public inbox for linux-nfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Mike Snitzer <snitzer@kernel.org>
To: linux-nfs@vger.kernel.org
Cc: Anna Schumaker <anna@kernel.org>,
	Trond Myklebust <trondmy@hammerspace.com>,
	Chuck Lever <chuck.lever@oracle.com>,
	Jeff Layton <jlayton@kernel.org>, NeilBrown <neilb@suse.de>
Subject: [for-6.13 PATCH 07/19] nfs/localio: add direct IO enablement with sync and async IO support
Date: Fri,  8 Nov 2024 18:39:50 -0500	[thread overview]
Message-ID: <20241108234002.16392-8-snitzer@kernel.org> (raw)
In-Reply-To: <20241108234002.16392-1-snitzer@kernel.org>

This commit simply adds the required O_DIRECT plumbing.  It doesn't
address the fact that NFS doesn't ensure all writes are page aligned
(nor device logical block size aligned as required by O_DIRECT).

Because NFS will read-modify-write for IO that isn't aligned, LOCALIO
will not use O_DIRECT semantics by default if/when an application
requests the use of O_DIRECT.  Allow the use of O_DIRECT semantics by:
1: Adding a flag to the nfs_pgio_header struct to allow the NFS
   O_DIRECT layer to signal that O_DIRECT was used by the application
2: Adding a 'localio_O_DIRECT_semantics' NFS module parameter that
   when enabled will cause LOCALIO to use O_DIRECT semantics (this may
   cause IO to fail if applications do not properly align their IO).

Adding Direct IO support helps side-step the problem that LOCALIO
currently double buffers buffered IO (by using page cache in both NFS
and the underlying filesystem).  More care is needed to craft a proper
solution for LOCALIO's redundant use of page cache for buffered IO,
e.g.: https://marc.info/?l=linux-nfs&m=171996211625151&w=2

This commit is derived from code developed by Weston Andros Adamson.

Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 fs/nfs/direct.c         |  1 +
 fs/nfs/localio.c        | 92 ++++++++++++++++++++++++++++++++++++-----
 include/linux/nfs_xdr.h |  1 +
 3 files changed, 84 insertions(+), 10 deletions(-)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 90079ca134dd..4b92493d6ff0 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -303,6 +303,7 @@ static void nfs_read_sync_pgio_error(struct list_head *head, int error)
 static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr)
 {
 	get_dreq(hdr->dreq);
+	set_bit(NFS_IOHDR_ODIRECT, &hdr->flags);
 }
 
 static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 4b8618cf114c..de0dcd76d84d 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -35,6 +35,7 @@ struct nfs_local_kiocb {
 	struct bio_vec		*bvec;
 	struct nfs_pgio_header	*hdr;
 	struct work_struct	work;
+	void (*aio_complete_work)(struct work_struct *);
 	struct nfsd_file	*localio;
 };
 
@@ -48,6 +49,10 @@ struct nfs_local_fsync_ctx {
 static bool localio_enabled __read_mostly = true;
 module_param(localio_enabled, bool, 0644);
 
+static bool localio_O_DIRECT_semantics __read_mostly = false;
+module_param(localio_O_DIRECT_semantics, bool, 0644);
+MODULE_PARM_DESC(localio_O_DIRECT_semantics, "Use O_DIRECT semantics");
+
 static inline bool nfs_client_is_local(const struct nfs_client *clp)
 {
 	return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
@@ -285,10 +290,19 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 		kfree(iocb);
 		return NULL;
 	}
-	init_sync_kiocb(&iocb->kiocb, file);
+
+	if (localio_O_DIRECT_semantics &&
+	    test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) {
+		iocb->kiocb.ki_filp = file;
+		iocb->kiocb.ki_flags = IOCB_DIRECT;
+	} else
+		init_sync_kiocb(&iocb->kiocb, file);
+
 	iocb->kiocb.ki_pos = hdr->args.offset;
 	iocb->hdr = hdr;
 	iocb->kiocb.ki_flags &= ~IOCB_APPEND;
+	iocb->aio_complete_work = NULL;
+
 	return iocb;
 }
 
@@ -343,6 +357,18 @@ nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
 	nfs_local_hdr_release(hdr, hdr->task.tk_ops);
 }
 
+/*
+ * Complete the I/O from iocb->kiocb.ki_complete()
+ *
+ * Note that this function can be called from a bottom half context,
+ * hence we need to queue the rpc_call_done() etc to a workqueue
+ */
+static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb)
+{
+	INIT_WORK(&iocb->work, iocb->aio_complete_work);
+	queue_work(nfsiod_workqueue, &iocb->work);
+}
+
 static void
 nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 {
@@ -365,6 +391,23 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 			status > 0 ? status : 0, hdr->res.eof);
 }
 
+static void nfs_local_read_aio_complete_work(struct work_struct *work)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(work, struct nfs_local_kiocb, work);
+
+	nfs_local_pgio_release(iocb);
+}
+
+static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(kiocb, struct nfs_local_kiocb, kiocb);
+
+	nfs_local_read_done(iocb, ret);
+	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */
+}
+
 static void nfs_local_call_read(struct work_struct *work)
 {
 	struct nfs_local_kiocb *iocb =
@@ -379,10 +422,10 @@ static void nfs_local_call_read(struct work_struct *work)
 	nfs_local_iter_init(&iter, iocb, READ);
 
 	status = filp->f_op->read_iter(&iocb->kiocb, &iter);
-	WARN_ON_ONCE(status == -EIOCBQUEUED);
-
-	nfs_local_read_done(iocb, status);
-	nfs_local_pgio_release(iocb);
+	if (status != -EIOCBQUEUED) {
+		nfs_local_read_done(iocb, status);
+		nfs_local_pgio_release(iocb);
+	}
 
 	revert_creds(save_cred);
 }
@@ -410,6 +453,11 @@ nfs_do_local_read(struct nfs_pgio_header *hdr,
 	nfs_local_pgio_init(hdr, call_ops);
 	hdr->res.eof = false;
 
+	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+		iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
+		iocb->aio_complete_work = nfs_local_read_aio_complete_work;
+	}
+
 	INIT_WORK(&iocb->work, nfs_local_call_read);
 	queue_work(nfslocaliod_workqueue, &iocb->work);
 
@@ -534,6 +582,24 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
 	nfs_local_pgio_done(hdr, status);
 }
 
+static void nfs_local_write_aio_complete_work(struct work_struct *work)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(work, struct nfs_local_kiocb, work);
+
+	nfs_local_vfs_getattr(iocb);
+	nfs_local_pgio_release(iocb);
+}
+
+static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(kiocb, struct nfs_local_kiocb, kiocb);
+
+	nfs_local_write_done(iocb, ret);
+	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */
+}
+
 static void nfs_local_call_write(struct work_struct *work)
 {
 	struct nfs_local_kiocb *iocb =
@@ -552,11 +618,11 @@ static void nfs_local_call_write(struct work_struct *work)
 	file_start_write(filp);
 	status = filp->f_op->write_iter(&iocb->kiocb, &iter);
 	file_end_write(filp);
-	WARN_ON_ONCE(status == -EIOCBQUEUED);
-
-	nfs_local_write_done(iocb, status);
-	nfs_local_vfs_getattr(iocb);
-	nfs_local_pgio_release(iocb);
+	if (status != -EIOCBQUEUED) {
+		nfs_local_write_done(iocb, status);
+		nfs_local_vfs_getattr(iocb);
+		nfs_local_pgio_release(iocb);
+	}
 
 	revert_creds(save_cred);
 	current->flags = old_flags;
@@ -592,10 +658,16 @@ nfs_do_local_write(struct nfs_pgio_header *hdr,
 	case NFS_FILE_SYNC:
 		iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
 	}
+
 	nfs_local_pgio_init(hdr, call_ops);
 
 	nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
 
+	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+		iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
+		iocb->aio_complete_work = nfs_local_write_aio_complete_work;
+	}
+
 	INIT_WORK(&iocb->work, nfs_local_call_write);
 	queue_work(nfslocaliod_workqueue, &iocb->work);
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index e0ae0a14257f..f30e94d105b7 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1632,6 +1632,7 @@ enum {
 	NFS_IOHDR_RESEND_PNFS,
 	NFS_IOHDR_RESEND_MDS,
 	NFS_IOHDR_UNSTABLE_WRITES,
+	NFS_IOHDR_ODIRECT,
 };
 
 struct nfs_io_completion;
-- 
2.44.0


  parent reply	other threads:[~2024-11-08 23:40 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-08 23:39 [for-6.13 PATCH 00/19] nfs/nfsd: fixes and improvements for LOCALIO Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 01/19] nfs/localio: must clear res.replen in nfs_local_read_done Mike Snitzer
2024-11-11  0:36   ` NeilBrown
2024-11-08 23:39 ` [for-6.13 PATCH 02/19] nfs_common: must not hold RCU while calling nfsd_file_put_local Mike Snitzer
2024-11-11  1:01   ` NeilBrown
2024-11-13 14:58   ` Jeff Layton
2024-11-13 16:51     ` Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 03/19] nfs/localio: remove redundant suid/sgid handling Mike Snitzer
2024-11-11  1:09   ` NeilBrown
2024-11-08 23:39 ` [for-6.13 PATCH 04/19] nfs/localio: eliminate unnecessary kref in nfs_local_fsync_ctx Mike Snitzer
2024-11-11  1:15   ` NeilBrown
2024-11-08 23:39 ` [for-6.13 PATCH 05/19] nfs/localio: remove extra indirect nfs_to call to check {read,write}_iter Mike Snitzer
2024-11-11  1:20   ` NeilBrown
2024-11-11 15:09     ` Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 06/19] nfs/localio: eliminate need for nfs_local_fsync_work forward declaration Mike Snitzer
2024-11-11  1:21   ` NeilBrown
2024-11-08 23:39 ` Mike Snitzer [this message]
2024-11-11  1:31   ` [for-6.13 PATCH 07/19] nfs/localio: add direct IO enablement with sync and async IO support NeilBrown
2024-11-12 14:31   ` Chuck Lever
2024-11-08 23:39 ` [for-6.13 PATCH 08/19] nfsd: add nfsd_file_{get,put} to 'nfs_to' nfsd_localio_operations Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 09/19] nfs_common: rename functions that invalidate LOCALIO nfs_clients Mike Snitzer
2024-11-11  1:32   ` NeilBrown
2024-11-08 23:39 ` [for-6.13 PATCH 10/19] nfs_common: move localio_lock to new lock member of nfs_uuid_t Mike Snitzer
2024-11-11  1:55   ` NeilBrown
2024-11-11 15:33     ` Mike Snitzer
2024-11-11 20:35       ` NeilBrown
2024-11-11 22:27         ` Mike Snitzer
2024-11-11 23:23           ` NeilBrown
2024-11-12  0:16             ` Mike Snitzer
2024-11-12  0:49               ` NeilBrown
2024-11-12 14:36                 ` Chuck Lever
2024-11-12 23:13                   ` NeilBrown
2024-11-13  0:07                     ` Chuck Lever III
2024-11-13  0:32                       ` NeilBrown
2024-11-08 23:39 ` [for-6.13 PATCH 11/19] nfs: cache all open LOCALIO nfsd_file(s) in client Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 12/19] nfsd: update percpu_ref to manage references on nfsd_net Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 13/19] nfsd: rename nfsd_serv_ prefixed methods and variables with nfsd_net_ Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 14/19] nfsd: nfsd_file_acquire_local no longer returns GC'd nfsd_file Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 15/19] nfs_common: rename nfslocalio nfs_uuid_lock to nfs_uuids_lock Mike Snitzer
2024-11-08 23:39 ` [for-6.13 PATCH 16/19] nfs_common: track all open nfsd_files per LOCALIO nfs_client Mike Snitzer
2024-11-08 23:40 ` [for-6.13 PATCH 17/19] nfs_common: add nfs_localio trace events Mike Snitzer
2024-11-08 23:40 ` [for-6.13 PATCH 18/19] nfs: probe for LOCALIO when v4 client reconnects to server Mike Snitzer
2024-11-08 23:40 ` [for-6.13 PATCH 19/19] nfs: probe for LOCALIO when v3 " Mike Snitzer
2024-11-11  3:06   ` NeilBrown
2024-11-10 15:49 ` [for-6.13 PATCH 00/19] nfs/nfsd: fixes and improvements for LOCALIO Chuck Lever III

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241108234002.16392-8-snitzer@kernel.org \
    --to=snitzer@kernel.org \
    --cc=anna@kernel.org \
    --cc=chuck.lever@oracle.com \
    --cc=jlayton@kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=neilb@suse.de \
    --cc=trondmy@hammerspace.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox