55..f48660e 100644
--- a/drivers/staging/lustre/lustre/llite/lcommon_misc.c
+++ b/drivers/staging/lustre/lustre/llite/lcommon_misc.c
@@ -162,13 +162,11 @@ int cl_get_grouplock(struct cl_object *obj, unsigned long gid, int nonblock,
 		return rc;
 	}
 
-	cg->lg_env  = cl_env_get(&refcheck);
+	cg->lg_env  = env;
 	cg->lg_io   = io;
 	cg->lg_lock = lock;
 	cg->lg_gid  = gid;
-	LASSERT(cg->lg_env == env);
 
-	cl_env_unplant(env, &refcheck);
 	return 0;
 }
 
@@ -177,14 +175,10 @@ void cl_put_grouplock(struct ll_grouplock *cg)
 	struct lu_env  *env  = cg->lg_env;
 	struct cl_io   *io   = cg->lg_io;
 	struct cl_lock *lock = cg->lg_lock;
-	int	     refcheck;
 
 	LASSERT(cg->lg_env);
 	LASSERT(cg->lg_gid);
 
-	cl_env_implant(env, &refcheck);
-	cl_env_put(env, &refcheck);
-
 	cl_lock_release(env, lock);
 	cl_io_fini(env, io);
 	cl_env_put(env, NULL);
diff --git a/drivers/staging/lustre/lustre/llite/llite_mmap.c b/drivers/staging/lustre/lustre/llite/llite_mmap.c
index 4366918..ad2a699 100644
--- a/drivers/staging/lustre/lustre/llite/llite_mmap.c
+++ b/drivers/staging/lustre/lustre/llite/llite_mmap.c
@@ -80,43 +80,24 @@ struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr,
  * API independent part for page fault initialization.
  * \param vma - virtual memory area addressed to page fault
  * \param env - corespondent lu_env to processing
- * \param nest - nested level
  * \param index - page index corespondent to fault.
  * \parm ra_flags - vma readahead flags.
  *
- * \return allocated and initialized env for fault operation.
- * \retval EINVAL if env can't allocated
- * \return other error codes from cl_io_init.
+ * \return error codes from cl_io_init.
  */
 static struct cl_io *
-ll_fault_io_init(struct vm_area_struct *vma, struct lu_env **env_ret,
-		 struct cl_env_nest *nest, pgoff_t index,
-		 unsigned long *ra_flags)
+ll_fault_io_init(struct lu_env *env, struct vm_area_struct *vma,
+		 pgoff_t index, unsigned long *ra_flags)
 {
 	struct file	       *file = vma->vm_file;
 	struct inode	       *inode = file_inode(file);
 	struct cl_io	       *io;
 	struct cl_fault_io     *fio;
-	struct lu_env	       *env;
 	int			rc;
 
-	*env_ret = NULL;
 	if (ll_file_nolock(file))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	/*
-	 * page fault can be called when lustre IO is
-	 * already active for the current thread, e.g., when doing read/write
-	 * against user level buffer mapped from Lustre buffer. To avoid
-	 * stomping on existing context, optionally force an allocation of a new
-	 * one.
-	 */
-	env = cl_env_nested_get(nest);
-	if (IS_ERR(env))
-		return ERR_PTR(-EINVAL);
-
-	*env_ret = env;
-
 restart:
 	io = vvp_env_thread_io(env);
 	io->ci_obj = ll_i2info(inode)->lli_clob;
@@ -155,7 +136,6 @@ restart:
 		if (io->ci_need_restart)
 			goto restart;
 
-		cl_env_nested_put(nest, env);
 		io = ERR_PTR(rc);
 	}
 
@@ -169,13 +149,17 @@ static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
 	struct lu_env	   *env;
 	struct cl_io	    *io;
 	struct vvp_io	   *vio;
-	struct cl_env_nest       nest;
 	int		      result;
+	int refcheck;
 	sigset_t	     set;
 	struct inode	     *inode;
 	struct ll_inode_info     *lli;
 
-	io = ll_fault_io_init(vma, &env,  &nest, vmpage->index, NULL);
+	env = cl_env_get(&refcheck);
+	if (IS_ERR(env))
+		return PTR_ERR(env);
+
+	io = ll_fault_io_init(env, vma, vmpage->index, NULL);
 	if (IS_ERR(io)) {
 		result = PTR_ERR(io);
 		goto out;
@@ -240,8 +224,8 @@ static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
 
 out_io:
 	cl_io_fini(env, io);
-	cl_env_nested_put(&nest, env);
 out:
+	cl_env_put(env, &refcheck);
 	CDEBUG(D_MMAP, "%s mkwrite with %d\n", current->comm, result);
 	LASSERT(ergo(result == 0, PageLocked(vmpage)));
 
@@ -285,13 +269,19 @@ static int ll_fault0(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct vvp_io	   *vio = NULL;
 	struct page	     *vmpage;
 	unsigned long	    ra_flags;
-	struct cl_env_nest       nest;
-	int		      result;
+	int		      result = 0;
 	int		      fault_ret = 0;
+	int refcheck;
 
-	io = ll_fault_io_init(vma, &env,  &nest, vmf->pgoff, &ra_flags);
-	if (IS_ERR(io))
-		return to_fault_error(PTR_ERR(io));
+	env = cl_env_get(&refcheck);
+	if (IS_ERR(env))
+		return PTR_ERR(env);
+
+	io = ll_fault_io_init(env, vma, vmf->pgoff, &ra_flags);
+	if (IS_ERR(io)) {
+		result = to_fault_error(PTR_ERR(io));
+		goto out;
+	}
 
 	result = io->ci_result;
 	if (result == 0) {
@@ -322,14 +312,15 @@ static int ll_fault0(struct vm_area_struct *vma, struct vm_fault *vmf)
 		}
 	}
 	cl_io_fini(env, io);
-	cl_env_nested_put(&nest, env);
 
 	vma->vm_flags |= ra_flags;
+
+out:
+	cl_env_put(env, &refcheck);
 	if (result != 0 && !(fault_ret & VM_FAULT_RETRY))
 		fault_ret |= to_fault_error(result);
 
-	CDEBUG(D_MMAP, "%s fault %d/%d\n",
-	       current->comm, fault_ret, result);
+	CDEBUG(D_MMAP, "%s fault %d/%d\n", current->comm, fault_ret, result);
 	return fault_ret;
 }
 
diff --git a/drivers/staging/lustre/lustre/llite/rw.c b/drivers/staging/lustre/lustre/llite/rw.c
index 80cb8e0..d2515a8 100644
--- a/drivers/staging/lustre/lustre/llite/rw.c
+++ b/drivers/staging/lustre/lustre/llite/rw.c
@@ -896,17 +896,17 @@ int ll_writepage(struct page *vmpage, struct writeback_control *wbc)
 	struct cl_io	   *io;
 	struct cl_page	 *page;
 	struct cl_object       *clob;
-	struct cl_env_nest      nest;
 	bool redirtied = false;
 	bool unlocked = false;
 	int result;
+	int refcheck;
 
 	LASSERT(PageLocked(vmpage));
 	LASSERT(!PageWriteback(vmpage));
 
 	LASSERT(ll_i2dtexp(inode));
 
-	env = cl_env_nested_get(&nest);
+	env = cl_env_get(&refcheck);
 	if (IS_ERR(env)) {
 		result = PTR_ERR(env);
 		goto out;
@@ -971,7 +971,7 @@ int ll_writepage(struct page *vmpage, struct writeback_control *wbc)
 		}
 	}
 
-	cl_env_nested_put(&nest, env);
+	cl_env_put(env, &refcheck);
 	goto out;
 
 out:
diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c
index 67010be..1a08a9d 100644
--- a/drivers/staging/lustre/lustre/llite/rw26.c
+++ b/drivers/staging/lustre/lustre/llite/rw26.c
@@ -103,7 +103,6 @@ static void ll_invalidatepage(struct page *vmpage, unsigned int offset,
 static int ll_releasepage(struct page *vmpage, gfp_t gfp_mask)
 {
 	struct lu_env     *env;
-	void			*cookie;
 	struct cl_object  *obj;
 	struct cl_page    *page;
 	struct address_space *mapping;
@@ -129,7 +128,6 @@ static int ll_releasepage(struct page *vmpage, gfp_t gfp_mask)
 	if (!page)
 		return 1;
 
-	cookie = cl_env_reenter();
 	env = cl_env_percpu_get();
 	LASSERT(!IS_ERR(env));
 
@@ -155,7 +153,6 @@ static int ll_releasepage(struct page *vmpage, gfp_t gfp_mask)
 	cl_page_put(env, page);
 
 	cl_env_percpu_put(env);
-	cl_env_reexit(cookie);
 	return result;
 }
 
@@ -340,7 +337,8 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io,
 		       PAGE_SIZE) & ~(DT_MAX_BRW_SIZE - 1))
 static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct lu_env *env;
+	struct ll_cl_context *lcc;
+	const struct lu_env *env;
 	struct cl_io *io;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -348,7 +346,6 @@ static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter)
 	ssize_t count = iov_iter_count(iter);
 	ssize_t tot_bytes = 0, result = 0;
 	long size = MAX_DIO_SIZE;
-	int refcheck;
 
 	/* FIXME: io smaller than PAGE_SIZE is broken on ia64 ??? */
 	if ((file_offset & ~PAGE_MASK) || (count & ~PAGE_MASK))
@@ -363,9 +360,13 @@ static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter)
 	if (iov_iter_alignment(iter) & ~PAGE_MASK)
 		return -EINVAL;
 
-	env = cl_env_get(&refcheck);
+	lcc = ll_cl_find(file);
+	if (!lcc)
+		return -EIO;
+
+	env = lcc->lcc_env;
 	LASSERT(!IS_ERR(env));
-	io = vvp_env_io(env)->vui_cl.cis_io;
+	io = lcc->lcc_io;
 	LASSERT(io);
 
 	while (iov_iter_count(iter)) {
@@ -422,7 +423,6 @@ out:
 		vio->u.write.vui_written += tot_bytes;
 	}
 
-	cl_env_put(env, &refcheck);
 	return tot_bytes ? tot_bytes : result;
 }